Author: "Service NEUROSPIN (NEUROSPIN)" - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"Service NEUROSPIN (NEUROSPIN)"' showing total 1,463 results

Start Over Author "Service NEUROSPIN (NEUROSPIN)"

1,463 results on '"Service NEUROSPIN (NEUROSPIN)"'

1. Wavelets in the Deep Learning Era

Author: Zaccharie Ramzi, Kevin Michalewicz, Jean-Luc Starck, Thomas Moreau, Philippe Ciuciu, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Astrophysique Interprétation Modélisation (AIM (UMR_7158 / UMR_E_9005 / UM_112)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modèles et inférence pour les données de Neuroimagerie (MIND), and IFR49 - Neurospin - CEA
Subjects: Statistics and Probability, Denoising, Neural Networks, Applied Mathematics, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Wavelets, Condensed Matter Physics, Machine Learning, Image restoration, Deep Learning, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0102 Applied Mathematics, Modeling and Simulation, 0801 Artificial Intelligence and Image Processing, Artificial Intelligence & Image Processing, Geometry and Topology, Computer Vision and Pattern Recognition, 0802 Computation Theory and Mathematics
Abstract: International audience; Sparsity-based methods, such as wavelets, have been the state of the art for more than 20 years for inverse problems before being overtaken by neural networks. In particular, U-nets have proven to be extremely effective. Their main ingredients are a highly nonlinear processing, a massive learning made possible by the flourishing of optimization algorithms with the power of computers (GPU) and the use of large available datasets for training. It is far from obvious to say which of these three ingredients has the biggest impact on the performance. While the many stages of nonlinearity are intrinsic to deep learning, the usage of learning with training data could also be exploited by sparsity-based approaches. The aim of our study is to push the limits of sparsity to use, similarly to U-nets, massive learning and large datasets, and then to compare the results with U-nets. We present a new network architecture, called learnlets, which conserves the properties of sparsity-based methods such as exact reconstruction and good generalization properties, while fostering the power of neural networks for learning and fast calculation. We evaluate the model on image denoising tasks. Our conclusion is that U-nets perform better than learnlets on image quality metrics in distribution, while learnlets have better generalization properties.
Published: 2022

2. Tissue outcome prediction in hyperacute ischemic stroke: Comparison of machine learning models

Author: Sylvain Charron, Guillaume Turc, Jean-Claude Baron, Joseph Benzakoun, Bertrand Thirion, Wagih Ben Hassen, Gregoire Boulouis, Catherine Oppenheim, Olivier Naggara, Laurence Legrand, Institut de psychiatrie et neurosciences de Paris (IPNP - U1266 Inserm), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Paris (UP), GHU Paris Psychiatrie et Neurosciences, Université de Paris - UFR Médecine Paris Centre [Santé] (UP Médecine Paris Centre), Université de Paris (UP), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris Cité (UPCité), UFR Médecine [Santé] - Université Paris Cité (UFR Médecine UPCité), Université Paris Cité (UPCité), Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: Male, Clinical Decision-Making, 030204 cardiovascular system & hematology, Machine learning, computer.software_genre, Machine Learning, 03 medical and health sciences, 0302 clinical medicine, Predictive Value of Tests, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Medicine, Acute ischemic stroke, Stroke, Aged, Ischemic Stroke, Retrospective Studies, Neuroradiology, Aged, 80 and over, business.industry, Penumbra, Brain, Original Articles, Middle Aged, Prognosis, medicine.disease, Patient management, Diffusion Magnetic Resonance Imaging, Neurology, Infarction, Reperfusion, Ischemic stroke, Female, Neurology (clinical), Artificial intelligence, Treatment decision making, Cardiology and Cardiovascular Medicine, Outcome prediction, business, computer, 030217 neurology & neurosurgery, Follow-Up Studies
Abstract: Machine Learning (ML) has been proposed for tissue fate prediction after acute ischemic stroke (AIS), with the aim to help treatment decision and patient management. We compared three different ML models to the clinical method based on diffusion-perfusion thresholding for the voxel-based prediction of final infarct, using a large MRI dataset obtained in a cohort of AIS patients prior to recanalization treatment. Baseline MRI (MRI0), including diffusion-weighted sequence (DWI) and Tmax maps from perfusion-weighted sequence, and 24-hr follow-up MRI (MRI24h) were retrospectively collected in consecutive 394 patients AIS patients (median age = 70 years; final infarct volume = 28mL). Manually segmented DWI24h lesion was considered the final infarct. Gradient Boosting, Random Forests and U-Net were trained using DWI, apparent diffusion coefficient (ADC) and Tmax maps on MRI0 as inputs to predict final infarct. Tissue outcome predictions were compared to final infarct using Dice score. Gradient Boosting had significantly better predictive performance (median [IQR] Dice Score as for median age, maybe you can replace the comma with an equal sign for consistency 0.53 [0.29–0.68]) than U-Net (0.48 [0.18–0.68]), Random Forests (0.51 [0.27–0.66]), and clinical thresholding method (0.45 [0.25–0.62]) ( P
Published: 2021

3. Optimizing full 3D SPARKLING trajectories for high-resolution T2*-weighted Magnetic Resonance Imaging

Author: R, Chaithya G, Weiss, Pierre, Daval-Fr��rot, Guillaume, Massire, Aur��lien, Vignaud, Alexandre, Ciuciu, Philippe, Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modèles et inférence pour les données de Neuroimagerie (MIND), IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Institut de Mathématiques de Toulouse UMR5219 (IMT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Université de Toulouse (UT)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS), PRIMO (ITAV), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut des Technologies Avancées en sciences du Vivant (ITAV), Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Centre National de la Recherche Scientifique (CNRS), Siemens Healthineers [Saint-Denis], Building large instruments for neuroimaging: from population imaging to ultra-high magnetic fields (BAOBAB), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Centre National de la Recherche Scientifique (CNRS), Chaithya Giliyar Radhakrishna was supported by the CEA NUMERICS PhD program, which received European funding from Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No800945.We acknowledge the financial support of the CrossDisciplinary Program on Numerical Simulation of CEA (SILICOSMIC project, PI: P. Ciuciu), the French Alternative Energies and Atomic Energy Commission. This work was granted access to the HPC resources of TGCC in France under the allocation 2019-GCH0424 made by GENCI. Pierre Weiss was supported by the ANR JCJC Optimization on Measures Spaces ANR-17-CE23-0013-01 and the ANR-3IA Artificial and Natural Intelligence Toulouse Institute., ANR-17-CE23-0013,OMS,Optimisation sur des espaces de mesures(2017), ANR-19-P3IA-0004,ANITI,Artificial and Natural Intelligence Toulouse Institute(2019), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National des Sciences Appliquées - Toulouse (INSA Toulouse), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut des Technologies Avancées en sciences du Vivant (ITAV), Centre National de la Recherche Scientifique (CNRS)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS), Unité Baobab (BAOBAB), and We acknowledge the financial support of the CrossDisciplinary Program on Numerical Simulation of CEA (SILICOSMIC project, PI: P. Ciuciu), the French Alternative Energies and Atomic Energy Commission. This work was granted access to the HPC resources of TGCC in France under the allocation 2019-GCH0424 made by GENCI. Pierre Weiss was supported by the ANR JCJC Optimization on Measures Spaces ANR-17-CE23-0013-01 and the ANR-3IA Artificial and Natural Intelligence Toulouse Institute.
Subjects: FOS: Computer and information sciences, 3D MRI, Computer Science - Distributed, Parallel, and Cluster Computing, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, non-Cartesian, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Distributed, Parallel, and Cluster Computing (cs.DC), acceleration, [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], [INFO.INFO-DC]Computer Science [cs]/Distributed, Parallel, and Cluster Computing [cs.DC], optimization, compressed sensing
Abstract: International audience; The Spreading Projection Algorithm for Rapid K-space samplING, or SPARKLING, is an optimization-driven method that has been recently introduced for accelerated 2D T2*-w MRI using compressed sensing. It has then been extended to address 3D imaging using either stacks of 2D sampling patterns or a local 3D strategy that optimizes a single sampling trajectory at a time. 2D SPARKLING actually performs variable density sampling (VDS) along a prescribed target density while maximizing sampling efficiency and meeting the gradient-based hardware constraints. However, 3D SPARKLING has remained limited in terms of acceleration factors along the third dimension if one wants to preserve a peaky point spread function (PSF) and thus good image quality.In this paper, in order to achieve higher acceleration factors in 3D imaging while preserving image quality, we propose a new efficient algorithm that performs optimization on full 3D SPARKLING. The proposed implementation based on fast multipole methods (FMM) allows us to design sampling patterns with up to 10^7 k-space samples, thus opening the door to 3D VDS. We compare multi-CPU and GPU implementations and demonstrate that the latter is optimal for 3D imaging in the high-resolution acquisition regime (600µm isotropic). Finally, we show that this novel optimization for full 3D SPARKLING outperforms stacking strategies or 3D twisted projection imaging through retrospective and prospective studies on NIST phantom and in vivo brain scans at 3 Tesla. Overall the proposed method allows for 2.5-3.75x shorter scan times compared to GRAPPA-4 parallel imaging acquisition at 3 Tesla without compromising image quality.
Published: 2022

4. Complex Coordinate-Based Meta-Analysis with Probabilistic Programming

Author: Valentin Iovene, Gaston Zanitti, Demian Wassermann, Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Université Paris-Saclay, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), European Project: 757672,H2020 Pilier ERC,NeuroLang(2018), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: FOS: Computer and information sciences, [SCCO]Cognitive science, Computer Science - Programming Languages, [INFO.INFO-PL]Computer Science [cs]/Programming Languages [cs.PL], Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], General Medicine, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Programming Languages (cs.PL)
Abstract: With the growing number of published functional magnetic resonance imaging (fMRI) studies, meta-analysis databases and models have become an integral part of brain mapping research. Coordinate-based meta-analysis (CBMA) databases are built by extracting both coordinates of reported peak activations and term associations using natural language processing techniques from neuroimaging studies. Solving term-based queries on these databases makes it possible to obtain statistical maps of the brain related to specific cognitive processes. However, existing tools for analysing CBMA data are limited in their expressivity to propositional logic, restricting the variety of their queries. Moreover, with tools like Neurosynth, term-based queries on multiple terms often lead to power failure, because too few studies from the database contribute to the statistical estimations. We design a probabilistic domain-specific language (DSL) standing on Datalog and one of its probabilistic extensions, CP-Logic, for expressing and solving complex logic-based queries. We show how CBMA databases can be encoded as probabilistic programs. Using the joint distribution of their Bayesian network translation, we show that solutions of queries on these programs compute the right probability distributions of voxel activations. We explain how recent lifted query processing algorithms make it possible to scale to the size of large neuroimaging data, where knowledge compilation techniques fail to solve queries fast enough for practical applications. Finally, we introduce a method for relating studies to terms probabilistically, leading to better solutions for two-term conjunctive queries (CQs) on smaller databases. We demonstrate results for two-term CQs, both on simulated meta-analysis databases and on the widely used Neurosynth database.
Published: 2021

5. DriPP: Driven point processes to model stimuli induced patterns in M/EEG signals

Author: Allain, Cédric, Gramfort, Alexandre, Moreau, Thomas, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay
Subjects: Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, [STAT.AP]Statistics [stat]/Applications [stat.AP], Mathematics - Statistics Theory, Statistics Theory (math.ST), Statistics - Applications, Machine Learning (cs.LG), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], FOS: Electrical engineering, electronic engineering, information engineering, FOS: Mathematics, Applications (stat.AP), Electrical Engineering and Systems Science - Signal Processing
Abstract: International audience; The quantitative analysis of non-invasive electrophysiology signals from electroencephalography (EEG) and magnetoencephalography (MEG) boils down to the identification of temporal patterns such as evoked responses, transient bursts of neural oscillations but also blinks or heartbeats for data cleaning. Several works have shown that these patterns can be extracted efficiently in an unsupervised way, e.g., using Convolutional Dictionary Learning. This leads to an event-based description of the data. Given these events, a natural question is to estimate how their occurrences are modulated by certain cognitive tasks and experimental manipulations. To address it, we propose a point process approach. While point processes have been used in neuroscience in the past, in particular for single cell recordings (spike trains), techniques such as Convolutional Dictionary Learning make them amenable to human studies based on EEG/MEG signals. We develop a novel statistical point process model-called driven temporal point processes (DriPP)-where the intensity function of the point process model is linked to a set of point processes corresponding to stimulation events. We derive a fast and principled expectation-maximization (EM) algorithm to estimate the parameters of this model. Simulations reveal that model parameters can be identified from long enough signals. Results on standard MEG datasets demonstrate that our methodology reveals event-related neural responses-both evoked and induced-and isolates non-task specific temporal patterns.
Published: 2022

6. Hybrid learning of Non-Cartesian k-space trajectory and MR image reconstruction networks

Author: Chaithya G R, Zaccharie Ramzi, Philippe Ciuciu, Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modèles et inférence pour les données de Neuroimagerie (MIND), IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Astrophysique Interprétation Modélisation (AIM (UMR_7158 / UMR_E_9005 / UM_112)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), IEEE, European Project: 800945,NUMERICS, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP)
Subjects: Signal Processing (eess.SP), acquisition, joint optimization, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Optimization and Control (math.OC), FOS: Electrical engineering, electronic engineering, information engineering, FOS: Mathematics, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], Electrical Engineering and Systems Science - Signal Processing, Mathematics - Optimization and Control, non-Cartesian trajectories, MRI
Abstract: International audience; Compressed sensing (CS) in Magnetic resonance Imaging (MRI) essentially involves the optimization of 1) the sampling pattern in k-space under MR hardware constraints and 2) image reconstruction from the undersampled k-space data. Recently, deep learning methods have allowed the community to address both problems simultaneously, especially in the non-Cartesian acquisition setting. This paper aims to contribute to this field by tackling some major concerns in existing approaches.Regarding the learning of the sampling pattern, we perform ablation studies using parameter-free reconstructions like the density compensated (DCp) adjoint operator of the nonuniform fast Fourier transform (NUFFT) to ensure that the learned k-space trajectories actually sample the center of k-space densely. Additionally we optimize these trajectories by embedding a projected gradient descent algorithm over the hardware MR constraints. Later, we introduce a novel hybrid learning approach that operates across multiple resolutions to jointly optimize the reconstruction network and the k-space trajectory and present improved image reconstruction quality at 20-fold acceleration factor on T1 and T2-weighted images on the fastMRI dataset with SSIM scores of nearly 0.92-0.95 in our retrospective studies.
Published: 2022

7. MC-PDNet: Deep Unrolled Neural Network For Multi-Contrast Mr Image Reconstruction From Undersampled K-Space Data

Author: Pooja, Kumari, Ramzi, Zaccharie, G R , Chaithya, Ciuciu, Philippe, Ciuciu, Philippe, Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Département d'Astrophysique (ex SAP) (DAP), Institut de Recherches sur les lois Fondamentales de l'Univers (IRFU), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Modèles et inférence pour les données de Neuroimagerie (MIND), IFR49 - Neurospin - CEA, and IEEE
Subjects: [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Multicontrast imaging, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, [INFO.INFO-NE] Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], Deep learning, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-NE]Computer Science [cs]/Neural and Evolutionary Computing [cs.NE], MRI reconstruction
Abstract: International audience; Multi-contrast (MC) MR images are similar in structure and can leverage anatomical structure to perform joint reconstruction especially from a limited number of k-space data in the Compressed Sensing (CS) setting. However CS-based multi-contrast image reconstruction has shown limited performance in these highly accelerated regimes due to the use of hand-crafted group sparsity priors. Deep learning can improve outcomes by learning the joint prior across multiple weighting contrasts. In this work, we extend the primal-dual neural network (PDNet) in the multi-contrast sense. We propose a MC-PDNet architecture which takes full advantage of multi-contrast information. Using an in-house database consisting of images from T2TSE, T2*GRE and FLAIR contrasts acquired in 65 healthy volunteers, we performed a retrospective study from 4fold under-sampled data. It was shown that MC-PDNet improves image quality by at least 1dB in PSNR for each contrast individually in comparison with PD-Net and U-Net architectures.
Published: 2022

8. Dark control: The default mode network as a reinforcement learning agent

Author: Danilo Bzdok, Guillaume Dumas, Elvis Dohmatob, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Criteo AI Lab, Criteo [Paris], IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Gènes, Synapses et Cognition (CNRS - UMR3571 ), Institut Pasteur [Paris] (IP)-Centre National de la Recherche Scientifique (CNRS), Centre de Bioinformatique, Biostatistique et Biologie Intégrative (C3BI), Génétique humaine et fonctions cognitives - Human Genetics and Cognitive Functions (GHFC (UMR_3571 / U-Pasteur_1)), Institut Pasteur [Paris] (IP)-Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS), Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), Montreal Neurological Hospital, McGill University Health Center [Montreal] (MUHC), McGill University = Université McGill [Montréal, Canada], Innovative Medicines Initiative, Grant/Award Number: 777394, Seventh Framework Programme, Grant/Award Number: 604102, Studienstiftung des Deutschen Volkes, Canada Institute for Advanced Research, Canada First Research Excellence fund, Exploratory Research Space, Grant/Award Number: OPSF449, START‐Program of the Faculty of Medicine, Grant/Award Number: 126/16, German National Merit Foundation, Amazon AWS Research Grant, International Research Training Group, Grant/Award Number: IRTG2150, Deutsche Forschungsgemeinschaft, Grant/Award Numbers: BZ2/4‐1, BZ2/3‐1, BZ2/2‐1, European Project: 604102,EC:FP7:ICT,FP7-ICT-2013-FET-F,HBP(2013), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Institut Pasteur [Paris]-Centre National de la Recherche Scientifique (CNRS), and Institut Pasteur [Paris]-Université Paris Diderot - Paris 7 (UPD7)-Centre National de la Recherche Scientifique (CNRS)
Subjects: Computer science, media_common.quotation_subject, human intelligence, systems neuroscience, Hippocampus, 050105 experimental psychology, Thinking, 03 medical and health sciences, [SCCO]Cognitive science, Executive Function, 0302 clinical medicine, Mind-wandering, Reinforcement learning, Humans, 0501 psychology and cognitive sciences, Radiology, Nuclear Medicine and imaging, Function (engineering), Default mode network, Research Articles, media_common, Cerebral Cortex, Radiological and Ultrasound Technology, [SCCO.NEUR]Cognitive science/Neuroscience, 05 social sciences, Perspective (graphical), Default Mode Network, mind-wandering, Models, Theoretical, Trial and error, artificial intelligence, Anticipation, Psychological, Markov Chains, Neurology, Action (philosophy), Neurology (clinical), Markov decision process, Anatomy, Reinforcement, Psychology, 030217 neurology & neurosurgery, Cognitive psychology, Research Article
Abstract: International audience; The default mode network (DMN) is believed to subserve the baseline mental activity in humans. Its higher energy consumption compared to other brain networks and its intimate coupling with conscious awareness are both pointing to an unknown overarching function. Many research streams speak in favor of an evolutionarily adaptive role in envisioning experience to anticipate the future. In the present work, we propose a process model that tries to explain how the DMN may implement continuous evaluation and prediction of the environment to guide behavior. The main purpose of DMN activity, we argue, may be described by Markov Decision Processes that optimize action policies via value estimates based through vicarious trial and error. Our formal perspective on DMN function naturally accommodates as special cases previous interpretations based on (1) predictive coding, (2) semantic associations, and (3) a sentinel role. Moreover, this process model for the neural optimization of complex behavior in the DMN offers parsimonious explanations for recent experimental findings in animals and humans.
Published: 2020

9. Benchmarking missing-values approaches for predictive models on health databases

Author: Alexandre Perez-Lebel, Gaël Varoquaux, Marine Le Morvan, Julie Josse, Jean-Baptiste Poline, McConnell Brain Imaging Centre (MNI), Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada]-McGill University = Université McGill [Montréal, Canada], McGill University = Université McGill [Montréal, Canada], Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria), Institut Desbrest de santé publique (IDESP), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Montpellier (UM), ANR-17-CE23-0018,DirtyData,Intégration et nettoyage de données pour l'analyse statistique(2017), ANR-16-IDEX-0006,MUSE,MUSE(2016), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Médecine de précision par intégration de données et inférence causale (PREMEDICAL), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Institut Desbrest de santé publique (IDESP), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Montpellier (UM)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Montpellier (UM), Perez-Lebel, Alexandre, Intégration et nettoyage de données pour l'analyse statistique - - DirtyData2017 - ANR-17-CE23-0018 - AAPG2017 - VALID, and MUSE - - MUSE2016 - ANR-16-IDEX-0006 - IDEX - VALID
Subjects: FOS: Computer and information sciences, [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Computer Science - Machine Learning, Databases, Factual, Computer Science - Artificial Intelligence, Data Collection, Health Informatics, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Benchmark, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Machine Learning (cs.LG), Computer Science Applications, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Benchmarking, Artificial Intelligence (cs.AI), [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Bagging, Machine learning, Multiple imputation, Electronic Health Records, Missing values, Supervised learning, Imputation
Abstract: BACKGROUND: As databases grow larger, it becomes harder to fully control their collection, and they frequently come with missing values: incomplete observations. These large databases are well suited to train machine-learning models, for instance for forecasting or to extract biomarkers in biomedical settings. Such predictive approaches can use discriminative -- rather than generative -- modeling, and thus open the door to new missing-values strategies. Yet existing empirical evaluations of strategies to handle missing values have focused on inferential statistics. RESULTS: Here we conduct a systematic benchmark of missing-values strategies in predictive models with a focus on large health databases: four electronic health record datasets, a population brain imaging one, a health survey and two intensive care ones. Using gradient-boosted trees, we compare native support for missing values with simple and state-of-the-art imputation prior to learning. We investigate prediction accuracy and computational time. For prediction after imputation, we find that adding an indicator to express which values have been imputed is important, suggesting that the data are missing not at random. Elaborate missing values imputation can improve prediction compared to simple strategies but requires longer computational time on large data. Learning trees that model missing values-with missing incorporated attribute-leads to robust, fast, and well-performing predictive modeling. CONCLUSIONS: Native support for missing values in supervised machine learning predicts better than state-of-the-art imputation with much less computational cost. When using imputation, it is important to add indicator columns expressing which values have been imputed., GigaScience, Oxford Univ Press, In press
Published: 2022

10. Implicit differentiation for fast hyperparameter selection in non-smooth convex learning

Author: Bertrand, Quentin, Klopfenstein, Quentin, Massias, Mathurin, Blondel, Mathieu, Vaiter, Samuel, Gramfort, Alexandre, Salmon, Joseph, Bertrand, Quentin, Apprentissage automatique et optimisation coopératifs. - - CAMELOT2020 - ANR-20-CHIA-0001 - PNIA - VALID, APPEL À PROJETS GÉNÉRIQUE 2018 - Méthodes variationnelles pour les signaux sur graphe - - GraVa2018 - ANR-18-CE40-0005 - AAPG2018 - VALID, Intelligence Artificielle et Neurosciences - - BrAIN2020 - ANR-20-CHIA-0016 - PNIA - VALID, Signal processing and Learning Applied to Brain data - SLAB - - H20202016-09-01 - 2021-08-31 - 676943 - VALID, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Institut de Mathématiques de Bourgogne [Dijon] (IMB), Université de Bourgogne (UB)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Centre National de la Recherche Scientifique (CNRS), Dipartimento di Informatica, Bioingegneria, Robotica e Ingegneria dei Sistemi [Genova] (DIBRIS), Università degli studi di Genova = University of Genoa (UniGe), Réseaux dynamiques : approche structurelle et temporelle (DANTE), Laboratoire de l'Informatique du Parallélisme (LIP), École normale supérieure de Lyon (ENS de Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure de Lyon (ENS de Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Institut Rhône-Alpin des systèmes complexes (IXXI), École normale supérieure de Lyon (ENS de Lyon)-Université Lumière - Lyon 2 (UL2)-Université Jean Moulin - Lyon 3 (UJML), Université de Lyon-Université de Lyon-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Université Lumière - Lyon 2 (UL2)-Université Jean Moulin - Lyon 3 (UJML), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Inria Lyon, Institut National de Recherche en Informatique et en Automatique (Inria), Google Research [Paris], Institut Montpelliérain Alexander Grothendieck (IMAG), Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM), Financial support of the European Research Council (grant SLING 819789)., ANR-20-CHIA-0001,CAMELOT,Apprentissage automatique et optimisation coopératifs.(2020), ANR-18-CE40-0005,GraVa,Méthodes variationnelles pour les signaux sur graphe(2018), ANR-20-CHIA-0016,BrAIN,Intelligence Artificielle et Neurosciences(2020), European Project: 676943,H2020,SLAB(2016), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université de Bourgogne (UB), Universita degli studi di Genova, Brain team [Paris], Research at Google, Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Université de Bourgogne (UB)-Centre National de la Recherche Scientifique (CNRS)-Université de Franche-Comté (UFC), and Université Bourgogne Franche-Comté [COMUE] (UBFC)-Université Bourgogne Franche-Comté [COMUE] (UBFC)
Subjects: FOS: Computer and information sciences, bilevel optimization, Computer Science - Machine Learning, hyperparameter selec- tion, Machine Learning (stat.ML), [MATH.MATH-OC] Mathematics [math]/Optimization and Control [math.OC], generalized linear models, Machine Learning (cs.LG), Convex optimization, Statistics - Machine Learning, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Optimization and Control (math.OC), FOS: Mathematics, [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], hyperparameter optimization, Lasso, Mathematics - Optimization and Control, [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST]
Abstract: International audience; Finding the optimal hyperparameters of a model can be cast as a bilevel optimization problem, typically solved using zero-order techniques. In this work we study first-order methods when the inner optimization problem is convex but non-smooth. We show that the forward-mode differentiation of proximal gradient descent and proximal coordinate descent yield sequences of Jacobians converging toward the exact Jacobian. Using implicit differentiation, we show it is possible to leverage the non-smoothness of the inner problem to speed up the computation. Finally, we provide a bound on the error made on the hypergradient when the inner optimization problem is solved approximately. Results on regression and classification problems reveal computational benefits for hyperparameter optimization, especially when multiple hyperparameters are required.
Published: 2022

11. Variable Importance on Medical Images and Socio-Demographic Data

Author: CHAMMA, Ahmad, Engemann, Denis, Thirion, Bertrand, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), CEA- Saclay (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Université Paris-Saclay, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Published: 2021

12. Electromagnetic neural source imaging under sparsity constraints with SURE-based hyperparameter tuning

Author: Bannier, Pierre-Antoine, Bertrand, Quentin, Salmon, Joseph, Gramfort, Alexandre, Université Paris-Saclay, CEA- Saclay (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Institut Montpelliérain Alexander Grothendieck (IMAG), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Université de Montpellier (UM), Centre National de la Recherche Scientifique (CNRS), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: Signal Processing (eess.SP), Optimization and Control (math.OC), [SCCO.NEUR]Cognitive science/Neuroscience, Image and Video Processing (eess.IV), FOS: Electrical engineering, electronic engineering, information engineering, FOS: Mathematics, Electrical Engineering and Systems Science - Image and Video Processing, Electrical Engineering and Systems Science - Signal Processing, Mathematics - Optimization and Control, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: International audience; Estimators based on non-convex sparsity-promoting penalties were shown to yield state-of-the-art solutions to the magneto-/electroencephalography (M/EEG) brain source localization problem. In this paper we tackle the model selection problem of these estimators: we propose to use a proxy of the Stein's Unbiased Risk Estimator (SURE) to automatically select their regularization parameters. The effectiveness of the method is demonstrated on realistic simulations and 30 subjects from the Cam-CAN dataset. To our knowledge, this is the first time that sparsity promoting estimators are automatically calibrated at such a scale. Results show that the proposed SURE approach outperforms cross-validation strategies and state-of-the-art Bayesian statistics methods both computationally and statistically.
Published: 2021

13. HNPE: Leveraging Global Parameters for Neural Posterior Estimation

Author: Coelho Rodrigues, Pedro Luiz, Moreau, Thomas, Louppe, Gilles, Gramfort, Alexandre, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Université de Liège, Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, FOS: Biological sciences, Machine Learning (stat.ML), Quantitative Biology - Quantitative Methods, Quantitative Methods (q-bio.QM), Machine Learning (cs.LG)
Abstract: Inferring the parameters of a stochastic model based on experimental observations is central to the scientific method. A particularly challenging setting is when the model is strongly indeterminate, i.e. when distinct sets of parameters yield identical observations. This arises in many practical situations, such as when inferring the distance and power of a radio source (is the source close and weak or far and strong?) or when estimating the amplifier gain and underlying brain activity of an electrophysiological experiment. In this work, we present hierarchical neural posterior estimation (HNPE), a novel method for cracking such indeterminacy by exploiting additional information conveyed by an auxiliary set of observations sharing global parameters. Our method extends recent developments in simulation-based inference (SBI) based on normalizing flows to Bayesian hierarchical models. We validate quantitatively our proposal on a motivating example amenable to analytical solutions and then apply it to invert a well known non-linear model from computational neuroscience, using both simulated and real EEG data.
Published: 2021

14. Shared Independent Component Analysis for Multi-Subject Neuroimaging

Author: Hugo Richard, Pierre Ablin, Bertrand Thirion, Alexandre Gramfort, Aapo Hyvarinen, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Centre National de la Recherche Scientifique (CNRS), Département de Mathématiques et Applications - ENS Paris (DMA), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS), Helsingin yliopisto = Helsingfors universitet = University of Helsinki, Ranzato, M, Beygelzimer, A, Nguyen, K, Liang, P S, Vaughan, J W, Dauphin, Y, Department of Computer Science, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, École normale supérieure - Paris (ENS Paris), University of Helsinki, Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL), and Richard, Hugo
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], FOS: Computer and information sciences, Computer Science - Machine Learning, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], education, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, 3112 Neurosciences, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], 113 Computer and information sciences, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: We consider shared response modeling, a multi-view learning problem where one wants to identify common components from multiple datasets or views. We introduce Shared Independent Component Analysis (ShICA) that models each view as a linear transform of shared independent components contaminated by additive Gaussian noise. We show that this model is identifiable if the components are either non-Gaussian or have enough diversity in noise variances. We then show that in some cases multi-set canonical correlation analysis can recover the correct unmixing matrices, but that even a small amount of sampling noise makes Multiset CCA fail. To solve this problem, we propose to use joint diagonalization after Multiset CCA, leading to a new approach called ShICA-J. We show via simulations that ShICA-J leads to improved results while being very fast to fit. While ShICA-J is based on second-order statistics, we further propose to leverage non-Gaussianity of the components using a maximum-likelihood method, ShICA-ML, that is both more accurate and more costly. Further, ShICA comes with a principled method for shared components estimation. Finally, we provide empirical evidence on fMRI and MEG datasets that ShICA yields more accurate estimation of the components than alternatives., Comment: Accepted at NeurIPS 2021
Published: 2021

15. AI as statistical methods for imperfect theories

Author: Varoquaux, Gaël, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), ANR-17-CE23-0018,DirtyData,Intégration et nettoyage de données pour l'analyse statistique(2017), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: [SHS.HISPHILSO]Humanities and Social Sciences/History, Philosophy and Sociology of Sciences, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], [PHYS.PHYS.PHYS-DATA-AN]Physics [physics]/Physics [physics]/Data Analysis, Statistics and Probability [physics.data-an]
Abstract: International audience; Science has progressed by reasoning on what models could not predict because they were missing important ingredients. And yet without correct models, standard statistical methods for scientific evidence are not sound. Here, I argue that machine-learning methodology provides solutions to ground reasoning about empirically evidence more on models’ predictions, and less on their ingredients.
Published: 2021

16. Inverting brain grey matter models with likelihood-free inference: a tool for trustable cytoarchitecture measurements

Author: Maëliss Jallais, Pedro L. C. Rodrigues, Alexandre Gramfort, Demian Wassermann, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Modèles statistiques bayésiens et des valeurs extrêmes pour données structurées et de grande dimension (STATIFY), Inria Grenoble - Rhône-Alpes, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK), Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), Université Grenoble Alpes (UGA), Modèles et inférence pour les données de Neuroimagerie (MIND), IFR49 - Neurospin - CEA, ANR-20-CHIA-0016,BrAIN,Intelligence Artificielle et Neurosciences(2020), European Project: 757672,H2020 Pilier ERC,NeuroLang(2018), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, Likelihood-Free Inference, [SCCO.NEUR]Cognitive science/Neuroscience, Quantitative Biology - Quantitative Methods, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, Machine Learning (cs.LG), Diffusion MRI, [STAT]Statistics [stat], [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], FOS: Biological sciences, Brain Microstructure, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Quantitative Methods (q-bio.QM)
Abstract: International audience; Effective characterisation of the brain grey matter cytoarchitecture with quantitative sensitivity to soma density and volume remains an unsolved challenge in diffusion MRI (dMRI). Solving the problem of relating the dMRI signal with cytoarchitectural characteristics calls for the definition of a mathematical model that describes brain tissue via a handful of physiologically-relevant parameters and an algorithm for inverting the model. To address this issue, we propose a new forward model, specifically a new system of equations, requiring a few relatively sparse b-shells. We then apply modern tools from Bayesian analysis known as likelihood-free inference (LFI) to invert our proposed model. As opposed to other approaches from the literature, our algorithm yields not only an estimation of the parameter vector θ that best describes a given observed data point x_0 , but also a full posterior distribution p(θ|x_0) over the parameter space. This enables a richer description of the model inversion, providing indicators such as credible intervals for the estimated parameters and a complete characterization of the parameter regions where the model may present indeterminacies. We approximate the posterior distribution using deep neural density estimators, known as normalizing flows, and fit them using a set of repeated simulations from the forward model. We validate our approach on simulations using dmipy and then apply the whole pipeline on two publicly available datasets.
Published: 2021

17. Numerical uncertainty in analytical pipelines lead to impactful variability in brain networks

Author: Gaël Varoquaux, de Oliveira Castro P, Alan C. Evans, Eric Petit, Gregory Kiar, Bratislav Misic, Yohan Chatelain, Tristan Glatard, Ariel Rokem, Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada], Concordia University [Montreal], Laboratoire d'Informatique Parallélisme Réseaux Algorithmes Distribués (LI-PaRAD), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ), Intel France [Meudon], University of Washington [Seattle], Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), McConnell Brain Imaging Centre (MNI), McGill University = Université McGill [Montréal, Canada]-McGill University = Université McGill [Montréal, Canada], Laboratoire Exascale Computing Research (ERC), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Intel France [Meudon], This research was financially supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) (award no. CGSD3-519497-2018). This work was also supported in part by funding provided by Brain Canada, in partner ship with Health Canada, for the Canadian Open Neuroscience Platform initiative, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay
Subjects: Computer science, Pipeline (computing), computer.software_genre, Nervous System, Infographics, 0302 clinical medicine, Range (statistics), Medicine and Health Sciences, Instrumentation, Reliability (statistics), Data Management, 0303 health sciences, Brain Mapping, Multidisciplinary, Uncertainty, Software Engineering, Brain, Variance (accounting), Reproducibility, Physical Sciences, Connectome, Medicine, Engineering and Technology, Data mining, Anatomy, Stability, Graphs, Network Analysis, Network analysis, Research Article, Statistical Distributions, Connectomics, Computer and Information Sciences, Neural Networks, Imaging Techniques, Science, Models, Neurological, Stability (learning theory), Context (language use), Neuroimaging, Research and Analysis Methods, Stability (probability), Computer Software, 03 medical and health sciences, Robustness (computer science), [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, 030304 developmental biology, Data Visualization, Biology and Life Sciences, Probability Theory, Noise, Neuroanatomy, Nerve Net, Network Neuroscience, computer, 030217 neurology & neurosurgery, Mathematics, Neuroscience
Abstract: The analysis of brain-imaging data requires complex and often non-linear transformations to support findings on brain function or pathologies. And yet, recent work has shown that variability in the choices that one makes when analyzing data can lead to quantitatively and qualitatively different results, endangering the trust in conclusions1–3. Even within a given method or analytical technique, numerical instabilities could compromise findings4–7. We instrumented a structural-connectome estimation pipeline with Monte Carlo Arithmetic8, 9, a technique to introduce random noise in floating-point computations, and evaluated the stability of the derived connectomes, their features10, 11, and the impact on a downstream analysis12, 13. The stability of results was found to be highly dependent upon which features of the connectomes were evaluated, and ranged from perfectly stable (i.e. no observed variability across executions) to highly unstable (i.e. the results contained no trustworthy significant information). While the extreme range and variability in results presented here could severely hamper our understanding of brain organization in brain-imaging studies, it also leads to an increase in the reliability of datasets. This paper highlights the potential of leveraging the induced variance in estimates of brain connectivity to reduce the bias in networks alongside increasing the robustness of their applications in the detection or classification of individual differences. This paper demonstrates that stability evaluations are necessary for understanding error and bias inherent to scientific computing, and that they should be a component of typical analytical workflows.
Published: 2021

18. An empirical evaluation of functional alignment using inter-subject decoding

Author: Jean-Baptiste Poline, Thomas Bazeille, Bertrand Thirion, Elizabeth DuPre, Hugo Richard, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada], Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay
Subjects: Computer science, Cognitive Neuroscience, Neurosciences. Biological psychiatry. Neuropsychiatry, Machine learning, computer.software_genre, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, 0302 clinical medicine, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Humans, 030304 developmental biology, inter-subject variability, 0303 health sciences, Brain Mapping, business.industry, fMRI, Brain, Usability, Magnetic Resonance Imaging, Variable (computer science), Range (mathematics), functional alignment, Neurology, Scalability, Benchmark (computing), Piecewise, Artificial intelligence, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], business, Neural coding, computer, predictive modeling, 030217 neurology & neurosurgery, Decoding methods, Algorithms, RC321-571
Abstract: Inter-individual variability in the functional organization of the brain presents a major obstacle to identifying generalizable neural coding principles. Functional alignment—a class of methods that matches subjects’ neural signals based on their functional similarity—is a promising strategy for addressing this variability. To date, however, a range of functional alignment methods have been proposed and their relative performance is still unclear. In this work, we benchmark five functional alignment methods for inter-subject decoding on four publicly available datasets. Specifically, we consider three existing methods: piecewise Procrustes, searchlight Procrustes, and piecewise Optimal Transport. We also introduce and benchmark two new extensions of functional alignment methods: piecewise Shared Response Modelling (SRM), and intra-subject alignment. We find that functional alignment generally improves inter-subject decoding accuracy though the best performing method depends on the research context. Specifically, SRM and Optimal Transport perform well at both the region-of-interest level of analysis as well as at the whole-brain scale when aggregated through a piecewise scheme. We also benchmark the computational efficiency of each of the surveyed methods, providing insight into their usability and scalability. Taking inter-subject decoding accuracy as a quantification of inter-subject similarity, our results support the use of functional alignment to improve inter-subject comparisons in the face of variable structure-function organization. We provide open implementations of all methods used.
Published: 2021

19. ADAVI: Automatic Dual Amortized Variational Inference Applied To Pyramidal Bayesian Models

Author: Rouillard, Louis, Wassermann, Demian, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Institut National de Recherche en Informatique et en Automatique (Inria), CEA- Saclay (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Université Paris-Saclay, European Project: 757672,H2020 Pilier ERC,NeuroLang(2018), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Artificial Intelligence, [INFO.INFO-DS]Computer Science [cs]/Data Structures and Algorithms [cs.DS], Machine Learning (stat.ML), [STAT.TH]Statistics [stat]/Statistics Theory [stat.TH], Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [MATH.MATH-PR]Mathematics [math]/Probability [math.PR], Artificial Intelligence (cs.AI), [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, FOS: Biological sciences, Quantitative Biology - Neurons and Cognition, Neurons and Cognition (q-bio.NC), [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], [STAT.ME]Statistics [stat]/Methodology [stat.ME]
Abstract: Preprint submitted to ICLR 2022; International audience; Frequently, population studies feature pyramidally-organized data represented using Hierarchical Bayesian Models (HBM) enriched with plates.These models can become prohibitively large in settings such as neuroimaging, where a sample is composed of a functional MRI signal measured on 64 thousand brain locations, across 4 measurement sessions, and at least tens of subjects. Even a reduced example on a specific cortical region of 300 brain locations features around 1 million parameters, hampering the usage of modern density estimation techniques such as Simulation-Based Inference (SBI) or structured Variational Inference (VI).To infer parameter posterior distributions in this challenging class of problems, we designed a novel methodology that automatically produces a variational family dual to a target HBM. This variational family, represented as a neural network, consists in the combination of an attention-based hierarchical encoder feeding summary statistics to a set of normalizing flows. Our automatically-derived neural network exploits exchangeability in the plate-enriched HBM and factorizes its parameter space. The resulting architecture reduces by orders of magnitude its parameterization with respect to that of a typical SBI or structured VI representation, while maintaining expressivity.Our method performs inference on the specified HBM in an amortized setup: once trained, it can readily be applied to a new data sample to compute the parameters' full posterior.We demonstrate the capability and scalability of our method on simulated data, as well as a challenging high-dimensional brain parcellation experiment. We also open up several questions that lie at the intersection between SBI techniques, structured Variational Inference, and inference amortization.
Published: 2021

20. Inferring the Localization of White-Matter Tracts using Diffusion Driven Label Fusion

Author: Gallardo, Guillermo, Zanitti, Gaston, Higger, Mat, Bouix, Sylvain, Wassermann, Demian, Max Planck Institute for Human Cognitive and Brain Sciences [Leipzig] (IMPNSC), Max-Planck-Gesellschaft, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Psychiatry Neuroimaging Laboratory (PNL), Brigham and Women's Hospital [Boston], ANR-16-NEUC-0002,NeuroRef,Building Normative Atlases of Diffusion MRI to Identify Subject-Specific Neuroimaging Abnormalities in Brain Trauma and Post-Traumatic Stress(2016), Computational Imaging of the Central Nervous System (ATHENA), Inria Sophia Antipolis - Méditerranée (CRISAM), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay
Subjects: FOS: Biological sciences, [SCCO.NEUR]Cognitive science/Neuroscience, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], Quantitative Biology - Quantitative Methods, Quantitative Methods (q-bio.QM)
Abstract: Inferring which pathways are affected by a brain lesion is key for both pre and post-treatment planning. However, many disruptive lesions cause changes in the tissue that interrupt tractography algorithms. In such cases, aggregating information from healthy subjects can provide a solution to inferring the affected pathways. In this paper, we introduce a novel label fusion technique that leverages diffusion information to locate brain pathways. Through simulations and experiments in publicly available data we show that our method is able to correctly reconstruct brain pathways, even if they are affected by a focal lesion.
Published: 2021

21. Hyperparameter selection for high dimensional sparse learning : application to neuroimaging

Author: Bertrand, Quentin, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria), IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Université Paris-Saclay, Alexandre Gramfort, Joseph Salmon, STAR, ABES, Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: Coordinate descent, Parcimonie, Selection et optimisation d'hyperparamètre, Hyperparameter selection and optimization, Neuroimaging, Descente par coordonnée, Convex optimization, Neuroimagerie, Optimisation bi-niveaux, Problèmes inverses, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Inverse problem, [MATH.MATH-ST] Mathematics [math]/Statistics [math.ST], Sparsity
Abstract: Due to non-invasiveness and excellent time resolution, magneto- and electroencephalography (M/EEG) have emerged as tools of choice to monitor brain activity. Reconstructing brain signals from M/EEG measurements can be cast as a high dimensional ill-posed inverse problem. Typical estimators of brain signals involve challenging optimization problems, composed of the sum of a data-fidelity term, and a sparsity promoting term. Because of their notoriously hard to tune regularization hyperparameters, sparsity-based estimators are currently not massively used by practitioners. The goal of this thesis is to provide a simple, fast, and automatic way to calibrate sparse linear models. We first study some properties of coordinate descent: model identification, local linear convergence, and acceleration. Relying on Anderson extrapolation schemes, we propose an effective way to speed up coordinate descent in theory and practice. We then explore a statistical approach to set the regularization parameter of Lasso-type problems. A closed-form formula can be derived for the optimal regularization parameter of L1 penalized linear regressions. Unfortunately, it relies on the true noise level, unknown in practice. To remove this dependency, one can resort to estimators for which the regularization parameter does not depend on the noise level. However, they require to solve challenging "nonsmooth + nonsmooth" optimization problems. We show that partial smoothing preserves their statistical properties and we propose an application to M/EEG source localization problems. Finally we investigate hyperparameter optimization, encompassing held-out or cross-validation hyperparameter selection. It requires tackling bilevel optimization with nonsmooth inner problems. Such problems are canonically solved using zeros order techniques, such as grid-search or random-search. We present an efficient technique to solve these challenging bilevel optimization problems using first-order methods., Grâce à leur caractère non invasif et leur excellente résolution temporelle, la magnéto- et l'électroencéphalographie (M/EEG) sont devenues des outils incontournables pour observer l'activité cérébrale. La reconstruction des signaux cérébraux à partir des enregistrements M/EEG peut être vue comme un problème inverse de grande dimension mal posé. Les estimateurs typiques des signaux cérébraux se basent sur des problèmes d'optimisation difficiles à résoudre, composés de la somme d'un terme d'attache aux données et d'un terme favorisant la parcimonie. À cause du paramètre de régularisation notoirement difficile à calibrer, les estimateurs basés sur la parcimonie ne sont actuellement pas massivement utilisés par les praticiens. L'objectif de cette thèse est de fournir un moyen simple, rapide et automatisé de calibrer des modèles linéaires parcimonieux. Nous étudions d'abord quelques propriétés de la descente par coordonnées : identification du modèle, convergence linéaire locale, et accélération. En nous appuyant sur les schémas d'extrapolation d'Anderson, nous proposons un moyen efficace d'accélérer la descente par coordonnées en théorie et en pratique. Nous explorons ensuite une approche statistique pour calibrer le paramètre de régularisation des problèmes de type Lasso. Il est possible de construire des estimateurs pour lesquels le paramètre de régularisation optimal ne dépend pas du niveau de bruit. Cependant, ces estimateurs nécessitent de résoudre des problèmes d'optimisation "non lisses + non lisses". Nous montrons que le lissage partiel préserve leurs propriétés statistiques et nous proposons une application aux problèmes de localisation de sources M/EEG. Enfin, nous étudions l'optimisation d'hyperparamètres, qui comprend notamment la validation croisée. Cela nécessite de résoudre des problèmes d'optimisation à deux niveaux avec des problèmes internes non lisses. De tels problèmes sont résolus de manière usuelle via des techniques d'ordre zéro, telles que la recherche sur grille ou la recherche aléatoire. Nous présentons une technique efficace pour résoudre ces problèmes d'optimisation à deux niveaux en utilisant des méthodes du premier ordre.
Published: 2021

22. Functional Magnetic Resonance Imaging data augmentation through conditional ICA

Author: Bertrand Thirion, Hugo Richard, Badr Tajini, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer science, Test data generation, [SCCO.COMP]Cognitive science/Computer science, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, 0302 clinical medicine, Neuroimaging, Sampling (signal processing), [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Functional neuroimaging, medicine, FOS: Electrical engineering, electronic engineering, information engineering, 030304 developmental biology, 0303 health sciences, medicine.diagnostic_test, business.industry, Image and Video Processing (eess.IV), Pattern recognition, Electrical Engineering and Systems Science - Image and Video Processing, Independent component analysis, 3. Good health, Conditional ICA, Decoding studies, Artificial intelligence, Data generation, Functional magnetic resonance imaging, business, 030217 neurology & neurosurgery, Decoding methods, Generator (mathematics)
Abstract: Advances in computational cognitive neuroimaging research are related to the availability of large amounts of labeled brain imaging data, but such data are scarce and expensive to generate. While powerful data generation mechanisms, such as Generative Adversarial Networks (GANs), have been designed in the last decade for computer vision, such improvements have not yet carried over to brain imaging. A likely reason is that GANs training is ill-suited to the noisy, high-dimensional and small-sample data available in functional neuroimaging. In this paper, we introduce Conditional Independent Components Analysis (Conditional ICA): a fast functional Magnetic Resonance Imaging (fMRI) data augmentation technique, that leverages abundant resting-state data to create images by sampling from an ICA decomposition. We then propose a mechanism to condition the generator on classes observed with few samples. We first show that the generative mechanism is successful at synthesizing data indistinguishable from observations, and that it yields gains in classification accuracy in brain decoding problems. In particular it outperforms GANs while being much easier to optimize and interpret. Lastly, Conditional ICA enhances classification accuracy in eight datasets without further parameters tuning., Comment: 14 pages, 5 figures, 7 tables
Published: 2021

23. Clinical Characteristics, Care Trajectories and Mortality Rate of SARS-CoV-2 Infected Cancer Patients: A Multicenter Cohort Study

Author: Benderra, Marc-Antoine, Aparicio, Ainhoa, Leblanc, Judith, Wassermann, Demian, Kempf, Emmanuelle, Galula, Gilles, Bernaux, Mélodie, Canellas, Anthony, Moreau, Thomas, Bellamine, Ali, Spano, Jean-Philippe, Daniel, Christel, Champ, Julien, Canouï-Poitrine, Florence, Gligorov, Joseph, Research, on Behalf of the AP-HP/Universities/INSERM COVID, Task, Cancer AP-HP Group COVID, Initiative, AP-HP Covid CDW, CHU Tenon [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), IMRB - CEPIA/'Clinical Epidemiology And Ageing : Geriatrics, Primary Care and Public Health' [Créteil] (U955 Inserm - UPEC), Institut Mondor de Recherche Biomédicale (IMRB), Institut National de la Santé et de la Recherche Médicale (INSERM)-IFR10-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12)-Institut National de la Santé et de la Recherche Médicale (INSERM)-IFR10-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), Institut Pierre Louis d'Epidémiologie et de Santé Publique (iPLESP), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Service d'Oncologie médicale [CHU Henri Mondor], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-CHU Henri Mondor [Créteil], Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé (LIMICS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Sorbonne Paris Nord, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Institut Universitaire de Cancérologie [Sorbonne Université] (IUC), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), Scientific Data Management (ZENITH), Laboratoire d'Informatique de Robotique et de Microélectronique de Montpellier (LIRMM), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de la Santé et de la Recherche Médicale (INSERM)-IFR10-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), Service d'Oncologie médicale [CHU Tenon], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-CHU Henri Mondor, Institut Universitaire de Cancérologie [Paris] (IUC), Gestionnaire, HAL Sorbonne Université 5, Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), Sorbonne Université (SU)-Institut National de la Santé et de la Recherche Médicale (INSERM), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), and Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS)-Université de Montpellier (UM)-Inria Sophia Antipolis - Méditerranée (CRISAM)
Subjects: Cancer Research, medicine.medical_specialty, Multivariate analysis, Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), [SDV.CAN]Life Sciences [q-bio]/Cancer, mortality rate, Article, law.invention, 03 medical and health sciences, 0302 clinical medicine, [SDV.CAN] Life Sciences [q-bio]/Cancer, law, Internal medicine, Medicine, cancer, Lung cancer, RC254-282, 030304 developmental biology, [SDV.MP.VIR] Life Sciences [q-bio]/Microbiology and Parasitology/Virology, 0303 health sciences, business.industry, Mortality rate, SARS-CoV-2 infection, Neoplasms. Tumors. Oncology. Including cancer and carcinogens, Cancer, medicine.disease, Intensive care unit, 3. Good health, multicenter study, Oncology, 030220 oncology & carcinogenesis, Cohort, [SDV.MP.VIR]Life Sciences [q-bio]/Microbiology and Parasitology/Virology, business, hospitals, Cohort study
Abstract: Background: COVID-19 may be more frequent and more severe in cancer patients than in other individuals. Our aims were to assess the rate of COVID-19 in hospitalized cancer patients, to describe their demographic characteristics, clinical features and care trajectories, and to assess the mortality rate. Methods: This multicenter cohort study was based on the Electronic Health Records of the Assistance Publique-Hôpitaux de Paris (AP-HP). Cancer patients with a diagnosis of COVID-19 between 3 March and 19 May 2020 were included. Main outcome was all-cause mortality within 30 days of COVID-19 diagnosis. Results: A total of 29,141 cancer patients were identified and 7791 (27%) were tested for SARS-CoV-2. Of these, 1359 (17%) were COVID-19-positive and 1148 (84%) were hospitalized, 217 (19%) were admitted to an intensive care unit. The mortality rate was 33% (383 deaths). In multivariate analysis, mortality-related factors were male sex (aHR = 1.39 [95% CI: 1.07–1.81]), advanced age (78–86 y: aHR = 2.83 [95% CI: 1.78–4.51] vs. &lt, 66 y, 86–103 y: aHR = 2.61 [95% CI: 1.56–4.35] vs. &lt, 66 y), more than two comorbidities (aHR = 2.32 [95% CI: 1.41–3.83]) and C-reactive protein &gt, 20 ng/mL (aHR = 2.20 [95% CI: 1.70–2.86]). Primary brains tumors (aHR = 2.19 [95% CI: 1.08–4.44]) and lung cancer (aHR = 1.66 [95% CI: 1.02–2.70]) were associated with higher mortality. Risk of dying was lower among patients with metabolic comorbidities (aHR = 0.65 [95% CI: 0.50–0.84]). Conclusions: In a hospital-based setting, cancer patients with COVID-19 had a high mortality rate. This mortality was mainly driven by age, sex, number of comorbidities and presence of inflammation. This is the first cohort of cancer patients in which metabolic comorbidities were associated with a better outcome.
Published: 2021

24. NC-PDNet: a Density-Compensated Unrolled Network for 2D and 3D non-Cartesian MRI Reconstruction

Author: Jean-Luc Starck, Chaithya G R, Philippe Ciuciu, Zaccharie Ramzi, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Service NEUROSPIN (NEUROSPIN), Astrophysique Interprétation Modélisation (AIM (UMR_7158 / UMR_E_9005 / UM_112)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP), We acknowledge the financial support of the CrossDisciplinary Program on Numerical Simulation of CEA for the project entitled SILICOSMIC. We also acknowledge the French Institute of development and resources in scientific computing (IDRIS) for their AI program allowing us to usethe Jean Zay supercomputer’s GPU partitions., Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), Modèles et inférence pour les données de Neuroimagerie (MIND), and IFR49 - Neurospin - CEA
Subjects: Radiological and Ultrasound Technology, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Brain, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], Signal-To-Noise Ratio, Magnetic Resonance Imaging, Computer Science Applications, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [INFO.INFO-TI]Computer Science [cs]/Image Processing [eess.IV], Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Neural Networks, Computer, Electrical and Electronic Engineering, Software
Abstract: This work is an extended version of the work presented at the 2021 ISBI conference.; International audience; Deep Learning has become a very promising avenue for magnetic resonance image (MRI) reconstruction. In this work, we explore the potential of unrolled networks for the non-Cartesian acquisition setting. We design the NC-PDNet, the first density-compensated unrolled network and validate the need for its key components via an ablation study. Moreover, we conduct some generalizability experiments to test our network in out-of-distribution settings, for example training on knee data and validating on brain data. The results show that the NC-PDNet outperforms the baseline models visually and quantitatively in the 2D settings. Additionally, in the 3D settings, it outperforms them visually. In particular, in the 2D multi-coil acquisition scenario, the NC-PDNet provides up to a 1.2 dB improvement in peak signal-to-noise ratio (PSNR) over baseline networks, while also allowing a gain of at least 1 dB in PSNR in generalization settings. We provide the opensource implementation of our network, and in particular the Non-uniform Fourier Transform in TensorFlow, tested on 2D multi-coil and 3D data.
Published: 2021

25. Preventing dataset shift from breaking machine-learning biomarkers

Author: Gaël Varoquaux, Jean-Baptiste Poline, Jéroôme Dockès, McGill University = Université McGill [Montréal, Canada], Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), This work was partially funded by DirtyData - ANR-17-CE23-0018, the National Institutes of Health (NIH) NIH-NIBIB P41 EB019936 (ReproNim) NIH-NIMH R01 MH083320 (CANDIShare) and NIH RF1 MH120021 (NIDM), the National Institute Of Mental Health under Award Number R01MH096906 (Neurosynth), the Canada First Research Excellence Fund, awarded to McGill University for the Healthy Brains for Healthy Lives initiative and the Brain Canada Foundation with support from Health Canada, Health Canada, through the Canada Brain Research Fund in partnership with the Montreal Neurological Institute., ANR-17-CE23-0018,DirtyData,Intégration et nettoyage de données pour l'analyse statistique(2017), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, Domain adaptation, Computer science, domain adaptation, precision medicine, AcademicSubjects/SCI02254, dataset shift, Mathematics - Statistics Theory, Health Informatics, Statistics Theory (math.ST), Target population, Review, Machine learning, computer.software_genre, Quantitative Biology - Quantitative Methods, Machine Learning (cs.LG), Predictive medicine, predictive medicine, Machine Learning, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], FOS: Mathematics, Humans, 030212 general & internal medicine, Quantitative Methods (q-bio.QM), generalization, 030304 developmental biology, 0303 health sciences, business.industry, Precision medicine, [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM], Computer Science Applications, ComputingMethodologies_PATTERNRECOGNITION, FOS: Biological sciences, Biomarker (medicine), AcademicSubjects/SCI00960, biomarker, Artificial intelligence, business, computer, Algorithms, Biomarkers
Abstract: Machine learning brings the hope of finding new biomarkers extracted from cohorts with rich biomedical measurements. A good biomarker is one that gives reliable detection of the corresponding condition. However, biomarkers are often extracted from a cohort that differs from the target population. Such a mismatch, known as a dataset shift, can undermine the application of the biomarker to new individuals. Dataset shifts are frequent in biomedical research, e.g. because of recruitment biases. When a dataset shift occurs, standard machine-learning techniques do not suffice to extract and validate biomarkers. This article provides an overview of when and how dataset shifts breaks machine-learning extracted biomarkers, as well as detection and correction strategies., Comment: GigaScience, BioMed Central, In press
Published: 2021

26. From deep brain phenotyping to functional atlasing

Author: Ana Luísa Pinho, Alexis Thual, Bertrand Thirion, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Institut National de la Santé et de la Recherche Médicale (INSERM), Collège de France (CdF (institution)), This project/research has received funding from the European Union’s Horizon 2020 Framework Program for Research and Innovation under the Specific Grant Agreement N° 945539 (Human Brain Project SGA3)., European Project: 945539,H2020,H2020-SGA-FETFLAG-HBP-2019,HBP SGA3(2020), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), European Project: 945539,HBP SGA3(2020), Thirion, Bertrand, and Human Brain Project Specific Grant Agreement 3 - HBP SGA3 - - H20202020-01-01 - 2023-09-30 - 945539 - VALID
Subjects: Cognitive science, 0303 health sciences, medicine.diagnostic_test, Computer science, Cognitive Neuroscience, media_common.quotation_subject, Large array, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Inference, Task (project management), 03 medical and health sciences, Behavioral Neuroscience, Psychiatry and Mental health, 0302 clinical medicine, Neuroimaging, Identity (object-oriented programming), medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Simple question, Function (engineering), Functional magnetic resonance imaging, 030217 neurology & neurosurgery, 030304 developmental biology, media_common
Abstract: International audience; How can neuroimaging inform us about the function of brain structures? This simple question immediately brings out two pertinent issues: (i) an inference problem, namely the fact that the function of a region can only be asserted after observing a large array of experimental conditions or contrasts; and (ii) the fact that the identity of a region can only be defined with accuracy at the individual level, because of intrinsic differences between subjects. To overcome this double challenge, we consider an approach based on the deep phenotyping of behavioral responses from task data acquired using functional Magnetic Resonance Imaging. The concept of functional fingerprint-which subsumes the accumulation of functional information at a given brain location-is herein discussed in detail through concrete examples taken from the Individual Brain Charting dataset.
Published: 2021

27. Verifying ontological knowledge through meta-analysis: Study cases of Pain and Consciousness

Author: ZANITTI, Gaston, IOVENE, Valentin, WASSERMANN, Demian, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), European Project: 757672,H2020 Pilier ERC,NeuroLang(2018), Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: [SCCO.NEUR]Cognitive science/Neuroscience, [INFO]Computer Science [cs]
Abstract: International audience; A main goal in current neuroscience is understanding of how different cognitive functions originate in the brain. To achieve this, several projects developed in the last decade sparked large heterogeneous databases. But at present, there is no unifying framework to represent theories.Progress has been made through meta-analysis but some limitations remain to be addressed. With Neurosynth, for example, we can't analyse whether, in the literature, terms dubbed as synonyms are really used in an exchangeable manner across articles. Furthermore, the type of queries that can be used can only be based on propositional logic. In this work, we address these issues by introducing NeuroLang, a probabilistic language based on Datalog$^{+/-}$ that was intended as a first-order logic-based tool. We will use NeuroLang's ability to combine structured knowledge and its power to perform queries based on first-order logic to perform an analysis of the relationship between ontological properties. We will show how, by analysing the changes in the statistical power of meta-analysis data, we can confirm the hierarchization of terms in ontologies.
Published: 2021

28. Probabilistic Logic for Coordinate-Based Meta-Analysis of Functional Segregation in the Brain

Author: Majd Abdallah, Valentin Iovene, Demian Wassermann, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), European Project: 757672,H2020 Pilier ERC,NeuroLang(2018), Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, [INFO.INFO-LO]Computer Science [cs]/Logic in Computer Science [cs.LO], [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], ComputingMilieux_MISCELLANEOUS
Abstract: International audience
Published: 2021

29. Gradient-based and wavelet-based compressed sensing approaches for highly undersampled tomographic datasets

Author: A. Jannaud, Jyh-Miin Lin, Zineb Saghi, Guido Mula, Gabriele Navarro, Philippe Ciuciu, Martin Jacob, Pascale Bayle-Guillemaud, Loubna El Gueddari, Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN)
Subjects: Polynomial, Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, 02 engineering and technology, 01 natural sciences, Wavelet, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0103 physical sciences, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Instrumentation, ComputingMilieux_MISCELLANEOUS, 010302 applied physics, business.industry, [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, Pattern recognition, 021001 nanoscience & nanotechnology, Sample (graphics), Atomic and Molecular Physics, and Optics, Haar wavelet, Electronic, Optical and Magnetic Materials, Compressed sensing, Electron tomography, Piecewise, Artificial intelligence, Minification, 0210 nano-technology, business
Abstract: Electron tomography is widely employed for the 3D morphological characterization at the nanoscale. In recent years, there has been a growing interest in analytical electron tomography (AET) as it is capable of providing 3D information about the elemental composition, chemical bonding and optical/electronic properties of nanomaterials. AET requires advanced reconstruction algorithms as the datasets often consist of a very limited number of projections. Total variation (TV)-based compressed sensing approaches were shown to provide high-quality reconstructions from undersampled datasets, but staircasing artefacts can appear when the assumption about piecewise constancy does not hold. In this paper, we compare higher-order TV and wavelet-based approaches for AET applications and provide an open-source Python toolbox, Pyetomo, containing 2D and 3D implementations of both methods. A highly sampled STEM-HAADF dataset of an Er-doped porous Si sample and a heavily undersampled STEM-EELS dataset of a Ge-rich GeSbTe (GST) thin film annealed at 450°C are used to evaluate the performance of the different approaches. We show that polynomial annihilation with order 3 (HOTV3) and the Bior4.4 wavelet outperform the classical TV minimization and the related Haar wavelet.
Published: 2021

30. Diabetes increases severe COVID-19 outcomes primarily in younger adults Age and diabetes in COVID-19 severity

Author: Diedisheim, Marc, Dancoisne, Etienne, Gautier, Jean-François, Larger, Etienne, Cosson, Emmanuel, Fève, Bruno, Chanson, Philippe, Czernichow, Sébastien, Tatulashvili, Sopio, Raffin-Sanson, Marie-Laure, Bourgeon, Muriel, Ajzenberg, Christiane, Hartemann, Agnès, Daniel, Christel, Moreau, Thomas, Roussel, Ronan, Potier, Louis, Centre de Recherche des Cordeliers (CRC (UMR_S_1138 / U1138)), École pratique des hautes études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université de Paris (UP), Service de diabétologie [CHU Cochin], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Hôpital Cochin [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), CIC - CHU Bichat, Institut National de la Santé et de la Recherche Médicale (INSERM), Groupe Hospitalier Saint Louis - Lariboisière - Fernand Widal [Paris], Centre de Recherche en Nutrition Humaine d'Ile-de-France (CRNH-IDF), Conservatoire National des Arts et Métiers [CNAM] (CNAM)-Institut de Veille Sanitaire (INVS)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Université Sorbonne Paris Nord-Institut National Agronomique Paris-Grignon (INA P-G)-Sorbonne Université (SU)-CETAF-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Institut National de la Santé et de la Recherche Médicale (INSERM), Unité de Recherche en Epidémiologie Nutritionnelle (UREN), Conservatoire National des Arts et Métiers [CNAM] (CNAM)-Université Sorbonne Paris Cité (USPC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Sorbonne Paris Nord, Service d'Endocrinologie, diabétologie et endocrinologie de la reproduction [CHU Saint-Antoine], CHU Saint-Antoine [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Unité de Recherche sur les Maladies Cardiovasculaires, du Métabolisme et de la Nutrition = Institute of cardiometabolism and nutrition (ICAN), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Pitié-Salpêtrière [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Sorbonne Université (SU), Centre de Recherche Saint-Antoine (CR Saint-Antoine), Sorbonne Université (SU)-Institut National de la Santé et de la Recherche Médicale (INSERM)-CHU Saint-Antoine [AP-HP], Physiologie et physiopathologie endocriniennes, Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris-Saclay, AP-HP Hôpital Bicêtre (Le Kremlin-Bicêtre), Centre de Recherche Épidémiologie et Statistique Sorbonne Paris Cité (CRESS (U1153 / UMR_A_1125 / UMR_S_1153)), Conservatoire National des Arts et Métiers [CNAM] (CNAM)-Université Sorbonne Paris Cité (USPC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Paris (UP)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Hôpital Européen Georges Pompidou [APHP] (HEGP), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Hôpitaux Universitaires Paris Ouest - Hôpitaux Universitaires Île de France Ouest (HUPO), Equipe 3: EREN- Equipe de Recherche en Epidémiologie Nutritionnelle (CRESS - U1153), Université Sorbonne Paris Nord-Centre de Recherche Épidémiologie et Statistique Sorbonne Paris Cité (CRESS (U1153 / UMR_A_1125 / UMR_S_1153)), Conservatoire National des Arts et Métiers [CNAM] (CNAM)-Université Sorbonne Paris Cité (USPC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Paris (UP)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM)-Université Sorbonne Paris Cité (USPC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Paris (UP)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Hôpital Avicenne [AP-HP], Service d’endocrinologie et nutrition [AP-HP Ambroise-Paré], Hôpital Ambroise Paré [AP-HP], Université de Versailles Saint-Quentin-en-Yvelines - UFR Sciences de la santé Simone Veil (UVSQ Santé), Université de Versailles Saint-Quentin-en-Yvelines (UVSQ), AP-HP - Hôpital Antoine Béclère [Clamart], CHU Henri Mondor, Service de Diabétologie [CHU Pitié-Salpétrière], CHU Pitié-Salpêtrière [AP-HP], Laboratoire d'Informatique Médicale et Ingénierie des Connaissances en e-Santé (LIMICS), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Sorbonne Paris Nord, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), CEA- Saclay (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Service d'endocrinologie, diabétologie et nutrition [CHU Bichat], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-AP-HP - Hôpital Bichat - Claude Bernard [Paris], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Université de Paris (UP), École Pratique des Hautes Études (EPHE), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Université Paris Cité (UPCité), Institut de Veille Sanitaire (INVS)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Conservatoire National des Arts et Métiers [CNAM] (CNAM), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Institut National Agronomique Paris-Grignon (INA P-G)-CETAF-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Sorbonne Paris Nord, Conservatoire National des Arts et Métiers [CNAM] (CNAM), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Université Sorbonne Paris Cité (USPC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Université Sorbonne Paris Nord, Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Unité de Recherche sur les Maladies Cardiovasculaires, du Métabolisme et de la Nutrition = Research Unit on Cardiovascular and Metabolic Diseases (ICAN), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-Institut de Cardiométabolisme et Nutrition = Institute of Cardiometabolism and Nutrition [CHU Pitié Salpêtrière] (IHU ICAN), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-CHU Pitié-Salpêtrière [AP-HP], Centre de Recherche Saint-Antoine (CRSA), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU), Physiologie et physiopathologie endocriniennes (PHYSENDO), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Université Sorbonne Paris Cité (USPC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris Cité (UPCité)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-HESAM Université - Communauté d'universités et d'établissements Hautes écoles Sorbonne Arts et métiers université (HESAM)-Université Sorbonne Paris Cité (USPC)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris Cité (UPCité)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)-Conservatoire National des Arts et Métiers [CNAM] (CNAM), CHU Henri Mondor [Créteil], Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Université Paris Cité (UPCité), Gestionnaire, Hal Sorbonne Université, Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU), Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)-CHU Saint-Antoine [AP-HP], Service de diabétologie [CHU Pitié-Salpétrière], Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Sorbonne Université (SU)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), and Université Sorbonne Paris Nord-Institut National de la Santé et de la Recherche Médicale (INSERM)-Sorbonne Université (SU)
Subjects: [SDV] Life Sciences [q-bio], Clinical Research Article, age, covid-19, diabetes, [SDV]Life Sciences [q-bio], mortality, AcademicSubjects/MED00250
Abstract: International audience; Context: Diabetes is reported as a risk factor for severe COVID-19, but whether this risk is similar in all categories of age remains unclear.Objective: To investigate the risk of severe COVID-19 outcomes in hospitalized patients with and without diabetes according to age categories.Design setting and participants: We conducted a retrospective observational cohort study of 6,314 consecutive patients hospitalized for COVID-19 between February and June 30 2020, and follow-up recorded until 30 September 2020, in the Paris metropolitan area, France.Main outcome measure(s): The main outcome was a composite outcome of mortality and orotracheal intubation in subjects with diabetes compared with subjects without diabetes, after adjustment for confounding variables and according to age categories.Results: Diabetes was recorded in 39% of subjects. Main outcome was higher in patients with diabetes, independently of confounding variables (HR 1.13 [1.03-1.24]) and increased with age in individuals without diabetes, from 23% for those 80 years but reached a plateau after 70 in those with diabetes. In direct comparison between patients with and without diabetes, diabetes-associated risk was inversely proportional to age, highest in
Published: 2021

31. Predictive models avoid excessive reductionism in cognitive neuroimaging

Author: Gaël Varoquaux, Russell A. Poldrack, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Service NEUROSPIN (NEUROSPIN), Department of Psychology [Stanford], Stanford University, Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: 0301 basic medicine, Computer science, Process (engineering), cognitive models, media_common.quotation_subject, Inference, Neuroimaging, brain imaging, psychology, Cognitive neuroscience, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Task (project management), 03 medical and health sciences, Cognition, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Function (engineering), media_common, Cognitive science, [STAT.AP]Statistics [stat]/Applications [stat.AP], Reductionism, [SHS.STAT]Humanities and Social Sciences/Methods and statistics, [SCCO.NEUR]Cognitive science/Neuroscience, General Neuroscience, Brain, ACM: I.: Computing Methodologies/I.2: ARTIFICIAL INTELLIGENCE, machine learning, 030104 developmental biology, [SCCO.PSYC]Cognitive science/Psychology, Neuroscience, 030217 neurology & neurosurgery
Abstract: International audience; Understanding the organization of complex behavior as it relates to the brain requires modeling the behavior, the relevant mental processes, and the corresponding neural activity. Experiments in cognitive neuroscience typically study a psychological process via controlled manipulations, reducing behavior to one of its component. Such reductionism can easily lead to paradigm-bound theories. Predictive models can generalize brain-mind associations to arbitrary new tasks and stimuli. We argue that they are needed to broaden theories beyond specific paradigms. Predicting behavior from neural activity can support robust reverse inference, isolating brain structures that support particular mental processes. The converse prediction enables modeling brain responses as a function of a complete description of the task, rather than building on oppositions.
Published: 2019

32. What's a good imputation to predict with missing values?

Author: Le Morvan, Marine, Josse, Julie, Scornet, Erwan, Varoquaux, Gaël, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Laboratoire de Physique des 2 Infinis Irène Joliot-Curie (IJCLab), Institut National de Physique Nucléaire et de Physique des Particules du CNRS (IN2P3)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria), Centre de Mathématiques Appliquées - Ecole Polytechnique (CMAP), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Institut Desbrest de santé publique (IDESP), Institut National de la Santé et de la Recherche Médicale (INSERM)-Université de Montpellier (UM), ANR-17-CE23-0018,DirtyData,Intégration et nettoyage de données pour l'analyse statistique(2017), ANR-20-CHIA-0026,LearnI,Apprendre l'intégration de données, des entités aux signaux(2020), and ANR-16-IDEX-0006,MUSE,MUSE(2016)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, consistency, Statistics::Applications, Computer Science - Artificial Intelligence, Machine Learning (stat.ML), imputation, Bayes optimality, [STAT.OT]Statistics [stat]/Other Statistics [stat.ML], neural networks, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], missing values, Artificial Intelligence (cs.AI), Statistics - Machine Learning, Statistics::Methodology
Abstract: 35th Conference on Neural Information Processing Systems (NeurIPS 2021); International audience; How to learn a good predictor on data with missing values? Most efforts focus on first imputing as well as possible and second learning on the completed data to predict the outcome. Yet, this widespread practice has no theoretical grounding. Here we show that for almost all imputation functions, an impute-then-regress procedure with a powerful learner is Bayes optimal. This result holds for all missing-values mechanisms, in contrast with the classic statistical results that require missing-at-random settings to use imputation in probabilistic modeling. Moreover, it implies that perfect conditional imputation is not needed for good prediction asymptotically. In fact, we show that on perfectly imputed data the best regression function will generally be discontinuous, which makes it hard to learn. Crafting instead the imputation so as to leave the regression function unchanged simply shifts the problem to learning discontinuous imputations. Rather, we suggest that it is easier to learn imputation and regression jointly. We propose such a procedure, adapting NeuMiss, a neural network capturing the conditional links across observed and unobserved variables whatever the missing-value pattern. Experiments confirm that joint imputation and regression through NeuMiss is better than various two step procedures in our experiments with finite number of samples.
Published: 2021

33. Correction d'inhomogénéités de champs pour la SWI non-cartésienne par estimation des cartes de champs

Author: Daval-Frérot, Guillaume, Massire, Aurélien, Ripart, Mathilde, Mailhé, Boris, Nadar, Mariappan S., Vignaud, Alexandre, Ciuciu, Philippe, Siemens Healthineers [Saint-Denis], Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Service NEUROSPIN (NEUROSPIN), Siemens Healthineers, Digital Services, Digital Technology and Innovation, Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: [INFO.INFO-IM]Computer Science [cs]/Medical Imaging
Abstract: International audience; Patient-induced inhomogeneities in the magnetic field cause distortions and blurring during acquisitions with long echo times, as in susceptibility-weighted imaging. Most correction methods require collecting an additional ΔB0 field map. To avoid that, we propose a method to approximate this field map using the single echo acquisition only. The main component of the observed phase is linearly related to ΔB0 and TE, and the relative impact of non-ΔB0 terms becomes insignificant with TE>20ms at 3T. The estimated 3D field maps, produced at 0.6 mm isotropic under 3 minutes, provide equivalent corrections to acquired ones.; Les inhomogénéités de champs induites par les patients sont à l'origine de distorsions et de floutages durant les acquisitions à temps d'écho longs, comme pour l'imagerie pondérée en susceptibilité. La plupart des méthodes de correction nécessitent d'acquérir une carte de champ ΔB0 additionnelle. Pour éviter cela, nous proposons une méthode pour approximer cette carte de champs en utilisant seulement l'acquisition à écho unique. La composante principale de la phase observée est linéairement liée au ΔB0 et au TE, et l'impact relatif des termes indépendants du ΔB0 deviennent négligeables pour TE>20ms à 3T. Les cartes 3D estimées, produites à 0.6 mm isotrope en moins de 3 minutes, permettent d'obtenir une correction équivalente aux cartes acquises.
Published: 2021

34. An Open Experimental Platform for Ranging, Proximity and Contact Event Tracking using Ultra-Wide-Band and Bluetooth Low-Energy

Author: Nathalie Mitton, Roudy Dagher, Emmanuel Baccelli, Alexandre Abadie, Francois-Xavier Molina, Self-organizing Future Ubiquitous Network (FUN), Inria Lille - Nord Europe, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), inTeRnet BEyond the usual (TRiBE ), Inria Saclay - Ile de France, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Service Expérimentation et Développement (SED [Saclay]), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: Flexibility (engineering), business.industry, Computer science, Ultra-wideband, Ranging, Context (language use), law.invention, Bluetooth, Microcontroller, [INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI], Software, law, business, Energy (signal processing), Computer hardware
Abstract: International audience; The need for cheaper and more precise localisation techniques has recently amplified. The initial approach has been to roll out high-level software running on smartphones and leveraging Bluetooth proximity sensing. However this approach lacks both precision in terms of ranging, and flexibility in terms of experimental framework to fully explore alternative schemes for contact event tracing. In this context, we thus provide openaccess nodes in an open-access experimental platform for ranging and proximity tracking, letting researchers tinker freely with the full software stack on a swarm of multi-radio, low-power devices based on cheap microcontrollers. We provide a tutorial on how to use the platform and open source code building blocks to to program the devices, bare-metal. We then report on initial measurements we have performed using the platform. Perspectives with our platform include applicability studies and comparative evaluation for a large variety of localisation schemes combining the use of Ultra-Wide Band and Bluetooth Low-Energy for better precision and smaller energy budgets-and the use of complementary mechanism guaranteeing privacy protection, able to run directly on-board cheap IoT microcontrollers.
Published: 2021

35. Guidelines to use Transfer Learning for Motor Imagery Detection: an experimental study

Author: Fabien Lotte, Laurent Bougrain, Pedro Rodrigues, Geoffrey Canron, Sébastien Rimbert, Analysis and modeling of neural systems by a system neuroscience approach (NEUROSYS), Inria Nancy - Grand Est, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Department of Complex Systems, Artificial Intelligence & Robotics (LORIA - AIS), Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Laboratoire Lorrain de Recherche en Informatique et ses Applications (LORIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS)-Université de Lorraine (UL)-Centre National de la Recherche Scientifique (CNRS), Psychologie Ergonomique et Sociale pour l'Expérience utilisateurs (PErSEUs), Université de Lorraine (UL), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Popular interaction with 3d content (Potioc), Laboratoire Bordelais de Recherche en Informatique (LaBRI), Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Université de Bordeaux (UB)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Centre National de la Recherche Scientifique (CNRS)-Inria Bordeaux - Sud-Ouest, The author acknowledges the support of the French Agence Nationale de la Recherche (ANR) under reference ANR-19-CE33-0007 (Grasp-IT project), and the European Research Council with project BrainConquest (grant ERC-2016-STG-714567)., European Project: 714567 ,H2020 Pilier ERC,BrainConquest(2017), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Université de Bordeaux (UB)-Centre National de la Recherche Scientifique (CNRS)-École Nationale Supérieure d'Électronique, Informatique et Radiocommunications de Bordeaux (ENSEIRB)-Inria Bordeaux - Sud-Ouest, Bougrain, Laurent, and Boosting Brain-Computer Communication with high Quality User Training - BrainConquest - - H2020 Pilier ERC2017-07-01 - 2022-06-30 - 714567 - VALID
Subjects: [INFO.INFO-AI] Computer Science [cs]/Artificial Intelligence [cs.AI], Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, 0206 medical engineering, 02 engineering and technology, Machine learning, computer.software_genre, Session (web analytics), Domain (software engineering), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, [SCCO]Cognitive science, 0302 clinical medicine, Motor imagery, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [INFO.INFO-HC]Computer Science [cs]/Human-Computer Interaction [cs.HC], Set (psychology), Reliability (statistics), Brain–computer interface, business.industry, Neural engineering, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], [SCCO] Cognitive science, 020601 biomedical engineering, [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, Artificial intelligence, [INFO.INFO-HC] Computer Science [cs]/Human-Computer Interaction [cs.HC], Transfer of learning, business, computer, 030217 neurology & neurosurgery
Abstract: International audience; Brain-Computer Interfaces (BCI) based on Motor imagery (MI) shown promising results for motor recovery, intraoperative awareness detection or assistive technology control. However, they suffer from several limitations due to the high variability of electroencephalographic (EEG) signals, mainly lengthy and tedious calibration times usually required for each new day of use, and a lack of reliability for all users. Such problems can be addressed, to some extent, using transfer learning algorithms. However, the performance of such algorithms has been very variable so far, and when they can be safely used is still unclear. Therefore, in this article, we study the performance of various state-of-the-art Riemannian transfer learning algorithms on a MI-BCI database (30 users), for various conditions: 1) supervised and unsupervised transfer learning; 2) for various amount of available training EEG data for the target domain; 3) intra-session or inter-session transfer; 4) for both users with good and less good MI-BCI performances. From such experiments, we derive guidelines about when to use which algorithm. Re-centering the target data is effective as soon as a few samples of this target set are taken into account. This is true even for an intra-session transfer learning. Likewise, re-centering is particularly useful for subjects who have difficulty producing stable motor imagery from session to session.
Published: 2021

36. Accounting for variance in machine learning benchmarks

Author: Bouthillier, Xavier, Delaunay, Pierre, Bronzi, Mirko, Trofimov, Assya, Nichyporuk, Brennan, Szeto, Justin, Sepah, Naz, Raff, Edward, Madan, Kanika, Voleti, Vikram, Kahou, Samira Ebrahimi, Michalski, Vincent, Serdyuk, Dmitriy, Arbel, Tal, Pal, Chris, Varoquaux, Ga��l, Vincent, Pascal, Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), Université de Montréal (UdeM), Independent Author, Bioinformatics platform [UdeM-Montréal] (IRIC), Institut de Recherche en Immunologie et en Cancérologie [UdeM-Montréal] (IRIC), Center for Intelligent Machines [Montréal], McGill University = Université McGill [Montréal, Canada], University of Maryland [Baltimore County] (UMBC), University of Maryland System, Ecole de Technologie Supérieure [Montréal] (ETS), Canadian Institute for Advanced Research (CIFAR), École Polytechnique de Montréal (EPM), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), ANR-17-CE23-0018,DirtyData,Intégration et nettoyage de données pour l'analyse statistique(2017), Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, Statistics - Machine Learning, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Machine Learning (stat.ML), Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI]
Abstract: Strong empirical evidence that one machine-learning algorithm A outperforms another one B ideally calls for multiple trials optimizing the learning pipeline over sources of variation such as data sampling, data augmentation, parameter initialization, and hyperparameters choices. This is prohibitively expensive, and corners are cut to reach conclusions. We model the whole benchmarking process, revealing that variance due to data sampling, parameter initialization and hyperparameter choice impact markedly the results. We analyze the predominant comparison methods used today in the light of this variance. We show a counter-intuitive result that adding more sources of variation to an imperfect estimator approaches better the ideal estimator at a 51 times reduction in compute cost. Building on these results, we study the error rate of detecting improvements, on five different deep-learning tasks/architectures. This study leads us to propose recommendations for performance comparisons., Submitted to MLSys2021
Published: 2021

37. POT : Python Optimal Transport

Author: Flamary, Rémi, Courty, Nicolas, Gramfort, Alexandre, Alaya, Mokhtar Zahdi, Boisbunon, Aurélie, Chambon, Stanislas, Chapel, Laetitia, Corenflos, Adrien, Fatras, Kilian, Fournier, Nemo, Gautheron, Léo, Gayraud, Nathalie, Janati, Hicham, Rakotomamonjy, Alain, Redko, Ievgen, Rolet, Antoine, Schutz, Antony, Seguy, Vivien, Sutherland, Danica, Tavenard, Romain, Tong, Alexander, Vayer, Titouan, Centre de Mathématiques Appliquées - Ecole Polytechnique (CMAP), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS), Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-IMT Atlantique (IMT Atlantique), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Laboratoire d'Informatique, de Traitement de l'Information et des Systèmes (LITIS), Université Le Havre Normandie (ULH), Normandie Université (NU)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA), MyDataModels, Therapixel [Nice], Therapixel, Observation de l’environnement par imagerie complexe (OBELIX), SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE (IRISA-D5), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Rennes (UR)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Aalto University, École normale supérieure de Lyon (ENS de Lyon), Université Jean Monnet - Saint-Étienne (UJM), Facebook, Criteo AI Lab, Criteo [Paris], Kyoto University, Université Côte d'Azur (UCA), Nomad AI, University of British Columbia (UBC), Université de Rennes 2 (UR2), Department of Computer Science (YALE), Yale University [New Haven], This work benefited from the support of the project OATMIL ANR-17-CE23-0012 and 3IA Côte d’Azur Investments ANR-19-P3IA-0002 of the French National Research Agency (ANR). This research was produced within the framework of Energy4Climate Interdisciplinary Center (E4C) of IP Paris and Ecole des Ponts ParisTech. This research was supported by 3rd Programme d’Investissements d’Avenir ANR-18-EUR-0006-02., ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019), ANR-18-EURE-0006,E4C,Energy for Climate Interdisciplinary Instute(2018), ANR-17-CE23-0012,OATMIL,Apprentissage statistique avec transport optimal(2017), Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Centre National de la Recherche Scientifique (CNRS)-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-CentraleSupélec-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Institut national des sciences appliquées Rouen Normandie (INSA Rouen Normandie), Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Institut National des Sciences Appliquées (INSA)-Normandie Université (NU)-Université de Rouen Normandie (UNIROUEN), Normandie Université (NU)-Université Le Havre Normandie (ULH), Normandie Université (NU), Institut Mines-Télécom [Paris] (IMT)-Institut Mines-Télécom [Paris] (IMT)-Université de Bretagne Sud (UBS)-Institut National des Sciences Appliquées - Rennes (INSA Rennes), École normale supérieure - Lyon (ENS Lyon), Université Jean Monnet [Saint-Étienne] (UJM), Kyoto University [Kyoto], and Université de Rennes (UNIV-RENNES)
Subjects: [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], domain adaptation, Optimal transport, divergence, optimization
Abstract: International audience; Optimal transport has recently been reintroduced to the machine learning community thanks in part to novel efficient optimization procedures allowing for medium to large scale applications. We propose a Python toolbox that implements several key optimal transport ideas for the machine learning community. The toolbox contains implementations of a number of founding works of OT for machine learning such as Sinkhorn algorithm and Wasserstein barycenters, but also provides generic solvers that can be used for conducting novel fundamental research. This toolbox, named POT for Python Optimal Transport, is open source with an MIT license.
Published: 2021

38. Population modeling with machine learning can enhance measures of mental health

Author: Josselin Houenou, Kamalaker Dadi, Denis A. Engemann, Danilo Bzdok, Gaël Varoquaux, Bertrand Thirion, Zunara, Fatima, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada], Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), Unité de recherche en NeuroImagerie Applicative Clinique et Translationnelle (UNIACT), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), IMRB - 'Neuropsychiatrie translationnelle' [Créteil] (U955 Inserm - UPEC), Institut Mondor de Recherche Biomédicale (IMRB), Institut National de la Santé et de la Recherche Médicale (INSERM)-IFR10-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12)-Institut National de la Santé et de la Recherche Médicale (INSERM)-IFR10-Université Paris-Est Créteil Val-de-Marne - Paris 12 (UPEC UP12), CHU Henri Mondor, Max Planck Institute for Human Cognitive and Brain Sciences [Leipzig] (IMPNSC), Max-Planck-Gesellschaft, CHU Henri Mondor [Créteil], Inria Saclay - Ile de France, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN)
Subjects: Aging, AcademicSubjects/SCI02254, sociodemographic factors, Population, [SDV.MHEP.PSM] Life Sciences [q-bio]/Human health and pathology/Psychiatrics and mental health, Neuroimaging, brain imaging, Machine learning, computer.software_genre, Machine Learning, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Intervention (counseling), Humans, education, Proxy (statistics), 030304 developmental biology, 0303 health sciences, education.field_of_study, business.industry, Research, Neuropsychology, Brain, proxy measures, Mental health, Biobank, Neuroticism, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Mental Health, Complementarity (molecular biology), [SDV.MHEP.PSM]Life Sciences [q-bio]/Human health and pathology/Psychiatrics and mental health, AcademicSubjects/SCI00960, Artificial intelligence, Psychology, business, computer, 030217 neurology & neurosurgery
Abstract: BackgroundBiological aging is revealed by physical measures, e.g., DNA probes or brain scans. Instead, individual differences in mental function are explained by psychological constructs, e.g., intelligence or neuroticism. These constructs are typically assessed by tailored neuropsychological tests that build on expert judgement and require careful interpretation. Could machine learning on large samples from the general population be used to build proxy measures of these constructs that do not require human intervention?ResultsHere, we built proxy measures by applying machine learning on multimodal MR images and rich sociodemographic information from the largest biomedical cohort to date: the UK Biobank. Objective model comparisons revealed that all proxies captured the target constructs and were as useful, and sometimes more useful than the original measures for characterizing real-world health behavior (sleep, exercise, tobacco, alcohol consumption). We observed this complementarity of proxy measures and original measures when modeling from brain signals or sociodemographic data, capturing multiple health-related constructs.ConclusionsPopulation modeling with machine learning can derive measures of mental health from brain signals and questionnaire data, which may complement or even substitute for psychometric assessments in clinical populations.Key PointsWe applied machine learning on more than 10.000 individuals from the general population to define empirical approximations of health-related psychological measures that do not require human judgment.We found that machine-learning enriched the given psychological measures via approximation from brain and sociodemographic data: Resulting proxy measures related as well or better to real-world health behavior than the original measures.Model comparisons showed that sociodemographic information contributed most to characterizing psychological traits beyond aging.
Published: 2021

39. Learning the sampling density in 2D SPARKLING MRI acquisition for optimized image reconstruction

Author: Chaithya G R, Zaccharie Ramzi, Philippe Ciuciu, Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), European Project: 800945,NUMERICS, Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and IEEE
Subjects: Signal Processing (eess.SP), 010102 general mathematics, 01 natural sciences, reconstruction networks, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, Compressed Sensing, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Optimization and Control (math.OC), FOS: Electrical engineering, electronic engineering, information engineering, FOS: Mathematics, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [MATH.MATH-OC]Mathematics [math]/Optimization and Control [math.OC], Electrical Engineering and Systems Science - Signal Processing, 0101 mathematics, Mathematics - Optimization and Control, non-Cartesian trajectories, MRI
Abstract: International audience; The SPARKLING algorithm was originally developed for accelerated 2D magnetic resonance imaging (MRI) in the compressed sensing (CS) context. It yields non-Cartesian sampling trajectories that jointly fulfill a target sampling density while each individual trajectory complies with MR hardware constraints. However, the two main limitations of SPARKLING are first that the optimal target sampling density is unknown and thus a user-defined parameter and second that this sampling pattern generation remains disconnected from MR image reconstruction thus from the optimization of image quality. Recently, datadriven learning schemes such as LOUPE have been proposed to learn a discrete sampling pattern, by jointly optimizing the whole pipeline from data acquisition to image reconstruction. In this work, we merge these methods with a state-of-the-art deep neural network for image reconstruction, called XPDNET, to learn the optimal target sampling density. Next, this density is used as input parameter to SPARKLING to obtain 20x accelerated non-Cartesian trajectories. These trajectories are tested on retrospective compressed sensing (CS) studies and show superior performance in terms of image quality with both deep learning (DL) and conventional CS reconstruction schemes.
Published: 2021

40. Decoding with Confidence: Statistical Control on Decoder Maps

Author: Jérôme-Alexis Chevalier, Joseph Salmon, Tuan-Binh Nguyen, Gaël Varoquaux, Bertrand Thirion, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Université Paris-Saclay, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Laboratoire de Mathématiques d'Orsay (LMO), Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Institut Montpelliérain Alexander Grothendieck (IMAG), Université de Montpellier (UM)-Centre National de la Recherche Scientifique (CNRS), Université de Montpellier (UM), Centre National de la Recherche Scientifique (CNRS), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and ANR-17-CE23-0011,FAST-BIG,Tests Statistiques efficaces pour les données de grande dimension: application à l'imagerie cérébrale et la génétique(2017)
Subjects: Data Analysis, Multivariate statistics, Computer science, Cognitive Neuroscience, Decoding, Multivariate Model, Inference, Neurosciences. Biological psychiatry. Neuropsychiatry, Statistical Control, 050105 experimental psychology, 03 medical and health sciences, 0302 clinical medicine, Empirical research, Lasso (statistics), [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistical inference, Image Processing, Computer-Assisted, Humans, 0501 psychology and cognitive sciences, Statistical Methods, ComputingMilieux_MISCELLANEOUS, High Dimension, Brain Mapping, [STAT.AP]Statistics [stat]/Applications [stat.AP], [SCCO.NEUR]Cognitive science/Neuroscience, 05 social sciences, fMRI, Brain, Statistical process control, Thresholding, Magnetic Resonance Imaging, Neurology, Neural Networks, Computer, Algorithm, 030217 neurology & neurosurgery, Decoding methods, Algorithms, Psychomotor Performance, RC321-571, Support Recovery
Abstract: In brain imaging, decoding is widely used to infer relationships between brain and cognition, or to craft brain-imaging biomarkers of pathologies. Yet, standard decoding procedures do not come with statistical guarantees, and thus do not give confidence bounds to interpret the pattern maps that they produce. Indeed, in whole-brain decoding settings, the number of explanatory variables is much greater than the number of samples, hence classical statistical inference methodology cannot be applied. Specifically, the standard practice that consists in thresholding decoding maps is not a correct inference procedure. We contribute a new statistical-testing framework for this type of inference. To overcome the statistical inefficiency of voxel-level control, we generalize the Family Wise Error Rate (FWER) to account for a spatial tolerance δ , introducing the δ -Family Wise Error Rate ( δ -FWER). Then, we present a decoding procedure that can control the δ -FWER: the Ensemble of Clustered Desparsified Lasso (EnCluDL), a procedure for multivariate statistical inference on high-dimensional structured data. We evaluate the statistical properties of EnCluDL with a thorough empirical study, along with three alternative procedures including decoder map thresholding. We show that EnCluDL exhibits the best recovery properties while ensuring the expected statistical control.
Published: 2021

41. Calibration-Less Multi-Coil Compressed Sensing Magnetic Resonance Image Reconstruction Based on OSCAR Regularization

Author: Emilie Chouzenoux, Loubna El Gueddari, Philippe Ciuciu, Chaithya Giliyar Radhakrishna, Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), OPtimisation Imagerie et Santé (OPIS), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre de vision numérique (CVN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-CentraleSupélec-Université Paris-Saclay, and ANR-17-CE40-0004,MajIC,Algorithmes de Majoration-Minimisation pour le traitement d'images(2017)
Subjects: Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, cluster norm, proximal algorithms, 02 engineering and technology, Iterative reconstruction, lcsh:Computer applications to medicine. Medical informatics, Regularization (mathematics), Article, lcsh:QA75.5-76.95, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Radiology, Nuclear Medicine and imaging, Computer vision, Sensitivity (control systems), lcsh:Photography, Electrical and Electronic Engineering, Cluster analysis, compressed sensing, business.industry, parallel MRI, Wavelet transform, [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, Inverse problem, lcsh:TR1-1050, Computer Graphics and Computer-Aided Design, non-Cartesian acquisition, Data set, Compressed sensing, lcsh:R858-859.7, 020201 artificial intelligence & image processing, Computer Vision and Pattern Recognition, Artificial intelligence, lcsh:Electronic computers. Computer science, business
Abstract: Over the last decade, the combination of compressed sensing (CS) with acquisition over multiple receiver coils in magnetic resonance imaging (MRI) has allowed the emergence of faster scans while maintaining a good signal-to-noise ratio (SNR). Self-calibrating techniques, such as ESPiRIT, have become the standard approach to estimating the coil sensitivity maps prior to the reconstruction stage. In this work, we proceed differently and introduce a new calibration-less multi-coil CS reconstruction method. Calibration-less techniques no longer require the prior extraction of sensitivity maps to perform multi-coil image reconstruction but usually alternate estimation sensitivity map estimation and image reconstruction. Here, to get rid of the nonconvexity of the latter approach we reconstruct as many MR images as the number of coils. To compensate for the ill-posedness of this inverse problem, we leverage structured sparsity of the multi-coil images in a wavelet transform domain while adapting to variations in SNR across coils owing to the OSCAR (octagonal shrinkage and clustering algorithm for regression) regularization. Coil-specific complex-valued MR images are thus obtained by minimizing a convex but nonsmooth objective function using the proximal primal-dual Condat-Vù algorithm. Comparison and validation on retrospective Cartesian and non-Cartesian studies based on the Brain fastMRI data set demonstrate that the proposed reconstruction method outperforms the state-of-the-art (ℓ1-ESPIRiT, calibration-less AC-LORAKS and CaLM methods) significantly on magnitude images for the T1 and FLAIR contrasts. Additionally, further validation operated on 8 to 20-fold prospectively accelerated high-resolution ex vivo human brain MRI data collected at 7 Tesla confirms the retrospective results. Overall, OSCAR-based regularization preserves phase information more accurately (both visually and quantitatively) compared to other approaches, an asset that can only be assessed on real prospective experiments.
Published: 2021

42. Uncovering the structure of clinical EEG signals with self-supervised learning

Author: Hubert Banville, Alexandre Gramfort, Omar Chehab, Aapo Hyvärinen, Denis-Alexander Engemann, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Ecole Normale Supérieure Paris-Saclay (ENS Paris Saclay), Helsingin yliopisto = Helsingfors universitet = University of Helsinki, PROMICE_BERNOULLI, ANR-20-CHIA-0016,BrAIN,Intelligence Artificielle et Neurosciences(2020), ANR-17-CONV-0003,Institut DATAIA (I2-DRIVE),Data Science, Artificial Intelligence and Society(2017), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, University of Helsinki, Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Department of Biochemistry and Developmental Biology, and Department of Computer Science
Subjects: Signal Processing (eess.SP), FOS: Computer and information sciences, Computer Science - Machine Learning, Computer science, 02 engineering and technology, Electroencephalography, computer.software_genre, Quantitative Biology - Quantitative Methods, Machine Learning (cs.LG), [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], [SHS]Humanities and Social Sciences, representation learning, [SCCO]Cognitive science, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, Feature (machine learning), Quantitative Methods (q-bio.QM), medicine.diagnostic_test, Clinical neuroscience, Research Design, Neurons and Cognition (q-bio.NC), Sleep Stages, Supervised Machine Learning, Self-supervised learning, 0206 medical engineering, Biomedical Engineering, Machine Learning (stat.ML), Sleep staging, Machine learning, 03 medical and health sciences, Cellular and Molecular Neuroscience, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], FOS: Electrical engineering, electronic engineering, information engineering, medicine, Humans, Presentation learning, Electrical Engineering and Systems Science - Signal Processing, Structure (mathematical logic), Self supervised learning, business.industry, Deep learning, [SCCO.NEUR]Cognitive science/Neuroscience, Supervised learning, 3112 Neurosciences, 020601 biomedical engineering, Pathology detection, ComputingMethodologies_PATTERNRECOGNITION, FOS: Biological sciences, Quantitative Biology - Neurons and Cognition, Neural Networks, Computer, Artificial intelligence, business, computer, Feature learning, 030217 neurology & neurosurgery
Abstract: Objective. Supervised learning paradigms are often limited by the amount of labeled data that is available. This phenomenon is particularly problematic in clinically-relevant data, such as electroencephalography (EEG), where labeling can be costly in terms of specialized expertise and human processing time. Consequently, deep learning architectures designed to learn on EEG data have yielded relatively shallow models and performances at best similar to those of traditional feature-based approaches. However, in most situations, unlabeled data is available in abundance. By extracting information from this unlabeled data, it might be possible to reach competitive performance with deep neural networks despite limited access to labels. Approach. We investigated self-supervised learning (SSL), a promising technique for discovering structure in unlabeled data, to learn representations of EEG signals. Specifically, we explored two tasks based on temporal context prediction as well as contrastive predictive coding on two clinically-relevant problems: EEG-based sleep staging and pathology detection. We conducted experiments on two large public datasets with thousands of recordings and performed baseline comparisons with purely supervised and hand-engineered approaches. Main results. Linear classifiers trained on SSL-learned features consistently outperformed purely supervised deep neural networks in low-labeled data regimes while reaching competitive performance when all labels were available. Additionally, the embeddings learned with each method revealed clear latent structures related to physiological and clinical phenomena, such as age effects. Significance. We demonstrate the benefit of self-supervised learning approaches on EEG data. Our results suggest that SSL may pave the way to a wider use of deep learning models on EEG data., 32 pages, 9 figures
Published: 2021

43. Single Encoding Diffusion MRI: a Probe to Brain Anisotropy

Author: Maëliss Jallais, Demian Wassermann, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: Computer science, [SCCO.NEUR]Cognitive science/Neuroscience, Measure (physics), Context (language use), Human brain, Signal, [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, medicine.anatomical_structure, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Encoding (memory), medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Representation (mathematics), Anisotropy, Algorithm, 030217 neurology & neurosurgery, Diffusion MRI
Abstract: This chapter covers anisotropy in the context of probing microstructure of the human brain using single encoded diffusion MRI. We will start by illustrating how diffusion MRI is a perfectly adapted technique to measure anisotropy in the human brain using water motion, followed by a biological presentation of human brain. The non-invasive imaging technique based on water motions known as diffusion MRI will be further presented, along with the difficulties that come with it. Within this context, we will first review and discuss methods based on signal representation that enable us to get an insight into microstructure anisotropy. We will then outline methods based on modeling, which are state-of-the-art methods to get parameter estimations of the human brain tissue.
Published: 2021

44. Prediction, Not Association, Paves the Road to Precision Medicine

Author: Ewout W. Steyerberg, Danilo Bzdok, Gaël Varoquaux, Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), McConnell Brain Imaging Centre (MNI), Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada]-McGill University = Université McGill [Montréal, Canada], Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Leiden University Medical Center (LUMC), Universiteit Leiden, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay
Subjects: 0303 health sciences, medicine.medical_specialty, [STAT.AP]Statistics [stat]/Applications [stat.AP], Association (object-oriented programming), MEDLINE, Precision medicine, 3. Good health, 03 medical and health sciences, Psychiatry and Mental health, 0302 clinical medicine, Family medicine, medicine, Humans, Precision Medicine, Psychology, 030217 neurology & neurosurgery, 030304 developmental biology
Abstract: International audience; In the 20th century, evidence-based medicine has put clinical practice on much more solid ground. For instance, randomized clinical trials have provided strong evidence on useful interventions, thanks to double-blind treatment application and tests for treatment associations with clinical outcomes. However, precision medicine in the 21st century strives for accurate prediction of what is beneficial for individual patients.1 Prediction, as opposed to association, comes into play when forecasting outcomes that are yet unobserved or hard to obtain.2 The machine-learning community has long cultivated and widely adopted practices that can be used to empirically evaluate successful generalization of extracted models on new individuals. We reinforce calls (eg, Stephan et al3) for wider adoption of statistical procedures that explicitly model and test extrapolation to individuals who have not yet been seen as a crucial avenue to hold up to the promises of precision psychiatry.
Published: 2021

45. Brain topography beyond parcellations: local gradients of functional maps

Author: Bertrand Thirion, Hugo Richard, Ana Luísa Pinho, Elvis Dohmatob, Criteo AI Lab, Criteo [Paris], Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Service NEUROSPIN (NEUROSPIN), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay
Subjects: Parcellation, Databases, Factual, Computer science, Rest, Cognitive Neuroscience, Functional gradients, Model selection, 050105 experimental psychology, Functional mapping, lcsh:RC321-571, 03 medical and health sciences, 0302 clinical medicine, Functional neuroimaging, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, 0501 psychology and cognitive sciences, lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry, Qualitative Research, Spatial organization, Brain Mapping, medicine.diagnostic_test, business.industry, 05 social sciences, Brain, Pattern recognition, Magnetic Resonance Imaging, Neurology, Artificial intelligence, Prediction, business, Constant (mathematics), Functional magnetic resonance imaging, 030217 neurology & neurosurgery
Abstract: International audience; Functional neuroimaging provides the unique opportunity to characterize brain regions based on their response to tasks or ongoing activity. As such, it holds the premise to capture brain spatial organization. Yet, the conceptual framework to describe this organization has remained elusive: on the one hand, parcellations build implicitly on a piecewise constant organization, i.e. flat regions separated by sharp boundaries; on the other hand, the recently popularized concept of functional gradient hints instead at a smooth structure. Noting that both views converge to a topographic scheme that pieces together local variations of functional features, we perform a quantitative assessment of local gradient-based models. Using as a driving case the prediction of functional Magnetic Resonance Imaging (fMRI) data —concretely, the prediction of task-fMRI from rest-fMRI maps across subjects— we develop a parcel-wise linear regression model based on a dictionary of reference topographies. Our method uses multiple random parcellations —as opposed to a single fixed parcellation— and aggregates estimates across these parcellations to predict functional features in left-out subjects. Our experiments demonstrate the existence of an optimal cardinality of the parcellation to capture local gradients of functional maps.
Published: 2021

46. Wavelets in the Deep Learning ERA

Author: Zaccharie Ramzi, Jean-Luc Starck, Philippe Ciuciu, Thomas Moreau, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Service NEUROSPIN (NEUROSPIN), Laboratoire de Cosmologie et Statistiques (LCS - COSMOSTAT), Institut de Recherches sur les lois Fondamentales de l'Univers (IRFU), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Astrophysique Interprétation Modélisation (AIM (UMR_7158 / UMR_E_9005 / UM_112)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité)
Subjects: Neural Networks, Computer science, Generalization, 02 engineering and technology, Iterative reconstruction, Wavelets, Machine learning, computer.software_genre, Machine Learning, Image restoration, Wavelet, Deep Learning, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, 0202 electrical engineering, electronic engineering, information engineering, Network architecture, Denoising, Training set, Artificial neural network, business.industry, Deep learning, [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV], 020206 networking & telecommunications, Inverse problem, 020201 artificial intelligence & image processing, Artificial intelligence, business, computer
Abstract: International audience; Sparsity based methods, such as wavelets, have been state-of-the-art for more than 20 years for inverse problems before being overtaken by neural networks. In particular, U-nets have proven to be extremely effective. Their main ingredients are a highly non-linear processing, a massive learning made possible by the flourishing of optimization algorithms with the power of computers (GPU) and the use of large available data sets for training. While the many stages of non-linearity are intrinsic to deep learning, the usage of learning with training data could also be exploited by sparsity based approaches. The aim of our study is to push the limits of sparsity with learning, and comparing the results with U-nets. We present a new network architecture, which conserves the properties of sparsity based methods such as exact reconstruction and good generalization properties, while fostering the power of neural networks for learning and fast calculation. We evaluate the model on image denoising tasks and show it is competitive with learning-based models.
Published: 2021

47. Revisiting Functional Connectivity for Infraslow Scale-Free Brain Dynamics using Complex Wavelet

Author: La Rocca, Daria, Wendt, Herwig, Van Wassenhove, Virginie, Ciuciu, Philippe, Abry, Patrice, Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), CoMputational imagINg anD viSion (IRIT-MINDS), Institut de recherche en informatique de Toulouse (IRIT), Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université de Toulouse (UT)-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université Toulouse Capitole (UT Capitole), Université de Toulouse (UT), Centre National de la Recherche Scientifique (CNRS), Neuroimagerie cognitive - Psychologie cognitive expérimentale (UNICOG-U992), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris-Saclay, Laboratoire de Physique de l'ENS Lyon (Phys-ENS), École normale supérieure de Lyon (ENS de Lyon)-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), ANR-16-CE33-0020,MULTIFRACS,Théories et méthodes multifractales multivariées pour les systèmes de grande taille - Applications à l'analyse des propriétés d'invariance d'échelle dans la dynamique de l'activité cérébrale(2016), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Centre National de la Recherche Scientifique (CNRS)-Institut National Polytechnique (Toulouse) (Toulouse INP), Université Fédérale Toulouse Midi-Pyrénées-Toulouse Mind & Brain Institut (TMBI), Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse III - Paul Sabatier (UT3), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse Capitole (UT Capitole), Université Fédérale Toulouse Midi-Pyrénées, École normale supérieure - Lyon (ENS Lyon)-Université Claude Bernard Lyon 1 (UCBL), Université de Lyon-Université de Lyon-Centre National de la Recherche Scientifique (CNRS), Ciuciu, Philippe, Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Université Toulouse 1 Capitole (UT1), Université Fédérale Toulouse Midi-Pyrénées-Université Toulouse 1 Capitole (UT1), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris Saclay (COmUE)-Institut National de la Santé et de la Recherche Médicale (INSERM), École normale supérieure - Lyon (ENS Lyon)-Centre National de la Recherche Scientifique (CNRS)-Université Claude Bernard Lyon 1 (UCBL), and Université de Lyon-Université de Lyon
Subjects: [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, functional connectivity assessed from fractal dynamics, [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, functional connectivity, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, [SCCO] Cognitive science, arrhythmic, Human brain temporal dynamics, [SCCO]Cognitive science, complex-wavelet, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, MEG data, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, [SDV.NEU.SC] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, scale-free, infraslow, phase coupling
Abstract: International audience; The analysis of human brain functional networks is achieved by computing functional connectivity indices reflecting phase coupling and interactions between remote brain regions. In magneto-and electroencephalography, the most often used functional connectivity indices are constructed on Fourier-based cross spectral estimation applied to specific fast and band limited oscillatory regimes. Recently, infraslow arrhythmic fluctuations (below the 1Hz) were recognized as playing a leading role in spontaneous brain activity. The present work aims to propose to assess functional connectivity, from fractal dynamics, thus extending the assessment of functional connectivity to the infraslow arrhythmic or scale-free temporal dynamics of M/EEG-quantified brain activity. Instead of being based on Fourier analysis, new Imaginary Coherence and weighted Phase Lag indices are constructed from complex-wavelet representations. Their performance are, first, assessed on synthetic data, by means of Monte-Carlo simulations, and compared favorably against the classical Fourier-based indices. These new assessment of functional connectivity indices are, second, applied to MEG data collected on 36 individuals, both at rest and during the learning of a visual motion discrimination 1 La Rocca et al. Functional Connectivity assessed from fractal dynamics task. They demonstrate a higher statistical sensitivity, compared to their Fourier counterparts, in capturing significant and relevant functional interactions in the infraslow regime, and modulations from rest to task. Notably, the consistent overall increase in functional connectivity assessed from fractal dynamics from rest to task, correlated with a change in temporal dynamics, as well as with improved performance in task completion, suggests that complex-wavelet weighted Phase Lag index is the sole index able to capture brain plasticity in the infraslow scale-free regime.
Published: 2021

48. Label scarcity in biomedicine: Data-rich latent factor discovery enhances phenotype prediction

Author: Schulz, Marc-Andre, Varoquaux, Gaël, Gramfort, Alexandre, Thirion, Bertrand, Bzdok, Danilo, Rheinisch-Westfälische Technische Hochschule Aachen University (RWTH), Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Department of Psychiatry, Psychotherapy and Psychosomatics [Aachen], Bzdok, Danilo, Rheinisch-Westfälische Technische Hochschule Aachen (RWTH), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, Quantitative Biology - Neurons and Cognition, FOS: Biological sciences, [INFO]Computer Science [cs], Neurons and Cognition (q-bio.NC), [INFO] Computer Science [cs], ComputingMilieux_MISCELLANEOUS, Machine Learning (cs.LG)
Abstract: High-quality data accumulation is now becoming ubiquitous in the health domain. There is increasing opportunity to exploit rich data from normal subjects to improve supervised estimators in specific diseases with notorious data scarcity. We demonstrate that low-dimensional embedding spaces can be derived from the UK Biobank population dataset and used to enhance data-scarce prediction of health indicators, lifestyle and demographic characteristics. Phenotype predictions facilitated by Variational Autoencoder manifolds typically scaled better with increasing unlabeled data than dimensionality reduction by PCA or Isomap. Performances gains from semisupervison approaches will probably become an important ingredient for various medical data science applications., Comment: Accepted at NIPS 2017 Workshop on Machine Learning for Health
Published: 2021
Full Text: View/download PDF

49. Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction

Author: Yohan Jun, Simon Arberet, Jean-Luc Starck, Dominik Nickel, Alireza Radmanesh, Yvonne W. Lui, Sunwoo Kim, Matthew J. Muckley, Mahmoud Mostapha, Jonas Teuwen, Zhengnan Huang, Nafissa Yakubova, Dosik Hwang, Geunu Jeong, Zaccharie Ramzi, Florian Knoll, Anuroop Sriram, Philippe Ciuciu, Chaoping Zhang, Bruno Riemenschneider, Hyungseob Shin, Jingyu Ko, Dimitrios Karkalousos, Facebook AI Research [New York] (FAIR), Facebook, New York University School of Medicine (NYU), New York University School of Medicine, NYU System (NYU)-NYU System (NYU), AIRS Medical [Seoul], Yonsei University, Siemens Healthineers, Digital Services, Digital Technology and Innovation, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, Service NEUROSPIN (NEUROSPIN), Astrophysique Interprétation Modélisation (AIM (UMR_7158 / UMR_E_9005 / UM_112)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université de Paris (UP), Radboud University Medical Center [Nijmegen], Amsterdam UMC, Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut national des sciences de l'Univers (INSU - CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité), and Amsterdam UMC - Amsterdam University Medical Center
Subjects: FOS: Computer and information sciences, fast imaging, medicine.medical_specialty, Computer science, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Neuroimaging, 02 engineering and technology, Iterative reconstruction, Article, Data modeling, Machine Learning, 03 medical and health sciences, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Research community, 0202 electrical engineering, electronic engineering, information engineering, medicine, FOS: Electrical engineering, electronic engineering, information engineering, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Medical physics, Challenge, Electrical and Electronic Engineering, MR image reconstruction, parallel imaging, 030304 developmental biology, compressed sensing, 0303 health sciences, Training set, Radiological and Ultrasound Technology, Principal (computer security), Image and Video Processing (eess.IV), Brain, 020206 networking & telecommunications, public data set, Electrical Engineering and Systems Science - Image and Video Processing, 16. Peace & justice, Magnetic Resonance Imaging, Computer Science Applications, 13. Climate action, Mr images, optimization, Software
Abstract: Accelerating MRI scans is one of the principal outstanding problems in the MRI research community. Towards this goal, we hosted the second fastMRI competition targeted towards reconstructing MR images with subsampled k-space data. We provided participants with data from 7,299 clinical brain scans (de-identified via a HIPAA-compliant procedure by NYU Langone Health), holding back the fully-sampled data from 894 of these scans for challenge evaluation purposes. In contrast to the 2019 challenge, we focused our radiologist evaluations on pathological assessment in brain images. We also debuted a new Transfer track that required participants to submit models evaluated on MRI scanners from outside the training set. We received 19 submissions from eight different groups. Results showed one team scoring best in both SSIM scores and qualitative radiologist evaluations. We also performed analysis on alternative metrics to mitigate the effects of background noise and collected feedback from the participants to inform future challenges. Lastly, we identify common failure modes across the submissions, highlighting areas of need for future research in the MRI reconstruction community., Comment: M. J. Muckley and B. Riemenschneider contributed equally to this work. This updates to version accepted in IEEE Transactions on Medical Imaging. It includes a rewrite of Section II.E as well as minor changes and corrections
Published: 2021

50. Disentangling Syntax and Semantics in the Brain with Deep Networks

Author: Caucheteux, Charlotte, Gramfort, Alexandre, King, Jean-Remi, Facebook AI Research [Paris] (FAIR), Facebook, Modelling brain structure, function and variability based on high-field MRI data (PARIETAL), Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Service NEUROSPIN (NEUROSPIN), Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay, École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL), Service NEUROSPIN (NEUROSPIN), Université Paris-Saclay-Direction de Recherche Fondamentale (CEA) (DRF (CEA)), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Inria Saclay - Ile de France, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria), and École normale supérieure - Paris (ENS-PSL)
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, Computer Science - Computation and Language, Quantitative Biology - Neurons and Cognition, [SCCO.NEUR]Cognitive science/Neuroscience, FOS: Biological sciences, Neurons and Cognition (q-bio.NC), Computation and Language (cs.CL), [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL], [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Machine Learning (cs.LG)
Abstract: The activations of language transformers like GPT-2 have been shown to linearly map onto brain activity during speech comprehension. However, the nature of these activations remains largely unknown and presumably conflate distinct linguistic classes. Here, we propose a taxonomy to factorize the high-dimensional activations of language models into four combinatorial classes: lexical, compositional, syntactic, and semantic representations. We then introduce a statistical method to decompose, through the lens of GPT-2's activations, the brain activity of 345 subjects recorded with functional magnetic resonance imaging (fMRI) during the listening of ~4.6 hours of narrated text. The results highlight two findings. First, compositional representations recruit a more widespread cortical network than lexical ones, and encompass the bilateral temporal, parietal and prefrontal cortices. Second, contrary to previous claims, syntax and semantics are not associated with separated modules, but, instead, appear to share a common and distributed neural substrate. Overall, this study introduces a versatile framework to isolate, in the brain activity, the distributed representations of linguistic constructs., Comment: Accepted to ICML 2021
Published: 2021
Full Text: View/download PDF

Catalog

Books, media, physical & digital resources

See catalog results

Searchworks

Select search scope, currently: Articles Catalog books, media & more in Jio Institute collections Articles journal articles & other e-resources

Search

Search Constraints

Refine your results

Search Limiters

Topic

Publication Year Range

Language

Journal

Database

Publisher

1,463 results on '"Service NEUROSPIN (NEUROSPIN)"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources