Author: "Bertrand Thirion" / Topic: business.industry - Searchworks@Jio Institute Digital Library Search Results

Your search keyword '"Bertrand Thirion"' showing total 123 results

Start Over Author "Bertrand Thirion" Topic business.industry

123 results on '"Bertrand Thirion"'

1. 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

2. Tackling the Complexity of Lesion-Symptoms Mapping: How to Bridge the Gap Between Data Scientists and Clinicians?

Author: Emmanuel Mandonnet and Bertrand Thirion
Subjects: Multivariate statistics, business.industry, Univariate, Inference, computer.software_genre, Machine learning, Field (computer science), Bridge (nautical), Voxel, Medicine, Artificial intelligence, business, computer, Relevant information, Curse of dimensionality
Abstract: Accurate and predictive lesion-symptoms mapping is a major goal in the field of clinical neurosciences. Recent studies have called for a reappraisal of the results given by the standard univariate voxel-based lesion-symptom mapping technique, emphasizing the need of developing multivariate methods. While the organization of large datasets and their analysis with machine learning (ML) approaches represents an opportunity to increase prediction accuracy, the complexity and dimensionality of the problem remain a major obstacle. Acknowledging the difficulty of inferring individual outcomes from the observation of spatial patterns of lesions, we propose here to base prediction on new individuals on models of brain connectivity, whereby the disruption of a given network predicts the occurrence of selective deficits. Well-suited ML tools are necessary to capture the relevant information from limited datasets and perform reliable inference.
Published: 2021

3. 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

4. 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

5. Functional annotation of human cognitive states using deep graph convolution

Author: Yu Zhang, Bertrand Thirion, Loïc Tetrel, Pierre Bellec, Centre de Recherche de l'Institut Universitaire de Gériatrie de Montréal (CRIUGM), Department of Psychology , Université de Montréal Centre de recherche de l’Institut universitaire de gériatrie de Montréal, Centre de recherche de l'Institut universitaire de gériatrie de Montreal (CRIUGM), Université de Montréal (UdeM), 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, and Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)
Subjects: Elementary cognitive task, Computer science, Brain activity and meditation, Cognitive Neuroscience, Graph convolutional network, Neurosciences. Biological psychiatry. Neuropsychiatry, Convolutional neural network, 050105 experimental psychology, 03 medical and health sciences, Cognition, 0302 clinical medicine, Connectome, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, 0501 psychology and cognitive sciences, Set (psychology), Human Connectome Project, business.industry, Deep learning, fMRI, 05 social sciences, Brain decoding, Brain, Pattern recognition, Human brain, Magnetic Resonance Imaging, medicine.anatomical_structure, Cognitive states, Neurology, Graph (abstract data type), Artificial intelligence, Nerve Net, business, 030217 neurology & neurosurgery, Brain dynamics, RC321-571, MRI
Abstract: A key goal in neuroscience is to understand brain mechanisms of cognitive functions. An emerging approach is “brain decoding”, which consists of inferring a set of experimental conditions performed by a participant, using pattern classification of brain activity. Few works so far have attempted to train a brain decoding model that would generalize across many different cognitive tasks drawn from multiple cognitive domains. To tackle this problem, we proposed a domain-general brain decoder that automatically learns the spatiotemporal dynamics of brain response within a short time window using a deep learning approach. By leveraging our prior knowledge on network organization of human brain cognition, we constructed deep graph convolutional neural networks to annotate cognitive states by first mapping the task-evoked fMRI response onto a brain graph, propagating brain dynamics among interconnected brain regions and functional networks, and generating state-specific representations of recorded brain activity. We evaluated the decoding model on a large population of 1200 participants, under 21 different experimental conditions spanning 6 different cognitive domains, acquired from the Human Connectome Project task-fMRI database. Using a 10s window of fMRI response, the 21 cognitive states were identified with a test accuracy of 89% (chance level 4.8%). Performance remained good when using a 6s window (82%). It was even feasible to decode cognitive states from a single fMRI volume (720ms), with the performance following the shape of the hemodynamic response. Moreover, a saliency map analysis demonstrated that the high decoding performance was driven by the response of biologically meaningful brain regions. Together, we provide an automated tool to annotate human brain activity with fine temporal resolution and fine cognitive granularity. Our model shows potential applications as a reference model for domain adaptation, possibly making contributions in a variety of domains, including neurological and psychiatric disorders.
Published: 2021

6. 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

7. 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

8. Multivariate analysis is sufficient for lesion-behaviour mapping

Author: Julie Josse, Lucas Martin, 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), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria), Thirion, Bertrand, 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, and Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)
Subjects: Multivariate statistics, Multivariate analysis, Computer science, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Machine learning, computer.software_genre, 01 natural sciences, Brain mapping, Lesion, 010104 statistics & probability, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0101 mathematics, Set (psychology), Lesion-behaviour mapping, Brain function, business.industry, [INFO.INFO-LG] Computer Science [cs]/Machine Learning [cs.LG], Causal inference, Multivariate methods, Artificial intelligence, medicine.symptom, Focus (optics), business, computer, 030217 neurology & neurosurgery
Abstract: International audience; Lesion-behaviour mapping aims at predicting individual be-havioural deficits, given a certain pattern of brain lesions. It also brings fundamental insights on brain organization, as lesions can be understood as interventions on normal brain function. We focus here on the case of stroke. The most standard approach to lesion-behaviour mapping is mass-univariate analysis, but it is inaccurate due to correlations between the different brain regions induced by vascularisation. Recently, it has been claimed that multivariate methods are also subject to lesion-anatomical bias, and that a move towards a causal approach is necessary to eliminate that bias. In this paper, we reframe the lesion-behaviour brain mapping problem using classical causal inference tools. We show that, in the absence of additional clinical data and if only one region has an effect on the behavioural scores, suitable multivariate methods are sufficient to address lesion-anatomical bias. This is a commonly encountered situation when working with public datasets, which very often lack general health data. We support our claim with a set of simulated experiments using a publicly available lesion imaging dataset, on which we show that adequate multivariate models provide state-of-the art results.
Published: 2020

9. Multi-Scale Network Regression for Brain-Phenotype Associations

Author: Danielle S. Bassett, Daniela Witten, Theodore D. Satterthwaite, Bertrand Thirion, Danilo Bzdok, Zongming Ma, Russell T. Shinohara, Zaixu Cui, Cedric Huchuan Xia, University of Pennsylvania [Philadelphia], Montreal Neurological Hospital, McGill University Health Center [Montreal] (MUHC), 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), Montreal Institute for Learning Algorithms [Montréal] (MILA), Centre de Recherches Mathématiques [Montréal] (CRM), Université de Montréal (UdeM)-Université de Montréal (UdeM), University of Washington [Seattle], University of Pennsylvania, 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, Multivariate statistics, Multivariate analysis, Computer science, Individuality, computer.software_genre, 01 natural sciences, 010104 statistics & probability, Functional connectivity, Technical Report, 0302 clinical medicine, Interpretability, Sex Characteristics, Radiological and Ultrasound Technology, 05 social sciences, Rank (computer programming), Brain, Magnetic Resonance Imaging, Regression, Phenotype, Neurology, Regression Analysis, Female, [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], Enhanced Data Rates for GSM Evolution, Anatomy, Adolescent, Network neuroscience, [SCCO.COMP]Cognitive science/Computer science, Machine learning, 050105 experimental psychology, 03 medical and health sciences, Neuroimaging, Connectome, Humans, 0501 psychology and cognitive sciences, Radiology, Nuclear Medicine and imaging, 0101 mathematics, Association (psychology), Models, Statistical, business.industry, Cross-Sectional Studies, Neurology (clinical), Artificial intelligence, Nerve Net, Scale (map), business, computer, 030217 neurology & neurosurgery
Abstract: Human brain mapping 41(10), 2553-2566 (2020). doi:10.1002/hbm.24982, Published by Wiley-Liss, New York, NY
Published: 2020

10. FReM – Scalable and stable decoding with fast regularized ensemble of models

Author: Yannick Schwartz, Andrés Hoyos-Idrobo, Gaël Varoquaux, Bertrand Thirion, 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: decoding, Computer science, Cognitive Neuroscience, Models, Neurological, Datasets as Topic, supervised learning, Regularization (mathematics), 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, MVPA, Prior probability, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Cluster analysis, Brain Mapping, business.industry, Dimensionality reduction, fMRI, Supervised learning, Brain, Estimator, Pattern recognition, bagging, Magnetic Resonance Imaging, Neurology, Artificial intelligence, business, Algorithms, 030217 neurology & neurosurgery, Decoding methods
Abstract: Brain decoding relates behavior to brain activity through predictive models. These are also used to identify brain regions involved in the cognitive operations related to the observed behavior. Training such multivariate models is a high-dimensional statistical problem that calls for suitable priors. State of the art priors -eg small total-variation- enforce spatial structure on the maps to stabilize them and improve prediction. However, they come with a hefty computational cost. We build upon very fast dimension reduction with spatial structure and model ensembling to achieve decoders that are fast on large datasets and increase the stability of the predictions and the maps. Our approach, fast regularized ensemble of models (FReM), includes an implicit spatial regularization by using a voxel grouping with a fast clustering algorithm. In addition, it aggregates different estimators obtained across splits of a cross-validation loop, each time keeping the best possible model. Experiments on a large number of brain imaging datasets show that our combination of voxel clustering and model ensembling improves decoding maps stability and reduces the variance of prediction accuracy. Importantly, our method requires less samples than state-of-the-art methods to achieve a given level of prediction accuracy. Finally, FreM is much faster than other spatially-regularized methods and, in addition, it can better exploit parallel computing resources.
Published: 2018

11. Joint prediction of multiple scores captures better individual traits from brain images

Author: Danilo Bzdok, Gaël Varoquaux, Mehdi Rahim, Bertrand Thirion, Irène Buvat, 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), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Imagerie Moléculaire in Vivo (IMIV - U1023 - ERL9218), Service Hospitalier Frédéric Joliot (SHFJ), 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)-Centre National de la Recherche Scientifique (CNRS), Rheinisch-Westfälische Technische Hochschule Aachen University (RWTH), ANR-11-BINF-0004,NiConnect,Outils pour la Recherche Clinique par cartographie de la connectivité cérébrale fonctionnelle(2011), ANR-11-IDEX-0003,IPS,Idex Paris-Saclay(2011), 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)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Institut National de la Santé et de la Recherche Médicale (INSERM), Rheinisch-Westfälische Technische Hochschule Aachen (RWTH), Rahim, Mehdi, Bio-informatique - Outils pour la Recherche Clinique par cartographie de la connectivité cérébrale fonctionnelle - - NiConnect2011 - ANR-11-BINF-0004 - BINF - VALID, and Idex Paris-Saclay - - IPS2011 - ANR-11-IDEX-0003 - IDEX - VALID
Subjects: 0301 basic medicine, Disease status, Cognitive Neuroscience, Schizophrenia (object-oriented programming), Population, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Individuality, Machine learning, computer.software_genre, Brain mapping, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Alzheimer Disease, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Computer Simulation, [SDV.NEU] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], education, Brain Mapping, Brain organization, education.field_of_study, business.industry, Brain, Magnetic Resonance Imaging, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Phenotype, 030104 developmental biology, Neurology, Schizophrenia, [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], Data mining, Artificial intelligence, business, Joint (audio engineering), Psychology, computer, Algorithms, 030217 neurology & neurosurgery
Abstract: International audience; To probe individual variations in brain organization, population imaging relates features of brain images to rich descriptions of the subjects such as genetic information or behavioral and clinical assessments. Capturing common trends across these measurements is important: they jointly characterize the disease status of patient groups. In particular, mapping imaging features to behavioral scores with predictive models opens the way toward more precise diagnosis. Here we propose to jointly predict all the dimensions (behavioral scores) that make up the individual profiles, using so-called multi-output models. This approach often boosts prediction accuracy by capturing latent shared information across scores. We demonstrate the efficiency of multi-output models on two independent resting-state fMRI datasets targeting different brain disorders (Alzheimer's Disease and schizophrenia). Furthermore, the model with joint prediction generalizes much better to a new cohort: a model learned on one study is more accurately transferred to an independent one. Finally, we show how multi-output models can easily be extended to multi-modal settings, combining heterogeneous data sources for a better overall accuracy.
Published: 2017

12. Local Optimal Transport for Functional Brain Template Estimation

Author: Hicham Janati, Thomas Bazeille, Hugo Richard, 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), European Project: 785907,H2020,HBP SGA2(2018), 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, Existential quantification, Inference, Machine learning, computer.software_genre, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Template estimation, 03 medical and health sciences, Functional brain, 0302 clinical medicine, Neuroimaging, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], 030304 developmental biology, 0303 health sciences, business.industry, Brain, Cognition, Atlas Inference, Template, FMRI, Artificial intelligence, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], business, computer, 030217 neurology & neurosurgery, Smoothing, Functionnal Alignment
Abstract: International audience; An important goal of cognitive brain imaging studies is to model the functional organization of the brain; yet there exists currently no functional brain atlas built from existing data. One of the main roadblocks to the creation of such an atlas is the functional variability that is observed in subjects performing the same task; this variability goes far beyond anatomical variability in brain shape and size. Function-based alignment procedures have recently been proposed in order to improve the correspondence of activation patterns across individuals. However, the corresponding computational solutions are costly and not well-principled. Here, we propose a new framework based on optimal transport theory to create such a template. We leverage entropic smoothing as an efficient means to create brain templates without losing fine-grain structural information; it is implemented in a computationally efficient way. We evaluate our approach on rich multi-subject, multi-contrasts datasets. These experiments demonstrate that the template-based inference procedure improves the transfer of information across individuals with respect to state of the art methods.
Published: 2019

13. ECKO: Ensemble of Clustered Knockoffs for robust multivariate inference on MRI data

Author: Jérôme-Alexis Chevalier, Tuan-Binh Nguyen, Bertrand Thirion, 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, IFR49 - Neurospin - CEA, Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Laboratoire de Mathématiques d'Orsay (LMO), Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS), Statistique mathématique et apprentissage (CELESTE), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire de Mathématiques d'Orsay (LMO), Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Télécom ParisTech, ANR-17-CE23-0011,FAST-BIG,Tests Statistiques efficaces pour les données de grande dimension: application à l'imagerie cérébrale et la génétique(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: False discovery rate, Multivariate statistics, [STAT.AP]Statistics [stat]/Applications [stat.AP], Variables, Computer science, business.industry, media_common.quotation_subject, [SCCO.NEUR]Cognitive science/Neuroscience, Inference, Pattern recognition, [STAT.TH]Statistics [stat]/Statistics Theory [stat.TH], Covariance, Nominal level, Feature (machine learning), Artificial intelligence, business, Cluster analysis, [STAT.ME]Statistics [stat]/Methodology [stat.ME], media_common
Abstract: International audience; Continuous improvement in medical imaging techniques allows the acquisition of higher-resolution images. When these are used in a predictive setting, a greater number of explanatory variables are potentially related to the dependent variable (the response). Meanwhile, the number of acquisitions per experiment remains limited. In such high dimension/small sample size setting, it is desirable to find the explanatory variables that are truly related to the response while controlling the rate of false discoveries. To achieve this goal, novel multivariate inference procedures, such as knockoff inference, have been proposed recently. However, they require the feature covariance to be well-defined, which is impossible in high-dimensional settings. In this paper, we propose a new algorithm, called Ensemble of Clustered Knockoffs, that allows to select explanatory variables while controlling the false discovery rate (FDR), up to a prescribed spatial tolerance. The core idea is that knockoff-based inference can be applied on groups (clusters) of voxels, which drastically reduces the problem's dimension; an ensembling step then removes the dependence on a fixed clustering and stabilizes the results. We benchmark this algorithm and other FDR-controlling methods on brain imaging datasets and observe empirical gains in sensitivity, while the false discovery rate is controlled at the nominal level.
Published: 2019

14. Group Level MEG/EEG Source Imaging via Optimal Transport: Minimum Wasserstein Estimates

Author: Marco Cuturi, Bertrand Thirion, Hicham Janati, Thomas Bazeille, and Alexandre Gramfort
Subjects: Similarity (geometry), medicine.diagnostic_test, business.industry, Computer science, Inference, Pattern recognition, 010103 numerical & computational mathematics, Magnetoencephalography, Inverse problem, Electroencephalography, 01 natural sciences, Measure (mathematics), 03 medical and health sciences, 0302 clinical medicine, medicine, Artificial intelligence, 0101 mathematics, Functional magnetic resonance imaging, business, Spatial analysis, 030217 neurology & neurosurgery
Abstract: Magnetoencephalography (MEG) and electroencephalogra-phy (EEG) are non-invasive modalities that measure the weak electromagnetic fields generated by neural activity. Inferring the location of the current sources that generated these magnetic fields is an ill-posed inverse problem known as source imaging. When considering a group study, a baseline approach consists in carrying out the estimation of these sources independently for each subject. The ill-posedness of each problem is typically addressed using sparsity promoting regularizations. A straightforward way to define a common pattern for these sources is then to average them. A more advanced alternative relies on a joint localization of sources for all subjects taken together, by enforcing some similarity across all estimated sources. An important advantage of this approach is that it consists in a single estimation in which all measurements are pooled together, making the inverse problem better posed. Such a joint estimation poses however a few challenges, notably the selection of a valid regularizer that can quantify such spatial similarities. We propose in this work a new procedure that can do so while taking into account the geometrical structure of the cortex. We call this procedure Minimum Wasserstein Estimates (MWE). The benefits of this model are twofold. First, joint inference allows to pool together the data of different brain geometries, accumulating more spatial information. Second, MWE are defined through Optimal Transport (OT) metrics which provide a tool to model spatial proximity between cortical sources of different subjects, hence not enforcing identical source location in the group. These benefits allow MWE to be more accurate than standard MEG source localization techniques. To support these claims, we perform source localization on realistic MEG simulations based on forward operators derived from MRI scans. On a visual task dataset, we demonstrate how MWE infer neural patterns similar to functional Magnetic Resonance Imaging (fMRI) maps.
Published: 2019

15. Inference and Prediction Diverge in Biomedicine

Author: Denis A. Engemann, Danilo Bzdok, and Bertrand Thirion
Subjects: Computer science, Significant group, General Decision Sciences, Inference, Medical care, Article, explainable AI, 03 medical and health sciences, 0302 clinical medicine, scientific discovery, Econometrics, reproducibility, Biomedicine, 030304 developmental biology, lcsh:Computer software, 0303 health sciences, business.industry, Linear model, Precision medicine, Regression, 3. Good health, Variable (computer science), lcsh:QA76.75-76.765, variable importance, data science, business, 030217 neurology & neurosurgery
Abstract: Summary In the 20th century, many advances in biological knowledge and evidence-based medicine were supported by p values and accompanying methods. In the early 21st century, ambitions toward precision medicine place a premium on detailed predictions for single individuals. The shift causes tension between traditional regression methods used to infer statistically significant group differences and burgeoning predictive analysis tools suited to forecast an individual's future. Our comparison applies linear models for identifying significant contributing variables and for finding the most predictive variable sets. In systematic data simulations and common medical datasets, we explored how variables identified as significantly relevant and variables identified as predictively relevant can agree or diverge. Across analysis scenarios, even small predictive performances typically coincided with finding underlying significant statistical relationships, but not vice versa. More complete understanding of different ways to define “important” associations is a prerequisite for reproducible research and advances toward personalizing medical care., Highlights • We systematically juxtapose variable selection using significance versus prediction • Successful prediction often coincided with significant p values • Yet strong statistical significance did not always coincide with predictive value • Understanding the inference-prediction dilemma is imperative for precision medicine, The Bigger Picture Across research communities, the analysis goals of inference and prediction are two sides of a coin. Many empirical studies leaning on statistical significance typically focus interpretation on the best p values obtained for one or a few variables. In contrast, many empirical studies dedicated to prediction are backed up by cross-validated model performance on fresh data points. In a future of single-patient prediction from big biomedical data, it may become central that modeling for inference and modeling for prediction are related but importantly different. The relevant subset of variables identified based on p values or based on predictive value can converge or diverge depending on the data scenario. We show that diverging conclusions can emerge even when the data are identical and when widespread linear models are used. Awareness of the relative strengths and weaknesses of both “data-analysis cultures” may become unavoidable in navigating between complementary goals in scientific inquiry., In systematic empirical data simulations and real-world biomedical datasets, we explore scenarios of agreement and disagreement between variables identified as statistically significant or variables identified as predictively relevant.
Published: 2020

16. Benchmarking functional connectome-based predictive models for resting-state fMRI

Author: Michael P. Milham, Bertrand Thirion, Alexandre Abraham, Darya Chyzhyk, Kamalaker Dadi, Mehdi Rahim, Gaël Varoquaux, 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), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Nathan S. Kline Institute for Psychiatric Research (NKI), New York State Office of Mental Health, 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, Rest, Models, Neurological, Machine learning, computer.software_genre, 050105 experimental psychology, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Connectome, Humans, 0501 psychology and cognitive sciences, Resting-state fMRI, Functional connectomes, Resting state fMRI, business.industry, 05 social sciences, Supervised learning, Brain, Benchmarking, medicine.disease, Classification, Magnetic Resonance Imaging, Predictive modeling, Neurology, Schizophrenia, Benchmark (computing), Artificial intelligence, business, computer, 030217 neurology & neurosurgery, Population study
Abstract: International audience; Functional connectomes reveal biomarkers of individual psychological or clinical traits. However, there is great variability in the analytic pipelines typically used to derive them from rest-fMRI cohorts. Here, we consider a specific type of studies, using predictive models on the edge weights of functional connectomes, for which we highlight the best modeling choices. We systematically study the prediction performances of models in 6 different cohorts and a total of 2 000 individuals, encompassing neuro-degenerative (Alzheimer’s, Post-traumatic stress disorder), neuro-psychiatric (Schizophrenia, Autism), drug impact (Cannabis use) clinical settings and psychological trait (fluid intelligence). The typical prediction procedure from rest-fMRI consists of three main steps: defining brain regions, representing the interactions, and supervised learning. For each step we benchmark typical choices: 8 different ways of defining regions –either pre-defined or generated from the rest-fMRI data– 3 measures to build functional connectomes from the extracted time-series, and 10 classification models to compare functional interactions across subjects. Our benchmarks summarize more than 240 different pipelines and outline modeling choices that show consistent prediction performances in spite of variations inthe populations and sites. We find that regions defined from functional data work best; that it is beneficial to capture between-region interactions with tangent-based parametrization of covariances, a midway between correlations and partial correlation; and that simple linear predictors such as a logistic regression give the best predictions. Our work is a step forward to establishing reproducible imaging-based biomarkers for clinical settings.
Published: 2018

17. Controlling a confound in predictive models with a test set minimizing its effect

Author: Michael P. Milham, Bertrand Thirion, Gaël Varoquaux, Darya Chyzhyk, 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), Nathan S. Kline Institute for Psychiatric Research (NKI), New York State Office of Mental Health, 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: 0301 basic medicine, Computer science, phenotype, subsampling, Machine learning, computer.software_genre, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], statistical testing, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], confound, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Healthy aging, Statistical hypothesis testing, business.industry, Linear model, biomarkers, Mutual information, Variance (accounting), predictive models, Confounding effect, 030104 developmental biology, Test set, Biomarker (medicine), Artificial intelligence, business, computer, 030217 neurology & neurosurgery
Abstract: International audience; Predictive models applied on brain images can extract imaging biomarkers of pathologies or psychological traits. Yet, a successful prediction may be driven by a confounding effect that is correlated with the effect of interest. For instance fluid intelligence is strongly impacted by age; age is well predicted from brain images; hence successful prediction of fluid intelligence from brain images might have captured nothing more than a biomarker of aging. Here we introduce a non-parametric approach to control for a confounding effect in a predictive model. It is based on crafting a test set on which the effect of interest is independent from the confounding effect. We name this strategy " anti mutual-information subsampling ". We demonstrate the approach with a large sample resting-state fMRI and psychometric data of healthy aging subjects (n = 608). We show that using a linear model to remove the effect of age on the brain signals (" deconfounding ") leads to pessimistic scores, as previously reported. Anti mutual-information subsampling does not require to remove from the brain signals the shared variance between aging and fluid intelligence, and hence does not display this pessimistic behavior. In addition, it is non-parametric and hence robust to violations of the linear hypothesis.
Published: 2018

18. Prediction and inference diverge in biomedicine: Simulations and real-world data

Author: Gaël Varoquaux, Danilo Bzdok, Bertrand Thirion, Denis A. Engemann, Olivier Grisel, Department of Psychiatry, Psychotherapy and Psychosomatics [Aachen], 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), Nuxeo, nuxeo, 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: Value (ethics), Computer science, Inference, MESH: data science, Machine learning, computer.software_genre, 01 natural sciences, 010104 statistics & probability, 03 medical and health sciences, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistical inference, 0101 mathematics, Clinical care, Biomedicine, 030304 developmental biology, 0303 health sciences, [STAT.AP]Statistics [stat]/Applications [stat.AP], business.industry, Linear model, MESH: scientific discovery, Precision medicine, 3. Good health, Variable (computer science), MESH: intelligent algorithms, Pattern recognition (psychology), [SDV.SPEE]Life Sciences [q-bio]/Santé publique et épidémiologie, Artificial intelligence, business, Real world data, computer, MESH: variable importance, MESH: reproducibility
Abstract: In the 20thcentury many advances in biological knowledge and evidence-based medicine were supported by p-values and accompanying methods. In the beginning 21stcentury, ambitions towards precision medicine put a premium on detailed predictions for single individuals. The shift causes tension between traditional methods used to infer statistically significant group differences and burgeoning machine-learning tools suited to forecast an individual’s future. This comparison applies the linear model for identifyingsignificantcontributing variables and for finding the mostpredictivevariable sets. In systematic data simulations and common medical datasets, we explored how statistical inference and pattern recognition can agree and diverge. Across analysis scenarios, even small predictive performances typically coincided with finding underlying significant statistical relationships. However, even statistically strong findings with very low p-values shed little light on their value for achieving accurate prediction in the same dataset. More complete understanding of different ways to define ‘important’ associations is a prerequisite for reproducible research findings that can serve to personalize clinical care.
Published: 2018

19. Optimizing deep video representation to match brain activity

Author: Hugo Richard, Guillaume Charpiat, Bertrand Thirion, Ana Luísa Pinho, 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, TAckling the Underspecified (TAU), Laboratoire de Recherche en Informatique (LRI), CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-CentraleSupélec-Université Paris-Sud - Paris 11 (UP11)-Centre National de la Recherche Scientifique (CNRS)-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)-Inria Saclay - Ile de France, and Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Inria Saclay - Ile de France
Subjects: FOS: Computer and information sciences, Computer Science - Machine Learning, genetic structures, Brain activity and meditation, Computer science, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Optical flow, 02 engineering and technology, Brain mapping, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], Machine Learning (cs.LG), 030218 nuclear medicine & medical imaging, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Foveal, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0202 electrical engineering, electronic engineering, information engineering, Neural and Evolutionary Computing (cs.NE), Association (psychology), business.industry, Deep learning, Representation (systemics), Computer Science - Neural and Evolutionary Computing, deep learning, Image content, Pattern recognition, eye diseases, video encoding, Quantitative Biology - Neurons and Cognition, FOS: Biological sciences, brain mapping, Neurons and Cognition (q-bio.NC), 020201 artificial intelligence & image processing, Artificial intelligence, business
Abstract: International audience; The comparison of observed brain activity with the statistics generated by artificial intelligence systems is useful to probe brain functional organization under ecological conditions. Here we study fMRI activity in ten subjects watching color natural movies and compute deep representations of these movies with an architecture that relies on optical flow and image content. The association of activity in visual areas with the different layers of the deep architecture displays complexity-related contrasts across visual areas and reveals a striking foveal/peripheral dichotomy.
Published: 2018

20. Decoding fMRI activity in the time domain improves classification performance

Author: João Loula, Gaël Varoquaux, Bertrand Thirion, Université Paris-Saclay, 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: Computer science, Cognitive Neuroscience, Speech recognition, Decoding, Models, Neurological, Functional magnetic resonance imaging, [SCCO.COMP]Cognitive science/Computer science, 050105 experimental psychology, Rapid event-related design, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], MVPA, medicine, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, 0501 psychology and cognitive sciences, Time domain, Brain Mapping, Series (mathematics), medicine.diagnostic_test, Event (computing), business.industry, 05 social sciences, Classification analysis, Brain, Pattern recognition, Magnetic Resonance Imaging, Neurology, Deconvolution, Artificial intelligence, business, 030217 neurology & neurosurgery, Decoding methods
Abstract: International audience; Most current functional Magnetic Resonance Imaging (fMRI) decoding analyses rely on statistical summaries of the data resulting from a deconvolution approach: each stimulation event is associated with a brain response. This standard approach leads to simple learning procedures, yet it is ill-suited for decoding events with short inter-stimulus intervals. In order to overcome this issue, we propose a novel framework thatseparates the spatial and temporal components of the prediction by decoding the fMRI time-series continuously, i.e. scan-by-scan. The stimulation events can then be identified through a deconvolution of the reconstructed time series. We show that this model performs as well as or better than standard approaches across several datasets, most notably in regimes with small inter-stimuli intervals (3 to 5s), while also offering predictionsthat are highly interpretable in the time domain. This opens the way toward analyzing datasets not normally thought of as suitable for decoding and makes it possible to run decoding on studies with reduced scan time.
Published: 2017

21. Hierarchical Region-Network Sparsity for High-Dimensional Inference in Brain Imaging

Author: Gaël Varoquaux, Michael Eickenberg, Danilo Bzdok, 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), Department of Psychiatry, Psychotherapy and Psychosomatics [Aachen], Rheinisch-Westfälische Technische Hochschule Aachen University (RWTH), 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 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, Rheinisch-Westfälische Technische Hochschule Aachen (RWTH), and Bzdok, Danilo
Subjects: 0301 basic medicine, [INFO.INFO-TS] Computer Science [cs]/Signal and Image Processing, Generalization, [SDV.NEU.NB]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology, Inference, Machine learning, computer.software_genre, curse of dimensionality, Article, 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, Prior probability, Interpretability, Mathematics, neuroimaging, Functional integration (neurobiology), business.industry, [SDV.NEU.NB] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Neurobiology, Statistical model, Pattern recognition, structured sparsity, Independent component analysis, Tree (data structure), 030104 developmental biology, machine learning, Artificial intelligence, parietal, business, computer, 030217 neurology & neurosurgery
Abstract: International audience; Structured sparsity penalization has recently improved statistical models applied to high-dimensional data in various domains. As an extension to medical imaging, the present work incorporates priors on network hierarchies of brain regions into logistic-regression to distinguish neural activity effects. These priors bridge two separately studied levels of brain architecture: functional segregation into regions and functional integration by networks. Hierarchical region-network priors are shown to better classify and recover 18 psychological tasks than other sparse esti-mators. Varying the relative importance of region and network structure within the hierarchical tree penalty captured complementary aspects of the neural activity patterns. Local and global priors of neurobiological knowledge are thus demonstrated to offer advantages in generalization performance, sample complexity, and domain interpretability.
Published: 2017

22. Towards a Faster Randomized Parcellation Based Inference

Author: Gaël Varoquaux, Bertrand Thirion, Andrés Hoyos-Idrobo, Microsoft Research - Inria Joint Centre (MSR - INRIA), Institut National de Recherche en Informatique et en Automatique (Inria)-Microsoft Research Laboratory Cambridge-Microsoft Corporation [Redmond, Wash.], 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), This project received funding from the European Union’s Horizon 2020 Framework Program for Research and Innovation under Grant Agreement No 720270 (Human Brain Project SGA1)., 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: Speedup, Computer science, Population, Stability (learning theory), Inference, Machine learning, computer.software_genre, 01 natural sciences, 010104 statistics & probability, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Resampling, 0101 mathematics, education, Cluster analysis, reproducibility, Group analysis, multiple comparisons, education.field_of_study, [STAT.AP]Statistics [stat]/Applications [stat.AP], business.industry, [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, Hierarchical clustering, [STAT]Statistics [stat], parcellation, Multiple comparisons problem, Data mining, Artificial intelligence, business, computer, 030217 neurology & neurosurgery
Abstract: International audience; In neuroimaging, multi-subject statistical analysis is an essential step, as it makes it possible to draw conclusions for the population under study. However, the lack of power in neuroimaging studies combined with the lack of stability and sensitivity of voxel-based methods may lead to non-reproducible results. A method designed to tackle this problem is Randomized Parcellation-Based Inference (RPBI), which has shown good empirical performance. Nevertheless, the use of an agglomerative clustering algorithm proposed in the initial RPBI formulation to build the parcellations entails a large computation cost. In this paper, we explore two strategies to speedup RPBI: Firstly, we use a fast clustering algorithm called Recursive Nearest Agglomeration (ReNA), to find the parcellations. Secondly, we consider the aggregation of p-values over multiple parcellations to avoid a permutation test. We evaluate their the computation time, as well as their recovery performance. As a main conclusion, we advocate the use of (permuted) RPBI with ReNA, as it yields very fast models, while keeping the performance of slower methods.
Published: 2017

23. Seeing it all: Convolutional network layers map the function of the human visual system

Author: Alexandre Gramfort, Bertrand Thirion, Michael Eickenberg, Gaël Varoquaux, 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 Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), European Union Seventh Framework Programme (FP7/2007-2013) under grant agreement no. 604102 ('Human Brain Project')France-Berkeley Fund 2012, 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: 0301 basic medicine, convolutional networks, vision, genetic structures, Computer science, Cognitive Neuroscience, fmri, Models, Neurological, Brain mapping, [INFO.INFO-AI]Computer Science [cs]/Artificial Intelligence [cs.AI], 03 medical and health sciences, 0302 clinical medicine, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Encoding (memory), medicine, Image Processing, Computer-Assisted, Humans, Computer vision, Visual Pathways, Visual Cortex, Brain Mapping, business.industry, [SCCO.NEUR]Cognitive science/Neuroscience, [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, Signal Processing, Computer-Assisted, Human brain, Net (mathematics), Magnetic Resonance Imaging, 030104 developmental biology, medicine.anatomical_structure, machine learning, Neurology, Retinotopy, Human visual system model, Visual Perception, [SDV.NEU]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC], Artificial intelligence, business, 030217 neurology & neurosurgery, Photic Stimulation
Abstract: International audience; Convolutional networks used for computer vision represent candidate models for the computations performed in mammalian visual systems. We use them as a detailed model of human brain activity during the viewing of natural images by constructing predictive models based on their different layers and BOLD fMRI activations. Analyzing the predictive performance across layers yields characteristic fingerprints for each visual brain region: early visual areas are better described by lower level convolutional net layers and later visual areas by higher level net layers, exhibiting a progression across ventral and dorsal streams. Our predictive model generalizes beyond brain responses to natural images. We illustrate this on two experiments, namely retinotopy and face-place oppositions, by synthesizing brain activity and performing classical brain mapping upon it. The synthesis recovers the activations observed in the corresponding fMRI studies, showing that this deep encoding model captures representations of brain function that are universal across experimental paradigms.
Published: 2017
Full Text: View/download PDF

24. Probabilistic atlas and geometric variability estimation to drive tissue segmentation

Author: Hao Xu, Stéphanie Allassonnière, Bertrand Thirion, Centre de Mathématiques Appliquées - Ecole Polytechnique (CMAP), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS), 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), Digiteo MMoVNI project, 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: Diagnostic Imaging, Statistics and Probability, Biometry, Epidemiology, Computer science, education, Population, stochastic algorithm, Atlases as Topic, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Computer Simulation, Segmentation, Computer vision, Probabilistic atlas, Anatomy, Artistic, atlas-based segmentation, Probability, neuro-segmentation coupled with registration, education.field_of_study, Models, Statistical, Tissue segmentation, Atlas (topology), business.industry, Brain, Bayes Theorem, Statistical model, Classification, Magnetic Resonance Imaging, Radiography, statistical estimation, Template, geometric variability, Artificial intelligence, business, Algorithms
Abstract: International audience; Computerized anatomical atlases play an important role in medical image analysis. While an atlas usually refers to a standard or mean image also called template, that presumably represents well a given population, it is not enough to characterize the observed population in detail. A template image should be learned jointly with the geometric variability of the shapes represented in the observations. These two quantities will in the sequel form the atlas of the corresponding population. The geometric variability is modelled as deformations of the template image so that it fits the observations. In this paper, we provide a detailed analysis of a new generative statistical model based on dense deformable templates that represents several tissue types observed in medical images. Our atlas contains both an estimation of probability maps of each tissue (called class) and the deformation metric. We use a stochastic algorithm for the estimation of the probabilistic atlas given a dataset. This atlas is then used for atlas-based segmentation method to segment the new images. Experiments are shown on brain T1 MRI datasets.
Published: 2014

25. Randomized parcellation based inference

Author: Vincent Frouin, Tomáš Paus, Jean-Luc Martinot, Gareth J. Barker, Marcella Rietschel, Gaël Varoquaux, Patricia J. Conrod, Jean-Baptiste Poline, Uli Bromberg, Arun L.W. Bokde, Frauke Nees, Jürgen Gallinat, Bertrand Thirion, Virgile Fritsch, Tobias Banaschewski, Andreas Ströhle, Michael N. Smolka, Zdenka Pausova, Hugh Garavan, Benoit Da Mota, 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 de Neuroimagerie Assistée par Ordinateur (LNAO), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Department of Child and Adolescent Psychiatry and Psychotherapy [Mannheim], Universität Heidelberg [Heidelberg] = Heidelberg University, Institute of Psychiatry, King‘s College London, Institute of Neuroscience, Trinity College Dublin-Trinity College Dublin-Discipline of Psychiatry [Dublin], School of Medicine [Dublin], Trinity College Dublin-Trinity College Dublin-School of Medicine [Dublin], Trinity College Dublin, Universitaetsklinikum Hamburg-Eppendorf = University Medical Center Hamburg-Eppendorf [Hamburg] (UKE), Institute of Psychiatry, Psychology & Neuroscience, King's College London, Department of Psychiatry and Psychotherapy, Charité - UniversitätsMedizin = Charité - University Hospital [Berlin], University of Vermont [Burlington], Neuroimagerie en psychiatrie (U1000), Université Paris-Sud - Paris 11 (UP11)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris Descartes - Paris 5 (UPD5)-Institut National de la Santé et de la Recherche Médicale (INSERM), Rotman Research Institute at the Baycrest Centre (RRI), McConnell Brain Imaging Centre (MNI), Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada]-McGill University = Université McGill [Montréal, Canada], School of Psychology [Nottingham], University of Nottingham, UK (UON), SickKids - The Hospital for sick children, The Hospital for sick children [Toronto] (SickKids), Department of Genetic Epidemiology in Psychiatry [Mannhein], Universität Heidelberg [Heidelberg] = Heidelberg University-Central Institute of Mental Health Mannheim, Technische Universität Dresden = Dresden University of Technology (TU Dresden), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Digitéo (HiDiNim project and ICoGeN project), Imagen Consortium, European Project: 39513,IMAGEN, 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), Universität Heidelberg [Heidelberg], Institut National de la Santé et de la Recherche Médicale (INSERM)-Université Paris Descartes - Paris 5 (UPD5)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Sud - Paris 11 (UP11), Universität Heidelberg [Heidelberg]-Central Institute of Mental Health Mannheim, Fritsch, Virgile, and Reinforcement-related behaviour in normal brain function and psychopathology - IMAGEN - 39513 - OLD
Subjects: [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, permutations, Cognitive Neuroscience, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, Inference, Neuroimaging, Stop signal, Catechol O-Methyltransferase, computer.software_genre, Polymorphism, Single Nucleotide, [STAT.AP] Statistics [stat]/Applications [stat.AP], Voxel, Resampling, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, medicine, Cluster Analysis, Humans, Computer Simulation, reproducibility, Genetic Association Studies, multiple comparisons, [STAT.AP]Statistics [stat]/Applications [stat.AP], medicine.diagnostic_test, business.industry, Brain, Contrast (statistics), Pattern recognition, Magnetic Resonance Imaging, [SDV.IB.IMA] Life Sciences [q-bio]/Bioengineering/Imaging, Neurology, group analysis, parcellation, Multiple comparisons problem, Data mining, Artificial intelligence, Functional magnetic resonance imaging, Psychology, business, computer
Abstract: International audience; Neuroimaging group analyses are used to relate inter-subject signal differences observed in brain imaging with behavioral or genetic variables and to assess risks factors of brain diseases. The lack of stability and of sensitivity of current voxel-based analysis schemes may however lead to non-reproducible results. We introduce a new approach to overcome the limitations of standard methods, in which active voxels are detected according to a consensus on several random parcellations of the brain images, while a permutation test controls the false positive risk. Both on synthetic and real data, this approach shows higher sensitivity, better accuracy and higher reproducibility than state-of-the-art methods. In a neuroimaging-genetic application, we find that it succeeds in detecting a significant association between a genetic variant next to the COMT gene and the BOLD signal in the left thalamus for a functional Magnetic Resonance Imaging contrast associated with incorrect responses of the subjects from a Stop Signal Task protocol.
Published: 2014

26. Bayesian estimation of probabilistic atlas for tissue segmentation

Author: Bertrand Thirion, Hao Xu, and Stéphanie Allassonnière
Subjects: business.industry, Atlas (topology), Computer science, Biomedical Engineering, Biophysics, Probabilistic logic, Partial volume, Scale-space segmentation, Pattern recognition, Statistical model, Image segmentation, Metric (mathematics), Segmentation, Computer vision, Artificial intelligence, business
Abstract: Automatic anatomical brain image segmentation is still a challenge. In particular, algorithms have to address the partial volume effect (PVE) as well as the variability of the gray level of internal brain structures which may appear closer to gray matter (GM) than white matter (WM). Atlas based segmentation is one solution as it brings prior information. For such tasks, probabilistic atlases are very useful as they take account of the PVE information. In this paper, we provide a detailed analysis of a generative statistical model based on dense deformable templates that represents several tissue types observed in medical images. The inputs are gray level data whereas our atlas is composed of both an estimation of the deformation metric and probability maps of each tissue (called class). This atlas is used to guide the tissue segmentation of new images. Experiments are shown on brain T1 MRI datasets. This method only requires approximate pre-registration, as the latter is done jointly with the segmentation. Note however that an approximate registration is a reasonable pre-requisite given the application.
Published: 2014

27. Structural Magnetic Resonance Imaging

Author: Bertrand Thirion
Subjects: education.field_of_study, business.industry, Population, Univariate, Inference, Machine learning, computer.software_genre, Neuroimaging, Functional neuroimaging, Econometrics, Statistical inference, Artificial intelligence, business, Set (psychology), education, Psychology, computer, Statistical hypothesis testing
Abstract: Multi-subject statistical analysis is an essential step of neuroimaging studies, as it makes it possible to draw conclusions that hold with a prescribed confidence level for the population under study. The use of the linear assumption to model activation signals in brain images and their modulation by various factors has opened the possibility to rely on relatively simple estimation and statistical testing procedures. Specifically, the analysis of functional neuroimaging signals is typically carried out on a per-voxel basis, in the so-called mass univariate framework. However, the lack of power in neuroimaging studies has incited neuroscientists to develop new procedures to improve this framework: various solutions have been set up to take into account the spatial context in statistical inference or to deal with violations of distributional assumptions of the data. In this chapter, we review the general framework for group inference, the ensuing mixed-effects model design and its simplifications, together with the various solutions that have been considered to improve the standard mass-univariate testing framework.
Published: 2016

28. Transmodal Learning of Functional Networks for Alzheimer's Disease Prediction

Author: Gaël Varoquaux, Claude Comtat, Mehdi Rahim, Bertrand Thirion, 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), Service Hospitalier Frédéric Joliot (SHFJ), ANR-11-BINF-0004,NiConnect,Outils pour la Recherche Clinique par cartographie de la connectivité cérébrale fonctionnelle(2011), ANR-11-IDEX-0003,IPS,Idex Paris-Saclay(2011), 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: Brain activity and meditation, Computer science, metabolic activity, Machine learning, computer.software_genre, Alzheimer's Disease, 050105 experimental psychology, Article, Correlation, Resting-state, 03 medical and health sciences, 0302 clinical medicine, Discriminative model, [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0501 psychology and cognitive sciences, Electrical and Electronic Engineering, FDG-PET, Modality (human–computer interaction), medicine.diagnostic_test, Resting state fMRI, business.industry, 05 social sciences, functional connectivity, fMRI, classification, Positron emission tomography, Signal Processing, Connectome, Artificial intelligence, business, Functional magnetic resonance imaging, computer, 030217 neurology & neurosurgery
Abstract: International audience; Functional connectivity describes neural activity from resting-state functional magnetic resonance imaging (rs-fMRI). This noninvasive modality is a promising imaging biomarker of neurodegenerative diseases, such as Alzheimer's disease (AD), where the connectome can be an indicator to assess and to understand the pathology. However, it only provides noisy measurements of brain activity. As a consequence, it has shown fairly limited discrimination power on clinical groups. So far, the reference functional marker of AD is the fluorodeoxyglucose positron emission tomography (FDG-PET). It gives a reliable quantification of metabolic activity, but it is costly and invasive. Here, our goal is to analyze AD populations solely based on rs-fMRI, as functional connectivity is correlated to metabolism. We introduce transmodal learning: leveraging a prior from one modality to improve results of another modality on different subjects. A metabolic prior is learned from an independent FDG-PET dataset to improve functional connectivity-based prediction of AD. The prior acts as a regularization of connectivity learning and improves the estimation of discriminative patterns from distinct rs-fMRI datasets. Our approach is a two-stage classification strategy that combines several seed-based connectivity maps to cover a large number of functional networks that identify AD physiopathology. Experimental results show that our transmodal approach increases classification accuracy compared to pure rs-fMRI approaches, without resorting to additional invasive acquisitions. The method successfully recovers brain regions known to be impacted by the disease.
Published: 2016

29. Deriving robust biomarkers from multi-site resting-state data: An Autism-based example

Author: Alexandre Abraham, Dimitris Samaras, Michael P. Milham, Gaël Varoquaux, Adriana Di Martino, Bertrand Thirion, and R. Cameron Craddock
Subjects: 0303 health sciences, Resting state fMRI, medicine.diagnostic_test, Computer science, business.industry, Multi site, medicine.disease, Machine learning, computer.software_genre, Pipeline (software), 03 medical and health sciences, 0302 clinical medicine, Sample size determination, Connectome, medicine, Autism, Artificial intelligence, Biomarker discovery, Functional magnetic resonance imaging, business, computer, 030217 neurology & neurosurgery, 030304 developmental biology
Abstract: Resting-state functional Magnetic Resonance Imaging (R-fMRI) holds the promise to reveal functional biomarkers of neuropsychiatric disorders. However, extracting such biomarkers is challenging for complex multi-faceted neuropathologies, such as autism spectrum disorders. Large multi-site datasets increase sample sizes to compensate for this complexity, at the cost of uncontrolled heterogeneity. This heterogeneity raises new challenges, akin to those face in realistic diagnostic applications. Here, we demonstrate the feasibility of inter-site classification of neuropsychiatric status, with an application to the Autism Brain Imaging Data Exchange (ABIDE) database, a large (N=871) multi-site autism dataset. For this purpose, we investigate pipelines that extract the most predictive biomarkers from the data. These R-fMRI pipelines build participant-specific connectomes from functionally-defined brain areas. Connectomes are then compared across participants to learn patterns of connectivity that differentiate typical controls from individuals with autism. We predict this neuropsychiatric status for participants from the same acquisition sites or different, unseen, ones. Good choices of methods for the various steps of the pipeline lead to 67% prediction accuracy on the full ABIDE data, which is significantly better than previously reported results. We perform extensive validation on multiple subsets of the data defined by different inclusion criteria. These enables detailed analysis of the factors contributing to successful connectome-based prediction. First, prediction accuracy improves as we include more subjects, up to the maximum amount of subjects available. Second, the definition of functional brain areas is of paramount importance for biomarker discovery: brain areas extracted from large R-fMRI datasets outperform reference atlases in the classification tasks.
Published: 2016
Full Text: View/download PDF

30. Compressed Online Dictionary Learning for Fast Resting-State fMRI Decomposition

Author: Bertrand Thirion, Gaël Varoquaux, Arthur Mensch, 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), IEEE, European Project: 284941,EC:FP7:ICT,FP7-ICT-2011-FET-F,HBP(2011), 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: Resting state fMRI, Computer science, business.industry, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, range finder, online learning, sparse decomposition, Pattern recognition, 02 engineering and technology, Sparse approximation, Measure (mathematics), Reduction (complexity), 03 medical and health sciences, 0302 clinical medicine, Dimension (vector space), [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], 0202 electrical engineering, electronic engineering, information engineering, Decomposition (computer science), 020201 artificial intelligence & image processing, Artificial intelligence, Resting-state fMRI, business, dictionary learning, Dictionary learning, 030217 neurology & neurosurgery
Abstract: International audience; We present a method for fast resting-state fMRI spatial decompositions of very large datasets, based on the reduction of the temporal dimension before applying dictionary learning on concatenated individual records from groups of subjects. Introducing a measure of correspondence between spatial decompositions of rest fMRI, we demonstrates that time-reduced dictionary learning produces result as reliable as non-reduced decompositions. We also show that this reduction significantly improves computational scalability.
Published: 2016

31. Fast brain decoding with random sampling and random projections

Author: Bertrand Thirion, Andrés Hoyos-Idrobo, Gaël Varoquaux, Hoyos Idrobo, Andres, 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)), Funding from the EU FP7/2007-2013 under grant agreement 604102 (HBP), 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: Computer science, Feature vector, Computation, [INFO.INFO-IM] Computer Science [cs]/Medical Imaging, brain imaging, Machine learning, computer.software_genre, Brain mapping, 050105 experimental psychology, 03 medical and health sciences, 0302 clinical medicine, Neuroimaging, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0501 psychology and cognitive sciences, business.industry, 05 social sciences, Pattern recognition, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], Visualization, Support vector machine, machine learning, Kernel (image processing), Index Terms—Nyström, Artificial intelligence, High-dimensional estimators, business, computer, 030217 neurology & neurosurgery, Decoding methods
Abstract: International audience; Machine learning from brain images is a central tool for image-based diagnosis and diseases characterization. Predicting behavior from functional imaging, brain decoding, analyzes brain activity in terms of the behavior that it implies. While these multivariate techniques are becoming standard brain mapping tools, like mass-univariate analysis, they entail much larger computational costs. In an time of growing data sizes, with larger cohorts and higher-resolutions imaging, this cost is increasingly a burden. Here we consider the use of random sampling and projections as fast data approximation techniques for brain images. We evaluate their prediction accuracy and computation time on various datasets and discrimination tasks. We show that the weight maps obtained after random sampling are highly consistent with those obtained with the whole feature space, while having a fair prediction performance. Altogether, we present the practical advantage of random sampling methods in neuroimaging, showing a simple way to embed back the reduced coefficients, with only a small loss of information.
Published: 2016

32. Social-sparsity brain decoders: faster spatial sparsity

Author: Matthieu Kowalski, Gaël Varoquaux, 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), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Laboratoire des signaux et systèmes (L2S), Université Paris-Sud - Paris 11 (UP11)-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), European Project: 284941,EC:FP7:ICT,FP7-ICT-2011-FET-F,HBP(2011), 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: Computer and information sciences, 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, Machine Learning (stat.ML), Variation (game tree), computer.software_genre, 030218 nuclear medicine & medical imaging, brain decoding, 03 medical and health sciences, 0302 clinical medicine, Operator (computer programming), [INFO.INFO-TS]Computer Science [cs]/Signal and Image Processing, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Statistics - Machine Learning, Voxel, [MATH.MATH-ST]Mathematics [math]/Statistics [math.ST], Fraction (mathematics), business.industry, Small number, sparsity, [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, Pattern recognition, Support vector machine, Quantitative Biology - Neurons and Cognition, FOS: Biological sciences, Neurons and Cognition (q-bio.NC), Artificial intelligence, business, Focus (optics), computer, 030217 neurology & neurosurgery, Decoding methods, spatial regularization
Abstract: Spatially-sparse predictors are good models for brain decoding: they give accurate predictions and their weight maps are interpretable as they focus on a small number of regions. However, the state of the art, based on total variation or graph-net, is computationally costly. Here we introduce sparsity in the local neighborhood of each voxel with social-sparsity, a structured shrinkage operator. We find that, on brain imaging classification problems, social-sparsity performs almost as well as total-variation models and better than graph-net, for a fraction of the computational cost. It also very clearly outlines predictive regions. We give details of the model and the algorithm., Comment: in Pattern Recognition in NeuroImaging, Jun 2016, Trento, Italy. 2016
Published: 2016
Full Text: View/download PDF

33. Very large fMRI study using the IMAGEN database: Sensitivity–specificity and population effect modeling in relation to the underlying anatomy

Author: Tomáš Paus, Patricia J. Conrod, Yannick Schwartz, Jean-Baptiste Poline, Eva Loth, Gunter Schumann, Vincent Frouin, Bertrand Thirion, Robert Whelan, Eric Artiges, Sabine Vollstädt-Klein, and Benjamin Thyreau
Subjects: Databases, Factual, Generalization, Cognitive Neuroscience, Models, Neurological, Population, Normal Distribution, Brain mapping, Normal distribution, Statistics, Image Processing, Computer-Assisted, Humans, education, Brain Mapping, education.field_of_study, Models, Statistical, business.industry, Linear model, Brain, Reproducibility of Results, Contrast (statistics), Pattern recognition, Random effects model, Mixture model, Magnetic Resonance Imaging, Oxygen, Neurology, Artificial intelligence, Psychology, business, Algorithms
Abstract: In this paper we investigate the use of classical fMRI Random Effect (RFX) group statistics when analyzing a very large cohort and the possible improvement brought from anatomical information. Using 1326 subjects from the IMAGEN study, we first give a global picture of the evolution of the group effect t-value from a simple face-watching contrast with increasing cohort size. We obtain a wide activated pattern, far from being limited to the reasonably expected brain areas, illustrating the difference between statistical significance and practical significance. This motivates us to inject tissue-probability information into the group estimation, we model the BOLD contrast using a matter-weighted mixture of Gaussians and compare it to the common, single-Gaussian model. In both cases, the model parameters are estimated per-voxel for one subgroup, and the likelihood of both models is computed on a second, separate subgroup to reflect model generalization capacity. Various group sizes are tested, and significance is asserted using a 10-fold cross-validation scheme. We conclude that adding matter information consistently improves the quantitative analysis of BOLD responses in some areas of the brain, particularly those where accurate inter-subject registration remains challenging.
Published: 2012

34. Robust clustering of massive tractography datasets

Author: Bertrand Thirion, Jean-François Mangin, Maxime Descoteaux, Cyril Poupon, Denis Rivière, Y. Cointepas, and Pamela Guevara
Subjects: Adult, Databases, Factual, Computer science, Cognitive Neuroscience, Physics::Optics, computer.software_genre, Imaging phantom, White matter, Nerve Fibers, Voxel, Neural Pathways, Image Processing, Computer-Assisted, medicine, Cluster Analysis, Humans, Computer Simulation, Computer vision, Child, Cluster analysis, Phantoms, Imaging, Fiber (mathematics), business.industry, Brain, Reproducibility of Results, Pattern recognition, Data Compression, Magnetic Resonance Imaging, Diffusion Tensor Imaging, medicine.anatomical_structure, Neurology, Artificial intelligence, business, computer, Algorithms, Tractography, Diffusion MRI
Abstract: This paper presents a clustering method that detects the fiber bundles embedded in any MR-diffusion based tractography dataset. Our method can be seen as a compressing operation, capturing the most meaningful information enclosed in the fiber dataset. For the sake of efficiency, part of the analysis is based on clustering the white matter (WM) voxels rather than the fibers. The resulting regions of interest are used to define subset of fibers that are subdivided further into consistent bundles using a clustering of the fiber extremities. The dataset is reduced from more than one million fiber tracts to about two thousand fiber bundles. Validations are provided using simulated data and a physical phantom. We see our approach as a crucial preprocessing step before further analysis of huge fiber datasets. An important application will be the inference of detailed models of the subdivisions of white matter pathways and the mapping of the main U-fiber bundles.
Published: 2011

35. Structural Analysis of fMRI Data Revisited: Improving the Sensitivity and Reliability of fMRI Group Studies

Author: Jean-Baptiste Poline, Philippe Ciuciu, Bertrand Thirion, Alexis Roche, J.-F. Mangin, Philippe Pinel, Alan Tucholka, Computer and biological vision (ODYSSEE), Département d'informatique - ENS Paris (DI-ENS), École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Inria Paris-Rocquencourt, Institut National de Recherche en Informatique et en Automatique (Inria)-École des Ponts ParisTech (ENPC), Laboratoire Toulousain de Technologie et d'Ingénierie des Systèmes (LATTIS), 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 de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-IUT Toulouse 2 Blagnac, Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT)-Université de Toulouse (UT)-Université Toulouse - Jean Jaurès (UT2J), Université de Toulouse (UT), Neuroimagerie cognitive (LCogn), Université Paris-Sud - Paris 11 (UP11)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut National de la Santé et de la Recherche Médicale (INSERM), 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), Laboratoire de Neuroimagerie Assistée par Ordinateur (LNAO), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Service Hospitalier Frédéric Joliot (SHFJ), Département d'informatique de l'École normale supérieure (DI-ENS), École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université Toulouse - Jean Jaurès (UT2J)-IUT Toulouse 2 Blagnac, Université Toulouse - Jean Jaurès (UT2J)-Université Toulouse - Jean Jaurès (UT2J), 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)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS Paris)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-IUT Toulouse 2 Blagnac-Université Toulouse - Jean Jaurès (UT2J), Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Paris (ENS Paris), and Université Paris sciences et lettres (PSL)-Université Paris sciences et lettres (PSL)-Inria Sophia Antipolis - Méditerranée (CRISAM)
Subjects: MESH: Subtraction Technique, [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, Computer science, Information Storage and Retrieval, computer.software_genre, Pattern Recognition, Automated, MESH: Magnetic Resonance Imaging, 030218 nuclear medicine & medical imaging, 0302 clinical medicine, Voxel, MESH: Pattern Recognition, Automated, Evoked Potentials, MESH: Brain Mapping, Reliability (statistics), Brain Mapping, Radiological and Ultrasound Technology, medicine.diagnostic_test, Brain, Random effects model, Magnetic Resonance Imaging, Computer Science Applications, MESH: Reproducibility of Results, MESH: Evoked Potentials, Parametric model, MESH: Image Enhancement, Algorithms, Normalization (statistics), MESH: Algorithms, Machine learning, Sensitivity and Specificity, MESH: Brain, 03 medical and health sciences, Artificial Intelligence, Image Interpretation, Computer-Assisted, medicine, Humans, MESH: Artificial Intelligence, Electrical and Electronic Engineering, MESH: Humans, business.industry, Reproducibility of Results, MESH: Information Storage and Retrieval, Pattern recognition, Magnetic resonance imaging, Image Enhancement, MESH: Sensitivity and Specificity, Subtraction Technique, Spatial normalization, Artificial intelligence, Functional magnetic resonance imaging, business, MESH: Image Interpretation, Computer-Assisted, computer, 030217 neurology & neurosurgery, Software
Abstract: International audience; Group studies of functional magnetic resonance imaging datasets are usually based on the computation of the mean signal across subjects at each voxel (random effects analyses), assuming that all subjects have been set in the same anatomical space (normalization). Although this approach allows for a correct specificity (rate of false detections), it is not very efficient for three reasons: i) its underlying hypotheses, perfect coregistration of the individual datasets and normality of the measured signal at the group level are frequently violated; ii) the group size is small in general, so that asymptotic approximations on the parameters distributions do not hold; iii) the large size of the images requires some conservative strategies to control the false detection rate, at the risk of increasing the number of false negatives. Given that it is still very challenging to build generative or parametric models of intersubject variability, we rely on a rule based, bottom-up approach: we present a set of procedures that detect structures of interest from each subject's data, then search for correspondences across subjects and outline the most reproducible activation regions in the group studied. This framework enables a strict control on the number of false detections. It is shown here that this analysis demonstrates increased validity and improves both the sensitivity and reliability of group analyses compared with standard methods. Moreover, it directly provides information on the spatial position correspondence or variability of the activated regions across subjects, which is difficult to obtain in standard voxel-based analyses.
Published: 2007

36. Integrating Multimodal Priors in Predictive Models for the Functional Characterization of Alzheimer's Disease

Author: Gaël Varoquaux, Claude Comtat, Elvis Dohmatob, Michael Eickenberg, Alexandre Abraham, Bertrand Thirion, Mehdi Rahim, 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), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Service Hospitalier Frédéric Joliot (SHFJ), 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, Population, Disease, Machine learning, computer.software_genre, Bioinformatics, 050105 experimental psychology, Fluorodeoxyglucose positron emission tomography, 03 medical and health sciences, 0302 clinical medicine, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Prior probability, medicine, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 0501 psychology and cognitive sciences, education, FDG-PET, education.field_of_study, Modality (human–computer interaction), medicine.diagnostic_test, Resting state fMRI, business.industry, 05 social sciences, Alzheimer's disease, Classification, prior, connectivity, Artificial intelligence, Functional magnetic resonance imaging, business, computer, metabolism, 030217 neurology & neurosurgery, resting-state fMRI
Abstract: International audience; Functional brain imaging provides key information to characterize neurodegenerative diseases, such as Alzheimer's disease (AD). Specifically, the metabolic activity measured through fluorodeoxyglu-cose positron emission tomography (FDG-PET) and the connectivity extracted from resting-state functional magnetic resonance imaging (fMRI), are promising biomarkers that can be used for early assessment and prognosis of the disease and to understand its mechanisms. FDG-PET is the best suited functional marker so far, as it gives a reliable quantitative measure, but is invasive. On the other hand, non-invasive fMRI acquisitions do not provide a straightforward quantification of brain functional activity. To analyze populations solely based on resting-state fMRI, we propose an approach that leverages a metabolic prior learned from FDG-PET. More formally, our classification framework embeds population priors learned from another modality at the voxel-level, which can be seen as a regularization term in the analysis. Experimental results show that our PET-informed approach increases classification accuracy compared to pure fMRI approaches and highlights regions known to be impacted by the disease.
Published: 2015

37. Improving sparse recovery on structured images with bagged clustering

Author: Andrés Hoyos-Idrobo, Gaël Varoquaux, Yannick Schwartz, Bertrand Thirion, 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), Hoyos Idrobo, Andres, 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: Computer science, Correlation clustering, Stability (learning theory), brain imaging, computer.software_genre, 01 natural sciences, 010104 statistics & probability, 03 medical and health sciences, 0302 clinical medicine, Discriminative model, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], 0101 mathematics, Cluster analysis, K-SVD, business.industry, [SCCO.NEUR]Cognitive science/Neuroscience, [SCCO.NEUR] Cognitive science/Neuroscience, Estimator, Pattern recognition, [STAT.ML] Statistics [stat]/Machine Learning [stat.ML], machine learning, Feature (computer vision), Artificial intelligence, Data mining, High-dimensional estimators, business, computer, Stability, 030217 neurology & neurosurgery, Data compression, clustering
Abstract: International audience; —The identification of image regions associated with external variables through discriminative approaches yields ill-posed estimation problems. This estimation challenge can be tackled by imposing sparse solutions. However, the sensitivity of sparse estimators to correlated variables leads to non-reproducible results, and only a subset of the important variables are selected. In this paper, we explore an approach based on bagging clustering-based data compression in order to alleviate the instability of sparse models. Specifically, we design a new framework in which the estimator is built by averaging multiple models estimated after feature clustering, to improve the conditioning of the model. We show that this combination of model averaging with spatially consistent compression can have the virtuous effect of increasing the stability of the weight maps, allowing a better interpretation of the results. Finally, we demonstrate the benefit of our approach on several predictive modeling problems.
Published: 2015

38. Transport on Riemannian Manifold for Connectivity-based Brain Decoding

Author: Gaël Varoquaux, Bernard Ng, Michael D. Greicius, Jean-Baptiste Poline, Bertrand Thirion, 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, Functional Imaging in Neuropsychiatric Disorders (Find Lab), Stanford University, Service NEUROSPIN (NEUROSPIN), Henry H. Wheeler Jr. Brain Imaging Center [Berkeley], Inria@SiliconValley program, Inria Parietal -- Stanford University / Greicius lab, 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, Positive-definite matrix, Riemannian geometry, Machine learning, computer.software_genre, brain decoding, 03 medical and health sciences, Matrix (mathematics), symbols.namesake, 0302 clinical medicine, Discriminative model, Image Processing, Computer-Assisted, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, Humans, Electrical and Electronic Engineering, transport on manifolds, Radiological and Ultrasound Technology, Parallel transport, business.industry, fMRI, Brain, Pattern recognition, Riemannian manifold, Covariance, Magnetic Resonance Imaging, Uncorrelated, Manifold, Computer Science Applications, Statistical classification, 030104 developmental biology, connectivity, symbols, Artificial intelligence, Nerve Net, business, computer, Classifier (UML), Algorithms, 030217 neurology & neurosurgery, Software, Decoding methods
Abstract: International audience; There is a recent interest in using functional magnetic resonance imaging (fMRI) for decoding more naturalistic, cognitive states, in which subjects perform various tasks in a continuous, self-directed manner. In this setting, the set of brain volumes over the entire task duration is usually taken as a single sample with connectivity estimates, such as Pearson's correlation, employed as features. Since covariance matrices live on the positive semidefinite cone, their elements are inherently interrelated. The assumption of uncorrelated features implicit in most classifier learning algorithms is thus violated. Coupled with the usual small sample sizes, the generalizability of the learned classifiers is limited, and the identification of significant brain connections from the classifier weights is nontrivial. In this paper, we present a Riemannian approach for connectivity-based brain decoding. The core idea is to project the covariance estimates onto a common tangent space to reduce the statistical dependencies between their elements. For this, we propose a matrix whitening transport, and compare it against parallel transport implemented via the Schild's ladder algorithm. To validate our classification approach, we apply it to fMRI data acquired from twenty four subjects during four continuous, self-driven tasks. We show that our approach provides significantly higher classification accuracy than directly using Pearson's correlation and its regularized variants as features. To facilitate result interpretation, we further propose a non-parametric scheme that combines bootstrapping and permutation testing for identifying significantly discriminative brain connections from the classifier weights. Using this scheme, a number of neuro-anatomically meaningful connections are detected, whereas no significant connections are found with pure permutation testing.
Published: 2015

39. Grouping Total Variation and Sparsity: Statistical Learning with Segmenting Penalties

Author: Bertrand Thirion, Elvis Dohmatob, Michael Eickenberg, and Gaël Varoquaux
Subjects: business.industry, Statistical learning, Regular polygon, Inverse problem, Machine learning, computer.software_genre, Regularization (mathematics), Contiguity (probability theory), Market segmentation, Voxel, Segmentation, Artificial intelligence, business, computer, Mathematics
Abstract: Prediction from medical images is a valuable aid to diagnosis. For instance, anatomical MR images can reveal certain disease conditions, while their functional counterparts can predict neuropsychiatric phenotypes. However, a physician will not rely on predictions by black-box models: understanding the anatomical or functional features that underpin decision is critical. Generally, the weight vectors of classifiers are not easily amenable to such an examination: Often there is no apparent structure. Indeed, this is not only a prediction task, but also an inverse problem that calls for adequate regularization. We address this challenge by introducing a convex region-selecting penalty. Our penalty combines total-variation regularization, enforcing spatial contiguity, and l1 regularization, enforcing sparsity, into one group: Voxels are either active with non-zero spatial derivative or zero with inactive spatial derivative. This leads to segmenting contiguous spatial regions inside which the signal can vary freely against a background of zeros. Such segmentation of medical images in a target-informed manner is an important analysis tool. On several prediction problems from brain MRI, the penalty shows good segmentation. Given the size of medical images, computational efficiency is key. Keeping this in mind, we contribute an efficient optimization scheme that brings significant computational gains.
Published: 2015

40. Dealing with the shortcomings of spatial normalization: Multi-subject parcellation of fMRI datasets

Author: Philippe Pinel, Bertrand Thirion, Alexis Roche, Guillaume Flandin, Jean-Baptiste Poline, and Philippe Ciuciu
Subjects: Computer science, Normalization (image processing), Inference, computer.software_genre, Voxel, Image Processing, Computer-Assisted, medicine, Cluster Analysis, Humans, Radiology, Nuclear Medicine and imaging, Research Articles, Brain Mapping, Radiological and Ultrasound Technology, medicine.diagnostic_test, business.industry, Brain, Pattern recognition, Random effects model, Magnetic Resonance Imaging, Spectral clustering, Neurology, Spatial normalization, Neurology (clinical), Artificial intelligence, Anatomy, Functional magnetic resonance imaging, business, computer, Algorithms, Smoothing
Abstract: The analysis of functional magnetic resonance imaging (fMRI) data recorded on several subjects resorts to the so‐called spatial normalization in a common reference space. This normalization is usually carried out on a voxel‐by‐voxel basis, assuming that after coregistration of the functional images with an anatomical template image in the Talairach reference system, a correct voxel‐based inference can be carried out across subjects. Shortcomings of such approaches are often dealt with by spatially smoothing the data to increase the overlap between subject‐specific activated regions. This procedure, however, cannot adapt to each anatomo‐functional subject configuration. We introduce a novel technique for intra‐subject parcellation based on spectral clustering that delineates homogeneous and connected regions. We also propose a hierarchical method to derive group parcels that are spatially coherent across subjects and functionally homogeneous. We show that we can obtain groups (or cliques) of parcels that well summarize inter‐subject activations. We also show that the spatial relaxation embedded in our procedure improves the sensitivity of random‐effect analysis. Hum Brain Mapp, 2005. © 2005 Wiley‐Liss, Inc.
Published: 2006

41. Feature characterization in fMRI data: the Information Bottleneck approach

Author: Olivier Faugeras and Bertrand Thirion
Subjects: Brain Mapping, Radiological and Ultrasound Technology, business.industry, Feature vector, Quantization (signal processing), Vector quantization, Health Informatics, Information bottleneck method, Pattern recognition, Information theory, Magnetic Resonance Imaging, Computer Graphics and Computer-Aided Design, Determining the number of clusters in a data set, Rate–distortion theory, Image Processing, Computer-Assisted, Cluster Analysis, Computer Simulation, Radiology, Nuclear Medicine and imaging, Computer Vision and Pattern Recognition, Artificial intelligence, business, Cluster analysis, Algorithms, Mathematics
Abstract: Clustering is a well-known technique for the analysis of Functional Magnetic Resonance Imaging (fMRI) data, whose main advantage is certainly flexibility: given a metric on the dataset, it "summarizes" the main characteristics of the data. But intrinsic to this approach are also the problem of defining correctly the quantization accuracy, and the number of clusters necessary to describe the data. The Information Bottleneck (IB) approach to vector quantization, proposed by Bialek and Tishby, addresses these difficulties: (1) it deals with an explicit trade-off between quantization and data fidelity; (2) it does so during the clustering procedure and not post hoc; (3) it takes into account the full statistical distribution of the features within the feature space and not only their most likely value; last, it is principled through an information theoretic formulation, which is relevant in many situations. In this paper, we present how to benefit from this method to analyze fMRI data. Our application is the clustering of voxels according to the magnitude of their responses to several experimental conditions. The IB quantization provides a consistent representation of the data, allowing for an easy interpretation and comparison of datasets.
Published: 2004

42. Dynamical components analysis of fMRI data through kernel PCA

Author: Olivier Faugeras and Bertrand Thirion
Subjects: Multivariate statistics, Computer science, Cognitive Neuroscience, computer.software_genre, Kernel principal component analysis, Kernel (linear algebra), Prior probability, Image Processing, Computer-Assisted, Computer Simulation, Time series, Representation (mathematics), Decorrelation, General linear model, Analysis of Variance, Electronic Data Processing, Principal Component Analysis, business.industry, Reproducibility of Results, Pattern recognition, Magnetic Resonance Imaging, Neurology, Kernel (statistics), Principal component analysis, Artificial intelligence, Analysis of variance, Data mining, business, computer, Algorithms
Abstract: In parallel with standard model-based methods for the analysis of fMRI data, exploratory methods--such as PCA, ICA, and clustering--have been developed to give an account of the dataset with minimal priors: no assumption is made on the data content itself, but the data structure is assumed to show some properties (decorrelation, independence) that allow for the detection of structures of interest. In this paper, we present an alternative that tries to take into account some relevant knowledge for the analysis of the dataset, e.g., the experimental paradigm, while keeping the flexibility of exploratory methods: we use a prior temporal modeling of the data that characterizes each voxel time course. Two implementations are proposed: one based on the General Linear Model, the other one on more flexible short-term predictors, whose complexity is controlled by a Minimum Description Length approach. However, our main concern here is the construction of a multivariate model; the latter is performed with the help of a kernel PCA method that builds a redundant representation of the data through the nonlinearity of the kernel. This allows for a refinement in the description of the (temporal) patterns of interest. In particular, this helps in the characterization of subtle variations in the response to different experimental conditions. We illustrate the usefulness of nonlinearity through the analysis of a synthetic dataset and show on a real dataset how it helps to interpret the experimental results.
Published: 2003

43. Transport on Riemannian Manifold for Functional Connectivity-based Classification

Author: Jean-Baptiste Poline, Martin Dressler, Michael D. Greicius, Bernard Ng, Gaël Varoquaux, 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), Functional Imaging in Neuropsychiatric Disorders (Find Lab), Stanford University, Donders Institute for Brain, Cognition and Behaviour, Radboud University [Nijmegen], Laboratoire de Neuroimagerie Assistée par Ordinateur (LNAO), 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), Henry H. Wheeler Jr. Brain Imaging Center [Berkeley], INRIA@Silicon Valley Program, Polina Golland, 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, and Radboud university [Nijmegen]
Subjects: Connectivity, Riemannian manifold, business.industry, fMRI, Pattern recognition, 02 engineering and technology, Covariance, Classification, Correlation, 03 medical and health sciences, Matrix (mathematics), 0302 clinical medicine, Discriminative model, Cone (topology), 0202 electrical engineering, electronic engineering, information engineering, Feature (machine learning), [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, 020201 artificial intelligence & image processing, Artificial intelligence, business, Classifier (UML), 030217 neurology & neurosurgery, Mathematics
Abstract: International audience; We present a Riemannian approach for classifying fMRI connectivity patterns before and after intervention in longitudinal studies. A fundamental difficulty with using connectivity as features is that covariance matrices live on the positive semi-definite cone, which renders their elements inter-related. The implicit independent feature assumption in most classifier learning algorithms is thus violated. In this paper, we propose a matrix whitening transport for projecting the covariance estimates onto a common tangent space to reduce the statistical dependencies between their elements. We show on real data that our approach provides significantly higher classification accuracy than directly using Pearson's correlation. We further propose a non-parametric scheme for identifying significantly discriminative connections from classifier weights. Using this scheme, a number of neuroanatomically meaningful connections are found, whereas no significant connections are detected with pure permutation testing.
Published: 2014

44. Principal Component Regression predicts functional responses across individuals

Author: Gaël Varoquaux, Bertrand Thirion, Philippe Pinel, Cyril Poupon, Olivier Grisel, 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 Neuroimagerie Assistée par Ordinateur (LNAO), Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Nuxeo, nuxeo, Laboratoire d'Imagerie et de Spectroscopie (LRMN), Neuroimagerie cognitive (LCogn), Université Paris-Sud - Paris 11 (UP11)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Institut National de la Santé et de la Recherche Médicale (INSERM), European Project: 284941,EC:FP7:ICT,FP7-ICT-2011-FET-F,HBP(2011), 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), Thirion, Bertrand, and Human Brain Project - HBP - - EC:FP7:ICT2011-05-01 - 2012-04-30 - 284941 - VALID
Subjects: [STAT.AP]Statistics [stat]/Applications [stat.AP], business.industry, fMRI, Estimator, Inference, [SDV.NEU.SC]Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, Pattern recognition, Regression analysis, Variance (accounting), principal components regression, Random effects model, [STAT.AP] Statistics [stat]/Applications [stat.AP], Statistics, Principal component analysis, Principal component regression, random effects, Artificial intelligence, business, [SDV.NEU.SC] Life Sciences [q-bio]/Neurons and Cognition [q-bio.NC]/Cognitive Sciences, Subspace topology, Mathematics
Abstract: International audience; Inter-subject variability is a major hurdle for neuroimaging group-level inference, as it creates complex image patterns that are not captured by standard analysis models and jeopardizes the sensitivity of statistical procedures. A solution to this problem is to model random subjects effects by using the redundant information conveyed by multiple imaging contrasts. In this paper, we introduce a novel analysis framework, where we estimate the amount of variance that is fit by a random effects subspace learned on other images; we show that a principal component regression estimator outperforms other regression models and that it fits a significant proportion (10% to 25%) of the between-subject variability. This proves for the first time that the accumulation of contrasts in each individual can provide the basis for more sensitive neuroimaging group analyzes.
Published: 2014

45. Benchmarking solvers for TV-ℓ1 least-squares and logistic regression in brain imaging

Author: Alexandre Gramfort, Gaël Varoquaux, Bertrand Thirion, and Elvis Dohmatob
Subjects: Optimization problem, medicine.diagnostic_test, business.industry, Benchmarking, Total variation denoising, Machine learning, computer.software_genre, Regularization (mathematics), Regression, Neuroimaging, medicine, Artificial intelligence, Functional magnetic resonance imaging, business, computer, Decoding methods, Mathematics
Abstract: Learning predictive models from brain imaging data, as in decoding cognitive states from fMRI (functional Magnetic Resonance Imaging), is typically an ill-posed problem as it entails estimating many more parameters than available sample points. This estimation problem thus requires regularization. Total variation regularization, combined with sparse models, has been shown to yield good predictive performance, as well as stable and interpretable maps. However, the corresponding optimization problem is very challenging: it is non-smooth, non-separable and heavily ill-conditioned. For the penalty to fully exercise its structuring effect on the maps, this optimization problem must be solved to a good tolerance resulting in a computational challenge. Here we explore a wide variety of solvers and exhibit their convergence properties on fMRI data. We introduce a variant of smooth solvers and show that it is a promising approach in these settings. Our findings show that care must be taken in solving TV-l1 estimation in brain imaging and highlight the successful strategies.
Published: 2014

46. Robust regression for large-scale neuroimaging studies

Author: Gareth J. Barker, Herta Flor, Herve Lemaitre, Tomáš Paus, Gunter Schumann, Karl Mann, Patricia J. Conrod, Benoit Da Mota, Frauke Nees, Arun L.W. Bokde, Brigitte Butzek, Virgile Fritsch, Eva Loth, Daniel J. Schad, Gaël Varoquaux, Vincent Frouin, Jean-Baptiste Poline, Bertrand Thirion, Tobias Banaschewski, Hugh Garavan, and Rüdiger Brühl
Subjects: Imaging genetics, Cognitive Neuroscience, media_common.quotation_subject, Inference, Neuroimaging, computer.software_genre, Sensitivity and Specificity, Robust regression, Normality test, Statistical inference, False positive paradox, Humans, Computer Simulation, Normality, media_common, business.industry, Functional Neuroimaging, Pattern recognition, Neurology, Data Interpretation, Statistical, Sample Size, Outlier, Regression Analysis, Artificial intelligence, Data mining, Psychology, business, computer
Abstract: Multi-subject datasets used in neuroimaging group studies have a complex structure, as they exhibit non-stationary statistical properties across regions and display various artifacts. While studies with small sample sizes can rarely be shown to deviate from standard hypotheses (such as the normality of the residuals) due to the poor sensitivity of normality tests with low degrees of freedom, large-scale studies (e.g. > 100 subjects) exhibit more obvious deviations from these hypotheses and call for more refined models for statistical inference. Here, we demonstrate the benefits of robust regression as a tool for analyzing large neuroimaging cohorts. First, we use an analytic test based on robust parameter estimates; based on simulations, this procedure is shown to provide an accurate statistical control without resorting to permutations. Second, we show that robust regression yields more detections than standard algorithms using as an example an imaging genetics study with 392 subjects. Third, we show that robust regression can avoid false positives in a large-scale analysis of brain–behavior relationships with over 1500 subjects. Finally we embed robust regression in the Randomized Parcellation Based Inference (RPBI) method and demonstrate that this combination further improves the sensitivity of tests carried out across the whole brain. Altogether, our results show that robust procedures provide important advantages in large-scale neuroimaging group studies.
Published: 2014

47. Machine learning patterns for neuroimaging-genetic studies in the cloud

Author: Benoit Da Mota, Bertrand Thirion, Herve Lemaitre, Alexandru Costan, Patricia J. Conrod, Marcella Rietschel, Vincent Frouin, Tomáš Paus, Goetz Brasche, Gaël Varoquaux, Gabriel Antoniu, Jean-Baptiste Poline, Radu Tudoran, 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), Scalable Storage for Clouds and Beyond (KerData), Inria Rennes – Bretagne Atlantique, Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-SYSTÈMES LARGE ÉCHELLE (IRISA-D1), 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)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-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)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Université de Bretagne Sud (UBS)-École normale supérieure - Rennes (ENS Rennes)-Télécom Bretagne-CentraleSupélec-Centre National de la Recherche Scientifique (CNRS), Cloud Team, European Microsoft Innovation Center (EMIC), Microsoft Corporation [Redmond, Wash.]-Microsoft Corporation [Redmond, Wash.], Institute of Psychiatry, Psychology & Neuroscience, King's College London, King‘s College London, Adolescent psychopathology and Medicine, Hôpital Cochin [AP-HP], Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP)-Assistance publique - Hôpitaux de Paris (AP-HP) (AP-HP), McConnell Brain Imaging Centre (MNI), Montreal Neurological Institute and Hospital, McGill University = Université McGill [Montréal, Canada]-McGill University = Université McGill [Montréal, Canada], School of Psychology [Nottingham], University of Nottingham, UK (UON), Department of Genetic Epidemiology in Psychiatry [Mannhein], Universität Heidelberg [Heidelberg] = Heidelberg University-Central Institute of Mental Health Mannheim, Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Henry H. Wheeler Jr. Brain Imaging Center [Berkeley], Projet Digiteo 2012-051D Icogen, ANR-10-BLAN-0128,GENIM,Analyse conjointe de données de grandes dimensions en neuroimagerie et génétique(2010), European Project: 39513,IMAGEN, 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, CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-Institut National de Recherche en Informatique et en Automatique (Inria)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-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)-CentraleSupélec-Télécom Bretagne-Université de Rennes 1 (UR1), Institut National des Sciences Appliquées (INSA)-Université de Rennes (UNIV-RENNES)-Institut National des Sciences Appliquées (INSA)-Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA), Université de Rennes (UNIV-RENNES)-Université de Rennes (UNIV-RENNES)-École normale supérieure - Rennes (ENS Rennes)-Université de Bretagne Sud (UBS)-Centre National de la Recherche Scientifique (CNRS)-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), and Universität Heidelberg [Heidelberg]-Central Institute of Mental Health Mannheim
Subjects: Computer science, Reliability (computer networking), Biomedical Engineering, Neuroscience (miscellaneous), Cloud computing, heritability, Machine learning, computer.software_genre, Neuroimaging, Methods Article, neuroimaging-genetic, business.industry, cloud computing, fMRI, SIGNAL (programming language), Neuroinformatics, [SDV.BIBS]Life Sciences [q-bio]/Quantitative Methods [q-bio.QM], Computer Science Applications, machine learning, Virtual machine, Software deployment, Scalability, Artificial intelligence, Data mining, [INFO.INFO-BI]Computer Science [cs]/Bioinformatics [q-bio.QM], business, computer, Neuroscience
Abstract: International audience; Brain imaging is a natural intermediate phenotype to understand the link between genetic information and behavior or brain pathologies risk factors. Massive efforts have been made in the last few years to acquire high-dimensional neuroimaging and genetic data on large cohorts of subjects. The statistical analysis of such data is carried out with increasingly sophisticated techniques and represents a great computational challenge. Fortunately, increasing computational power in distributed architectures can be harnessed, if new neuroinformatics infrastructures are designed and training to use these new tools is provided. Combining a MapReduce framework (TomusBLOB) with machine learning algorithms (Scikit-learn library), we design a scalable analysis tool that can deal with non-parametric statistics on high-dimensional data. End-users describe the statistical procedure to perform and can then test the model on their own computers before running the very same code in the cloud at a larger scale. We illustrate the potential of our approach on real data with an experiment showing how the functional signal in subcortical brain regions can be significantly fit with genome-wide genotypes. This experiment demonstrates the scalability and the reliability of our framework in the cloud with a two weeks deployment on hundreds of virtual machines.
Published: 2014

48. Automatic pathology classification using a single feature machine learning support - vector machines

Author: Natasha Lepore, Bertrand Thirion, Yalin Wang, Fernando Yepes-Calderon, Fabian Pedregosa, 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), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Arizona State University [Tempe] (ASU), University of Southern California (USC), Capneonates Collaboration, 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: [SDV.IB.IMA]Life Sciences [q-bio]/Bioengineering/Imaging, business.industry, Computer science, Machine learning, computer.software_genre, Medical diagnostics, 3. Good health, Support vector machine, ComputingMethodologies_PATTERNRECOGNITION, Magnetic resonance imaging, [STAT.ML]Statistics [stat]/Machine Learning [stat.ML], Neuroimaging, Pathology Diseases and disorders, Artificial intelligence, Brain Databases Diagnostics, business, Cognitive impairment, computer, Neuroimaging Algorithms
Abstract: Magnetic Resonance Imaging (MRI) has been gaining popularity in the clinic in recent years as a safe in-vivoimaging technique. As a result, large troves of data are being gathered and stored daily that may be used asclinical training sets in hospitals. While numerous machine learning (ML) algorithms have been implemented forAlzheimer's disease classi cation, their outputs are usually di cult to interpret in the clinical setting. Here, wepropose a simple method of rapid diagnostic classi cation for the clinic using Support Vector Machines (SVM) 1 and easy to obtain geometrical measurements that, together with a cortical and sub-cortical brain parcellation,create a robust framework capable of automatic diagnosis with high accuracy. On a signi cantly large imagingdataset consisting of over 800 subjects taken from the Alzheimer's Disease Neuroimaging Initiative (ADNI)database, classi cation-success indexes of up to 99.2% are reached with a single measurement.Keywords: Alzheimer's disease, machine learning, mild cognitive impairment, support vector machines, fastclinical diagnosis.
Published: 2014

49. Machine Learning for Neuroimaging with Scikit-Learn

Author: Alexandre Abraham, Fabian Pedregosa, Bertrand Thirion, Michael Eickenberg, Alexandre Gramfort, Philippe Gervais, Gaël Varoquaux, Jean Kossaifi, Andreas Mueller, 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)), Institute of Computer Science VI, Department of Computing [London], Biomedical Image Analysis Group [London] (BioMedIA), Imperial College London-Imperial College London, Laboratoire Traitement et Communication de l'Information (LTCI), Télécom ParisTech-Institut Mines-Télécom [Paris] (IMT)-Centre National de la Recherche Scientifique (CNRS), NIDA R21 DA034954, SUBSample project from the DIGITEO Institute, France, ANR-11-BINF-0003,MAPPING,Vers une cartographie haute résolution des interactions protéiques à l'échelle du génome.(2011), 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, Multivariate analysis, Computer science, Computer Vision and Pattern Recognition (cs.CV), education, Biomedical Engineering, Neuroscience (miscellaneous), Computer Science - Computer Vision and Pattern Recognition, Machine Learning (stat.ML), Machine learning, computer.software_genre, Machine Learning (cs.LG), lcsh:RC321-571, 03 medical and health sciences, 0302 clinical medicine, Neuroimaging, [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG], Functional neuroimaging, Statistics - Machine Learning, Methods Article, [INFO.INFO-IM]Computer Science [cs]/Medical Imaging, lcsh:Neurosciences. Biological psychiatry. Neuropsychiatry, 030304 developmental biology, computer.programming_language, 0303 health sciences, neuroimaging, Resting state fMRI, business.industry, Supervised learning, Python (programming language), Computer Science Applications, Computer Science - Learning, statistical learning, machine learning, Unsupervised learning, scikit-learn, Artificial intelligence, business, computer, 030217 neurology & neurosurgery, Decoding methods, Neuroscience, Python
Abstract: Statistical machine learning methods are increasingly used for neuroimaging data analysis. Their main virtue is their ability to model high-dimensional datasets, e.g. multivariate analysis of activation images or resting-state time series. Supervised learning is typically used in decoding or encoding settings to relate brain images to behavioral or clinical observations, while unsupervised learning can uncover hidden structures in sets of images (e.g. resting state functional MRI) or find sub-populations in large cohorts. By considering different functional neuroimaging applications, we illustrate how scikit-learn, a Python machine learning library, can be used to perform some key analysis steps. Scikit-learn contains a very large set of statistical learning algorithms, both supervised and unsupervised, and its application to neuroimaging data provides a versatile tool to study the brain., Comment: Frontiers in neuroscience, Frontiers Research Foundation, 2013, pp.15
Published: 2013

50. Bayesian Estimation of Probabilistic Atlas for Anatomically-Informed Functional MRI Group Analyses

Author: Hao Xu, Stéphanie Allassonnière, Bertrand Thirion, Centre de Mathématiques Appliquées - Ecole Polytechnique (CMAP), École polytechnique (X)-Centre National de la Recherche Scientifique (CNRS), 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), Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA), MMoVNI (Digiteo DIM), Yoshinobu Sato and Christian Barillot and Nassir Navab, 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, and Thirion, Bertrand
Subjects: Computer science, Models, Neurological, multi-modal, Multimodal Imaging, Sensitivity and Specificity, Pattern Recognition, Automated, 030218 nuclear medicine & medical imaging, 03 medical and health sciences, joint registration, 0302 clinical medicine, Artificial Intelligence, Atlas (anatomy), T1 MRI and fMRI, Image Interpretation, Computer-Assisted, medicine, Humans, Computer Simulation, Segmentation, Computer vision, Probabilistic atlas, atlas-based segmentation, Bayes estimator, [STAT.ME] Statistics [stat]/Methodology [stat.ME], Models, Statistical, medicine.diagnostic_test, Atlas (topology), business.industry, segmentation, Brain, Reproducibility of Results, Bayes Theorem, Pattern recognition, Image Enhancement, Magnetic Resonance Imaging, medicine.anatomical_structure, Data Interpretation, Statistical, geometric variability, Artificial intelligence, Functional magnetic resonance imaging, business, [STAT.ME]Statistics [stat]/Methodology [stat.ME], Algorithms, 030217 neurology & neurosurgery
Abstract: International audience; Traditional analyses of Functional Magnetic Resonance Imaging (fMRI) use little anatomical information. The registration of the images to a template is based on the individual anatomy and ignores functional information; subsequently detected activations are not confined to gray matter (GM). In this paper, we propose a statistical model to estimate a probabilistic atlas from functional and T1 MRIs that summarizes both anatomical and functional information and the geometric variability of the population. Registration and Segmentation are performed jointly along the atlas estimation and the functional activity is constrained to the GM, increasing the accuracy of the atlas.
Published: 2013

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

123 results on '"Bertrand Thirion"'

Search Results

Catalog

Select search scope, currently: Articles

Catalog

books, media & more in Jio Institute collections

Articles

journal articles & other e-resources