Search

Exposure to certain monochromatic wavelengths can affect non-visual brain regions. Growing research indicates that exposure to light can have a positive impact on health-related problems such as spring asthenia, circadian rhythm disruption, and even bipolar disorders and Alzheimer’s. However, the extent and location of changes in brain areas caused by exposure to monochromatic light remain largely unknown. This pilot study (N = 7) using resting-state functional magnetic resonance shows light-dependent functional connectivity patterns on brain networks. We demonstrated that 1 min of blue, green, or red light exposure modifies the functional connectivity (FC) of a broad range of visual and non-visual brain regions. Largely, we observed: (i) a global decrease in FC in all the networks but the salience network after blue light exposure, (ii) a global increase in FC after green light exposure, particularly noticeable in the left hemisphere, and (iii) a decrease in FC on attentional networks coupled with a FC increase in the default mode network after red light exposure. Each one of the FC patterns appears to be best arranged to perform better on tasks associated with specific cognitive domains. Results can be relevant for future research on the impact of light stimulation on brain function and in a variety of health disciplines.

Biological networks have gained considerable attention within the Deep Learning community because of the promising framework of Graph Neural Networks (GNN), neural models that operate in complex networks. In the context of neuroimaging, GNNs have successfully been employed for functional MRI processing but their application to ROI-level structural MRI (sMRI) remains mostly unexplored. In this work we analyze the implementation of these geometric models with sMRI by building graphs of ROIs (ROI graphs) using tools from Graph Signal Processing literature and evaluate their performance in a downstream supervised task, age prediction. We first make a qualitative and quantitative comparison of the resulting networks obtained with common graph topology learning strategies. In a second stage, we train GNN-based models for brain age prediction. Since the order of every ROI graph is exactly the same and each vertex is an entity by itself (a ROI), we evaluate whether including ROI information during message-passing or global pooling operations is beneficial and compare the performance of GNNs against a Fully-Connected Neural Network baseline. The results show that ROI-level information is needed during the global pooling operation in order to achieve competitive results. However, no relevant improvement has been detected when it is incorporated during the message passing. These models achieve a MAE of 4.27 in hold-out test data, which is a performance very similar to the baseline, suggesting that the inductive bias included with the obtained graph connectivity is relevant and useful to reduce the dimensionality of the problem. This work has been supported by the Spanish Research Agency (AEI) under project PID2020-116907RB-I00 of the call MCIN/ AEI /10.13039/501100011033 and the FI-AGAUR grant funded by Direcció General de Recerca (DGR) of Departament de Recerca i Universitats (REU) of the Generalitat de Catalunya.

Background: Structural MRI measurements can contribute to the prediction of amyloid pathology in cognitively unimpaired (CU) individuals. In this work, we aimed at studying the predictive capacity, robustness, and generalizability of ML techniques to predict amyloid-ß pathology in CU individuals, as well as identifying key brain regions contributing to this prediction. Method: We included 653 and 250 CU individuals from the EPAD and ADNI studies, respectively, with available T1w MRI and CSF Aß42 measurements. Subjects were categorized as amyloid-ß positive (Aß+) or negative (Aß-) according to established cut-offs (CSF Aß42

Background: CSF Aß42 is thought to show AD-related alterations earlier than amyloid-ß PET. Therefore, cognitively unimpaired (CU) individuals with abnormal CSF Aß42 and normal amyloid-ß PET are believed to be in the earliest stages of the AD continuum. In this work, we sought to detect structural cerebral alterations in CU individuals with discordant status in these amyloid-ß biomarkers using Machine Learning techniques. Method: We included 498 CU individuals from the ALFA+ and ADNI studies with available MRI, amyloid-ß PET and CSF Aß42 measurements, the latter measured with the exploratory Roche NeuroToolKit assays, a panel of automated robust prototype immunoassays. In addition, we calculated Centiloid (CL) values for the PET measurements. Individuals were categorized as CSF-/PET-, CSF+/PET- and CSF+/PET+ according to established cut-offs (CSF Aß42

Background Manual brain extraction from magnetic resonance (MR) images is time-consuming and prone to intra- and inter-rater variability. Several automated approaches have been developed to alleviate these constraints, including deep learning pipelines. However, these methods tend to reduce their performance in unseen magnetic resonance imaging (MRI) scanner vendors and different imaging protocols. Purpose To present and evaluate for clinical use PARIETAL, a pre-trained deep learning brain extraction method. We compare its reproducibility in a scan/rescan analysis and its robustness among scanners of different manufacturers. Study Type Retrospective. Population Twenty-one subjects (12 women) with age range 22–48 years acquired using three different MRI scanner machines including scan/rescan in each of them. Field Strength/Sequence T1-weighted images acquired in a 3-T Siemens with magnetization prepared rapid gradient-echo sequence and two 1.5 T scanners, Philips and GE, with spin-echo and spoiled gradient-recalled (SPGR) sequences, respectively. Assessment Analysis of the intracranial cavity volumes obtained for each subject on the three different scanners and the scan/rescan acquisitions. Statistical Tests Parametric permutation tests of the differences in volumes to rank and statistically evaluate the performance of PARIETAL compared to state-of-the-art methods. Results The mean absolute intracranial volume differences obtained by PARIETAL in the scan/rescan analysis were 1.88 mL, 3.91 mL, and 4.71 mL for Siemens, GE, and Philips scanners, respectively. PARIETAL was the best-ranked method on Siemens and GE scanners, while decreasing to Rank 2 on the Philips images. Intracranial differences for the same subject between scanners were 5.46 mL, 27.16 mL, and 30.44 mL for GE/Philips, Siemens/Philips, and Siemens/GE comparison, respectively. The permutation tests revealed that PARIETAL was always in Rank 1, obtaining the most similar volumetric results between scanners. Data Conclusion PARIETAL accurately segments the brain and it generalizes to images acquired at different sites without the need of training or fine-tuning it again. PARIETAL is publicly available This work has been partially supported by DPI2017-86696-R from the Ministerio de Ciencia, Innovación y Universidades. Albert Clèrigues also holds a FPI grant PRE2018-083507. The authors gratefully acknowledge the support of the NVIDIA Corporation with their donation of the TITAN X GPU used in this research Open Access funding provided thanks to the CRUE-CSIC agreement with Wiley

In recent years, some convolutional neural networks (CNNs) have been proposed to segment sub-cortical brain structures from magnetic resonance images (MRIs). Although these methods provide accurate segmentation, there is a reproducibility issue regarding segmenting MRI volumes from different image domains – e.g., differences in protocol, scanner, and intensity profile. Thus, the network must be retrained from scratch to perform similarly in different imaging domains, limiting the applicability of such methods in clinical settings. In this paper, we employ the transfer learning strategy to solve the domain shift problem. We reduced the number of training images by leveraging the knowledge obtained by a pretrained network, and improved the training speed by reducing the number of trainable parameters of the CNN. We tested our method on two publicly available datasets – MICCAI 2012 and IBSR – and compared them with a commonly used approach: FIRST. Our method showed similar results to those obtained by a fully trained CNN, and our method used a remarkably smaller number of images from the target domain. Moreover, training the network with only one image from MICCAI 2012 and three images from IBSR datasets was sufficient to significantly outperform FIRST with (p

Accurate brain tissue segmentation in magnetic resonance imaging (MRI) has attracted the attention of medical doctors and researchers since variations in tissue volume and shape permit diagnosing and monitoring neurological diseases. Several proposals have been designed throughout the years comprising conventional machine learning strategies as well as convolutional neural networks (CNNs) approaches. In particular, in this paper, we analyze a sub-group of deep learning methods producing dense predictions. This branch, referred in the literature as fully CNN (FCNN), is of interest as these architectures can process an input volume in less time than CNNs. Our study focuses on understanding the architectural strengths and weaknesses of literature-like approaches. We implement eight FCNN architectures inspired by robust state-of-the-art methods on brain segmentation related tasks and use them within a standard pipeline. We evaluate them using the IBSR18, MICCAI2012, and iSeg2017 datasets as they contain infant and adult data and exhibit different voxel spacing, image quality, number of scans, and available imaging modalities. The discussion is driven in four directions: comparison between 2D and 3D approaches, the relevance of multiple imaging sequences, the effect of patch size, and the impact of patch overlap as a sampling strategy for training and testing models. Besides the aforementioned analysis, we show that the methods under evaluation can yield top performance on the three data collections. A public version is accessible to download from our research website to encourage other researchers to explore the evaluation framework This work was supported in part by the La Fundació la Marató de TV3 and in part by the Retos de Investigació under Grant TIN2014-55710-R, Grant TIN2015-73563-JIN, and Grant DPI2017-86696-R from the Ministerio de Ciencia y Tecnología. The work of J. Bernal and K. Kushibar was supported by the Catalan Government under Grant FI-DGR2017, Grant 2017FI B00476, and Grant 2017FI B00372. The work of M. Cabezas was supported by the Juan de la Cierva–Incorporación Grant from the Spanish Government under Grant IJCI-2016-29240

Background: Plasma biomarkers have demonstrated excellent agreement with established markers of amyloid-ß (Aß) positivity (PET and CSF) to identify patients with symptomatic AD. However, their predictive capacity in cognitively unimpaired (CU) individuals is lower. In this work, we aimed at assessing whether structural MRI features could improve the capacity of machine learning algorithms applied to plasma biomarkers to identify Aß positive CU individuals. Method: We included 344 CU individuals from the ALFA+ study, with available T1w MRI, Aß PET and plasma measurements for p-tau181, p-tau231, and GFAP. We determined the capacity to predict Aß+ according to PET visual read of plasma biomarkers in combination with clinical data (age, sex, education, MMSE, and APOE genotype) and MRI-derived measurements. We trained Random Forest classifiers with clinical, clinical and plasma, clinical and MRI; and clinical, plasma and MRI data. The MRI-selected measurements consisted of Jack’s AD-signature and the two features best predictive of Aß+: left-lat-inf-ventricle and left caudal-anterior-cingulate as determined with Freesurfer 6.0. We conducted ROC and Precision-Recall analyses and calculated savings as the percentage difference of costs between standard trial recruitment and a triaging step with the different classifiers. The threshold for positivity prediction was chosen to maximize savings and the precision-recall ratio. We computed ROC-AUC, PPV, sensitivity and savings as metrics for the comparison. Results: The mean centiloid values of Aß+ subjects (13.66%) and Aß- were 33.73 and -1.82, respectively (Table 1). ROC-AUCs for the classifiers to detect Aß+ was 0.723 for clinical information; 0.861 for clinical and plasma measurements; 0.711 for clinical and MRI; and 0.871 for clinical, plasma and MRI. Savings associated with the best classifier (clinical + plasma + MRI) would translate in savings (95%CI) of 52.8% (49.0, 56.3) in recruitment costs. See Figure 1 for all the metrics’ results. Conclusion: Machine learning algorithms on plasma biomarkers achieved a high accuracy on predicting a positive visual read on amyloid PET scans in cognitively unimpaired individuals. MRI biomarkers marginally improved the predictive capacity. Used as a triaging method, such an algorithm would result in a reduction of over 50% in the cost to identify participants for secondary prevention trials.

Automation of brain tumor segmentation in 3D magnetic resonance images (MRIs) is key to assess the diagnostic and treatment of the disease. In recent years, convolutional neural networks (CNNs) have shown improved results in the task. However, high memory consumption is still a problem in 3D-CNNs. Moreover, most methods do not include uncertainty information, which is especially critical in medical diagnosis. This work studies 3D encoder-decoder architectures trained with patch-based techniques to reduce memory consumption and decrease the effect of unbalanced data. The different trained models are then used to create an ensemble that leverages the properties of each model, thus increasing the performance. We also introduce voxel-wise uncertainty information, both epistemic and aleatoric using test-time dropout (TTD) and data-augmentation (TTA) respectively. In addition, a hybrid approach is proposed that helps increase the accuracy of the segmentation. The model and uncertainty estimation measurements proposed in this work have been used in the BraTS’20 Challenge for task 1 and 3 regarding tumor segmentation and uncertainty estimation. This work has been partially supported by the project MALEGRA TEC2016-75976-R financed by the Spanish Ministerio de Economía y Competitividad.

Transient global amnesia (TGA) is a disorder characterised by a temporary, reversible disruption of short-term memory. While the diagnosis of TGA is based on its clinical features, neuroimaging is important to exclude other sinister causes of global amnesia. Furthermore, classical MRI changes in TGA have been well described in the literature. These consist of unilateral or bilateral punctuate areas of hyperintensity in the hippocampal cornu ammonis 1 (CA1) region on diffusion-weighted imaging. We describe a case of a 61-year- old gentleman, presenting with symptoms of transient memory loss and confusion. A stroke was initially suspected in view of his multiple risk factors. Timely MRI demonstrated the typical findings associated with TGA. Recognition of these imaging features is of the utmost importance for radiologists in order to allow for an accurate diagnosis and differentiation from ischaemic pathology., peer-reviewed

Highlights • We present an automated pipeline to segment the brain structures of MS patients. • The proposed pipeline improves the segmentation result of the traditional methods. • Traditional methods combined with lesion filling are sensitive to the lesion mask used. • The results show that our pipeline is robust against variations in the lesion mask., Accurate volume measurements of the brain structures are important for treatment evaluation and disease follow-up in multiple sclerosis (MS) patients. With the aim of obtaining reproducible measurements and avoiding the intra-/inter-rater variability that manual delineations introduce, several automated brain structure segmentation strategies have been proposed in recent years. However, most of these strategies tend to be affected by the abnormal MS lesion intensities, which corrupt the structure segmentation result. To address this problem, we recently reformulated two label fusion strategies of the state of the art, improving their segmentation performance on the lesion areas. Here, we integrate these reformulated strategies in a completely automated pipeline that includes pre-processing (inhomogeneity correction and intensity normalization), atlas selection, masked registration and label fusion, and combine them with an automated lesion segmentation method of the state of the art. We study the effect of automating the lesion mask acquisition on the structure segmentation result, analyzing the output of the proposed pipeline when used in combination with manually and automatically segmented lesion masks. We further analyze the effect of those masks on the segmentation result of the original label fusion strategies when combined with the well-established pre-processing step of lesion filling. The experiments performed show that, when the original methods are used to segment the lesion-filled images, significant structure volume differences are observed in a comparison between manually and automatically segmented lesion masks. The results indicate a mean volume decrease of 1.13%±1.93 in the cerebrospinal fluid, and a mean volume increase of 0.13%±0.14 and 0.05%±0.08 in the cerebral white matter and cerebellar gray matter, respectively. On the other hand, no significant volume differences were found when the proposed automated pipeline was used for segmentation, which demonstrates its robustness against variations in the lesion mask used.

There has been an increasing interest in examining organisational principles of the cerebral cortex (and subcortical regions) using different MRI features such as structural or functional connectivity. Despite the widespread interest, introductory tutorials on the underlying technique targeted for the novice neuroimager are sparse in the literature. Articles that investigate various “neural gradients” (for example based on region studied “cortical gradients,” “cerebellar gradients,” “hippocampal gradients” etc … or feature of interest “functional gradients,” “cytoarchitectural gradients,” “myeloarchitectural gradients” etc …) have increased in popularity. Thus, we believe that it is opportune to discuss what is generally meant by “gradient analysis”. We introduce basics concepts in graph theory, such as graphs themselves, the degree matrix, and the adjacency matrix. We discuss how one can think about gradients of feature similarity (the similarity between timeseries in fMRI, or streamline in tractography) using graph theory and we extend this to explore such gradients across the whole MRI scale; from the voxel level to the whole brain level. We proceed to introduce a measure for quantifying the level of similarity in regions of interest. We propose the term “the Vogt-Bailey index” for such quantification to pay homage to our history as a brain mapping community. We run through the techniques on sample datasets including a brain MRI as an example of the application of the techniques on real data and we provide several appendices that expand upon details. To maximise intuition, the appendices contain a didactic example describing how one could use these techniques to solve a particularly pernicious problem that one may encounter at a wedding. Accompanying the article is a tool, available in both MATLAB and Python, that enables readers to perform the analysis described in this article on their own data. We refer readers to the graphical abstract as an overview of the analysis pipeline presented in this work., Graphical abstract The two basic algorithms to compute the VB Index and the principal gradient. The algorithm on the left depicts a searchlight algorithm that identifies local borders. The algorithm on the right (yellow route) depicts the creation of a gradient map and single VB Index for the whole brain or (inclusion of orange route) multiple clusters.Image 1, Highlights • This article provides a beginner friendly review of the main steps for creating gradient maps. • We introduce a new index for quantifying mesoscopic gradients (the “VB Index”). • We use historical background to highlight the need for such quantification. • Software for computing gradient maps and the VB Index is made available.

After falling asleep, the brain needs to detach from waking activity and reorganize into a functionally distinct state. A functional MRI (fMRI) study has recently revealed that the transition to unconsciousness induced by propofol involves a global decline of brain activity followed by a transient reduction in cortico-subcortical coupling. We have analyzed the relationships between transitional brain activity and breathing changes as one example of a vital function that needs the brain to readapt. Thirty healthy participants were originally examined. The analysis involved the correlation between breathing and fMRI signal upon loss of consciousness. We proposed that a decrease in ventilation would be coupled to the initial decline in fMRI signal in brain areas relevant for modulating breathing in the awake state, and that the subsequent recovery would be coupled to fMRI signal in structures relevant for controlling breathing during the unconscious state. Results showed that a slight reduction in breathing from wakefulness to unconsciousness was distinctively associated with decreased activity in brain systems underlying different aspects of consciousness including the prefrontal cortex, the default mode network and somatosensory areas. Breathing recovery was distinctively coupled to activity in deep brain structures controlling basic behaviors such as the hypothalamus and amygdala. Activity in the brainstem, cerebellum and hippocampus was associated with breathing variations in both states. Therefore, our brain maps illustrate potential drives to breathe, unique to wakefulness, in the form of brain systems underlying cognitive awareness, self-awareness and sensory awareness, and to unconsciousness involving structures controlling instinctive and homeostatic behaviors.

Sub-cortical brain structure segmentation in Magnetic Resonance Images (MRI) has attracted the interest of the research community for a long time as morphological changes in these structures are related to different neurodegenerative disorders. However, manual segmentation of these structures can be tedious and prone to variability, highlighting the need for robust automated segmentation methods. In this paper, we present a novel convolutional neural network based approach for accurate segmentation of the sub-cortical brain structures that combines both convolutional and prior spatial features for improving the segmentation accuracy. In order to increase the accuracy of the automated segmentation, we propose to train the network using a restricted sample selection to force the network to learn the most difficult parts of the structures. We evaluate the accuracy of the proposed method on the public MICCAI 2012 challenge and IBSR 18 datasets, comparing it with different traditional and deep learning state-of-the-art methods. On the MICCAI 2012 dataset, our method shows an excellent performance comparable to the best participant strategy on the challenge, while performing significantly better than state-of-the-art techniques such as FreeSurfer and FIRST. On the IBSR 18 dataset, our method also exhibits a significant increase in the performance with respect to not only FreeSurfer and FIRST, but also comparable or better results than other recent deep learning approaches. Moreover, our experiments show that both the addition of the spatial priors and the restricted sampling strategy have a significant effect on the accuracy of the proposed method. In order to encourage the reproducibility and the use of the proposed method, a public version of our approach is available to download for the neuroimaging community Kaisar Kushibar and Jose Bernal hold FI-DGR2017 grant from the Catalan Government with reference numbers 2017FI_B00372 and 2017FI_B00476, respectively. This work has been partially supported by La Fundació la Marató de TV3, by Retos de Investigación TIN2014-55710-R, TIN2015-73563-JIN, and DPI2017-86696-R from the Ministerio de Ciencia y Tecnologia

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes,creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Quantification of white matter hyperintensities (WMH) of presumed vascular origin is of key importance in many neurological research studies. Advanced measurements are obtained from manual segmentations on brain MR images, which is a laborious procedure. Automatic WMH segmentation methods exist, but a standardized comparison of such methods is lacking. We organized a scientific challenge, in which developers could evaluate their method on a standardized multi-center/-scanner image dataset, giving an objective comparison: the WMH Segmentation Challenge (http://wmh.isi.uu.nl/). Sixty T1+FLAIR images from three MR scanners were released with manual WMH segmentations. A secret test set of 110 images from five MR scanners was used for evaluation. Methods had to be containerized and submitted to the challenge organizers. Five evaluation metrics were used to rank the methods: (1) Dice Similarity Coefficient, (2) modified Hausdorff distance (95th percentile), (3) absolute percentage volume difference, (4) sensitivity for detecting individual lesions, and (5) F1-score for individual lesions. Additionally, methods were ranked on their inter-scanner robustness. Twenty participants submitted their method for evaluation. This paper provides a detailed analysis of the results. In brief, there is a cluster of four methods that rank significantly better than the other methods. There is one clear winner, which also has the best inter-scanner robustness. The challenge remains open for future submissions and provides a public platform for method evaluation.