Showing papers by "Bertrand Thirion published in 2018"

Subspecialization within default mode nodes characterized in 10,000 UK Biobank participants.

Abstract: The human default mode network (DMN) is implicated in several unique mental capacities. In this study, we tested whether brain-wide interregional communication in the DMN can be derived from population variability in intrinsic activity fluctuations, gray-matter morphology, and fiber tract anatomy. In a sample of 10,000 UK Biobank participants, pattern-learning algorithms revealed functional coupling states in the DMN that are linked to connectivity profiles between other macroscopical brain networks. In addition, DMN gray matter volume was covaried with white matter microstructure of the fornix. Collectively, functional and structural patterns unmasked a possible division of labor within major DMN nodes: Subregions most critical for cortical network interplay were adjacent to subregions most predictive of fornix fibers from the hippocampus that processes memories and places.

Individual Brain Charting, a high-resolution fMRI dataset for cognitive mapping.

Abstract: Functional Magnetic Resonance Imaging (fMRI) has furthered brain mapping on perceptual, motor, as well as higher-level cognitive functions. However, to date, no data collection has systematically addressed the functional mapping of cognitive mechanisms at a fine spatial scale. The Individual Brain Charting (IBC) project stands for a high-resolution multi-task fMRI dataset that intends to provide the objective basis toward a comprehensive functional atlas of the human brain. The data refer to a cohort of 12 participants performing many different tasks. The large amount of task-fMRI data on the same subjects yields a precise mapping of the underlying functions, free from both inter-subject and inter-site variability. The present article gives a detailed description of the first release of the IBC dataset. It comprises a dozen of tasks, addressing both low- and high- level cognitive functions. This openly available dataset is thus intended to become a reference for cognitive brain mapping. Machine-accessible metadata file describing the reported data (ISA-Tab format)

Atlases of cognition with large-scale human brain mapping.

Abstract: To map the neural substrate of mental function, cognitive neuroimaging relies on controlled psychological manipulations that engage brain systems associated with specific cognitive processes. In order to build comprehensive atlases of cognitive function in the brain, it must assemble maps for many different cognitive processes, which often evoke overlapping patterns of activation. Such data aggregation faces contrasting goals: on the one hand finding correspondences across vastly different cognitive experiments, while on the other hand precisely describing the function of any given brain region. Here we introduce a new analysis framework that tackles these difficulties and thereby enables the generation of brain atlases for cognitive function. The approach leverages ontologies of cognitive concepts and multi-label brain decoding to map the neural substrate of these concepts. We demonstrate the approach by building an atlas of functional brain organization based on 30 diverse functional neuroimaging studies, totaling 196 different experimental conditions. Unlike conventional brain mapping, this functional atlas supports robust reverse inference: predicting the mental processes from brain activity in the regions delineated by the atlas. To establish that this reverse inference is indeed governed by the corresponding concepts, and not idiosyncrasies of experimental designs, we show that it can accurately decode the cognitive concepts recruited in new tasks. These results demonstrate that aggregating independent task-fMRI studies can provide a more precise global atlas of selective associations between brain and cognition.

Shared endo-phenotypes of default mode dsfunction in attention deficit/hyperactivity disorder and autism spectrum disorder.

Abstract: Categorical diagnoses from the Diagnostic and Statistical Manual of Mental Disorders (DSM) or International Classification of Diseases (ICD) manuals are increasingly found to be incongruent with emerging neuroscientific evidence that points towards shared neurobiological dysfunction underlying attention deficit/hyperactivity disorder and autism spectrum disorder. Using resting-state functional magnetic resonance imaging data, functional connectivity of the default mode network, the dorsal attention and salience network was studied in 1305 typically developing and diagnosed participants. A transdiagnostic hierarchical Bayesian modeling framework combining Indian Buffet Processes and Latent Dirichlet Allocation was proposed to address the urgent need for objective brain-derived measures that can acknowledge shared brain network dysfunction in both disorders. We identified three main variation factors characterized by distinct coupling patterns of the temporoparietal cortices in the default mode network with the dorsal attention and salience network. The brain-derived factors were demonstrated to effectively capture the underlying neural dysfunction shared in both disorders more accurately, and to enable more reliable diagnoses of neurobiological dysfunction. The brain-derived phenotypes alone allowed for a classification accuracy reflecting an underlying neuropathology of 67.33% (+/-3.07) in new individuals, which significantly outperformed the 46.73% (+/-3.97) accuracy of categorical diagnoses. Our results provide initial evidence that shared neural dysfunction in ADHD and ASD can be derived from conventional brain recordings in a data-led fashion. Our work is encouraging to pursue a translational endeavor to find and further study brain-derived phenotypes, which could potentially be used to improve clinical decision-making and optimize treatment in the future.

Different shades of default mode disturbance in schizophrenia: Subnodal covariance estimation in structure and function

Abstract: Schizophrenia is a devastating mental disease with an apparent disruption in the highly associative default mode network (DMN). Interplay between this canonical network and others probably contributes to goal-directed behavior so its disturbance is a candidate neural fingerprint underlying schizophrenia psychopathology. Previous research has reported both hyperconnectivity and hypoconnectivity within the DMN, and both increased and decreased DMN coupling with the multimodal saliency network (SN) and dorsal attention network (DAN). This study systematically revisited network disruption in patients with schizophrenia using data-derived network atlases and multivariate pattern-learning algorithms in a multisite dataset (n = 325). Resting-state fluctuations in unconstrained brain states were used to estimate functional connectivity, and local volume differences between individuals were used to estimate structural co-occurrence within and between the DMN, SN, and DAN. In brain structure and function, sparse inverse covariance estimates of network coupling were used to characterize healthy participants and patients with schizophrenia, and to identify statistically significant group differences. Evidence did not confirm that the backbone of the DMN was the primary driver of brain dysfunction in schizophrenia. Instead, functional and structural aberrations were frequently located outside of the DMN core, such as in the anterior temporoparietal junction and precuneus. Additionally, functional covariation analyses highlighted dysfunctional DMN-DAN coupling, while structural covariation results highlighted aberrant DMN-SN coupling. Our findings reframe the role of the DMN core and its relation to canonical networks in schizophrenia. We thus underline the importance of large-scale neural interactions as effective biomarkers and indicators of how to tailor psychiatric care to single patients.

Stochastic Subsampling for Factorizing Huge Matrices

Abstract: We present a matrix-factorization algorithm that scales to input matrices with both huge number of rows and columns. Learned factors may be sparse or dense and/or nonnegative, which makes our algorithm suitable for dictionary learning, sparse component analysis, and nonnegative matrix factorization. Our algorithm streams matrix columns while subsampling them to iteratively learn the matrix factors. At each iteration, the row dimension of a new sample is reduced by subsampling, resulting in lower time complexity compared to a simple streaming algorithm. Our method comes with convergence guarantees to reach a stationary point of the matrix-factorization problem. We demonstrate its efficiency on massive functional magnetic resonance imaging data (2 TB), and on patches extracted from hyperspectral images (103 GB). For both problems, which involve different penalties on rows and columns, we obtain significant speed-ups compared to state-of-the-art algorithms.

Inter-subject Registration of Functional Images: Do We Need Anatomical Images?

Abstract: In Echo-Planar Imaging (EPI)-based MRI (Magnetic Resonance Imaging), inter-subject registration typically uses the subject's T1-weighted (T1w) anatomical image to learn deformations of the subject's brain onto a template. The estimated deformation fields are then applied to the subject's EPI scans (functional or diffusion-weighted images) to warp the latter to a template space. Historically, such indirect T1w-based registration was motivated by the lack of clear anatomical details in low-resolution EPI images: a direct registration of the EPI scans to template space would be futile. A central prerequisite in such indirect methods is that the anatomical (aka the T1w) image of each subject is well aligned with their EPI images via rigid coregistration. We provide experimental evidence that things have changed: nowadays, there is a decent amount of anatomical contrast in high-resolution EPI data. That notwithstanding, EPI distortions due to B0 inhomogeneities cannot be fully corrected. Residual uncorrected distortions induce non-rigid deformations between the EPI scans and the same subject's anatomical scan. In this manuscript, we contribute a computationally cheap pipeline that leverages the high spatial resolution of modern EPI scans for direct inter-subject matching. Our pipeline is direct and does not rely on the T1w scan to estimate the inter-subject deformation. Results on a large dataset show that this new pipeline outperforms the classical indirect T1w-based registration scheme, across a variety of post-registration quality-assessment metrics including: Normalized Mutual Information, relative variance (variance-to-mean ratio), and to a lesser extent, improved peaks of group-level General Linear Model (GLM) activation maps.

Approximate message-passing for convex optimization with non-separable penalties

Abstract: We introduce an iterative optimization scheme for convex objectives consisting of a linear loss and a non-separable penalty, based on the expectation-consistent approximation and the vector approximate message-passing (VAMP) algorithm. Specifically, the penalties we approach are convex on a linear transformation of the variable to be determined, a notable example being total variation (TV). We describe the connection between message-passing algorithms-typically used for approximate inference-and proximal methods for optimization, and show that our scheme is, as VAMP, similar in nature to the Peaceman-Rachford splitting, with the important difference that stepsizes are set adaptively. Finally, we benchmark the performance of our VAMP-like iteration in problems where TV penalties are useful, namely classification in task fMRI and reconstruction in tomography, and show faster convergence than that of state-of-the-art approaches such as FISTA and ADMM in most settings.

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

Abstract: In the 20th century many advances in biological knowledge and evidence-based medicine were supported by p-values and accompanying methods. In the beginning 21st century, 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 individual9s future. This comparison applies the linear model for identifying significant contributing variables and for finding the most predictive variable 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.

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

Abstract: 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-sparametric 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.

Patterns of schizophrenia symptoms: hidden structure in the PANSS questionnaire.

Abstract: The clinical presentation of patients with schizophrenia has long been described to be very heterogeneous. Coherent symptom profiles can probably be directly derived from behavioral manifestations quantified in medical questionnaires. The combination of machine learning algorithms and an international multi-site dataset (n = 218 patients) identified distinctive patterns underlying schizophrenia from the widespread PANSS questionnaire. Our clustering approach revealed a negative symptom patient group as well as a moderate and a severe group, giving further support for the existence of schizophrenia subtypes. Additionally, emerging regression analyses uncovered the most clinically predictive questionnaire items. Small subsets of PANSS items showed convincing forecasting performance in single patients. These item subsets encompassed the entire symptom spectrum confirming that the different facets of schizophrenia can be shown to enable improved clinical diagnosis and medical action in patients. Finally, we did not find evidence for complicated relationships among the PANSS items in our sample. Our collective results suggest that identifying best treatment for a given individual may be grounded in subtle item combinations that transcend the long-trusted positive, negative, and cognitive categories.

Brain-based ranking of cognitive domains to predict schizophrenia

Abstract: Schizophrenia is a devastating brain disorder that disturbs sensory perception, motor action, and abstract thought. Its clinical phenotype implies dysfunction of various mental domains, which has motivated a series of theories regarding the underlying pathophysiology. Aiming at a predictive benchmark of a catalogue of cognitive functions, we developed a bottom-up machine-learning strategy and provide a proof of principle in a multi-site clinical dataset (n=324). Existing neuroscientific knowledge on diverse cognitive domains was first condensed into neuro-topographical maps. We then examined how the ensuing meta-analytic cognitive priors can distinguish patients and controls using brain morphology and intrinsic functional connectivity. Some affected cognitive domains supported well-studied directions of research on auditory evaluation and social cognition. However, rarely suspected cognitive domains also emerged as disease-relevant, including self-oriented processing of bodily sensations in gustation and pain. Such algorithmic charting of the cognitive landscape can be used to make targeted recommendations for future mental health research.

Extracting Universal Representations of Cognition across Brain-Imaging Studies

Abstract: We show in this paper how to extract shared brain representations that predict mental processes across many cognitive neuroimaging studies. Focused cognitive-neuroimaging experiments study precise mental processes with carefully-designed cognitive paradigms; however the cost of imaging limits their statistical power. On the other hand, large-scale databasing efforts increase considerably the sample sizes, but cannot ask precise cognitive questions. To address this tension, we develop new methods that turn the heterogeneous cognitive information held in different task-fMRI studies into common-universal-cognitive models. Our approach does not assume any prior knowledge of the commonalities shared by the studies in the corpus; those are inferred during model training. The method uses deep-learning techniques to extract representations - task-optimized networks - that form a set of basis cognitive dimensions relevant to the psychological manipulations. In this sense, it forms a novel kind of functional atlas, optimized to capture mental state across many functional-imaging experiments. As it bridges information on the neural support of mental processes, this representation improves decoding performance for 80% of the 35 widely-different functional imaging studies that we consider. Our approach opens new ways of extracting information from brain maps, increasing statistical power even for focused cognitive neuroimaging studies, in particular for those with few subjects.

Statistical Inference with Ensemble of Clustered Desparsified Lasso

Abstract: Medical imaging involves high-dimensional data, yet their acquisition is obtained for limited samples. Multivariate predictive models have become popular in the last decades to fit some external variables from imaging data, and standard algorithms yield point estimates of the model parameters. It is however challenging to attribute confidence to these parameter estimates, which makes solutions hardly trustworthy. In this paper we present a new algorithm that assesses parameters statistical significance and that can scale even when the number of predictors \(p \ge 10^{5}\) is much higher than the number of samples \(n \le 10^{3}\), by leveraging structure among features. Our algorithm combines three main ingredients: a powerful inference procedure for linear models –the so-called Desparsified Lasso– feature clustering and an ensembling step. We first establish that Desparsified Lasso alone cannot handle \(n \ll p\) regimes; then we demonstrate that the combination of clustering and ensembling provides an accurate solution, whose specificity is controlled. We also demonstrate stability improvements on two neuroimaging datasets.

Using Feature Grouping as a Stochastic Regularizer for High-Dimensional Noisy Data.

Abstract: The use of complex models --with many parameters-- is challenging with high-dimensional small-sample problems: indeed, they face rapid overfitting. Such situations are common when data collection is expensive, as in neuroscience, biology, or geology. Dedicated regularization can be crafted to tame overfit, typically via structured penalties. But rich penalties require mathematical expertise and entail large computational costs. Stochastic regularizers such as dropout are easier to implement: they prevent overfitting by random perturbations. Used inside a stochastic optimizer, they come with little additional cost. We propose a structured stochastic regularization that relies on feature grouping. Using a fast clustering algorithm, we define a family of groups of features that capture feature covariations. We then randomly select these groups inside a stochastic gradient descent loop. This procedure acts as a structured regularizer for high-dimensional correlated data without additional computational cost and it has a denoising effect. We demonstrate the performance of our approach for logistic regression both on a sample-limited face image dataset with varying additive noise and on a typical high-dimensional learning problem, brain image classification.

Text to brain: predicting the spatial distribution of neuroimaging observations from text reports

Abstract: Despite the digital nature of magnetic resonance imaging, the resulting observations are most frequently reported and stored in text documents. There is a trove of information untapped in medical health records, case reports, and medical publications. In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms. The problem is formulated in terms of minimization of a risk on distributions which leads to a least-deviation cost function. An efficient algorithm in the dual then learns the mapping from documents to brain structures. Empirical results using coordinates extracted from the brain-imaging literature show that i) models must adapt to semantic variation in the terms used to describe a given anatomical structure, ii) voxel-wise parameterization leads to higher likelihood of locations reported in unseen documents, iii) least-deviation cost outperforms least-square. As a proof of concept for our method, we use our model of spatial distributions to predict the distribution of specific neurological conditions from text-only reports.

Atlases of cognition with large-scale brain mapping

Abstract: To map the neural substrate of mental function, cognitive neuroimaging relies on controlled psychological manipulations that engage brain systems associated with specific cognitive processes. In order to build comprehensive atlases of cognitive function in the brain, it must assemble maps for many different cognitive processes, which often evoke overlapping patterns of activation. Such data aggregation faces contrasting goals: on the one hand finding correspondences across vastly different cognitive experiments, while on the other hand precisely describing the function of any given brain region. Here we introduce a new analysis framework that tackles these difficulties and thereby enables the generation of brain atlases for cognitive function. The approach leverages ontologies of cognitive concepts and multi-label brain decoding to map the neural substrate of these concepts. We demonstrate the approach by building an atlas of functional brain organization based on 30 diverse functional neuroimaging studies, totaling 196 different experimental conditions. Unlike conventional brain mapping, this functional atlas supports robust reverse inference: predicting the mental processes from brain activity in the regions delineated by the atlas. To establish that this reverse inference is indeed governed by the corresponding concepts, and not idiosyncrasies of experimental designs, we show that it can accurately decode the cognitive concepts recruited in new tasks. These results demonstrate that aggregating independent task-fMRI studies can provide a more precise global atlas of selective associations between brain and cognition.

Optimizing deep video representation to match brain activity

Abstract: 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.

Optimizing deep video representation to match brain activity

Abstract: 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.

Statistical Inference with Ensemble of Clustered Desparsified Lasso

Abstract: Medical imaging involves high-dimensional data, yet their acquisition is obtained for limited samples. Multivariate predictive models have become popular in the last decades to fit some external variables from imaging data, and standard algorithms yield point estimates of the model parameters. It is however challenging to attribute confidence to these parameter estimates, which makes solutions hardly trustworthy. In this paper we present a new algorithm that assesses parameters statistical significance and that can scale even when the number of predictors p $\ge$ 10^5 is much higher than the number of samples n $\le$ 10^3 , by lever-aging structure among features. Our algorithm combines three main ingredients: a powerful inference procedure for linear models --the so-called Desparsified Lasso-- feature clustering and an ensembling step. We first establish that Desparsified Lasso alone cannot handle n p regimes; then we demonstrate that the combination of clustering and ensembling provides an accurate solution, whose specificity is controlled. We also demonstrate stability improvements on two neuroimaging datasets.

Text to brain: predicting the spatial distribution of neuroimaging observations from text reports

Abstract: Despite the digital nature of magnetic resonance imaging, the resulting observations are most frequently reported and stored in text documents. There is a trove of information untapped in medical health records, case reports, and medical publications. In this paper, we propose to mine brain medical publications to learn the spatial distribution associated with anatomical terms. The problem is formulated in terms of minimization of a risk on distributions which leads to a least-deviation cost function. An efficient algorithm in the dual then learns the mapping from documents to brain structures. Empirical results using coordinates extracted from the brain-imaging literature show that (i) models must adapt to semantic variation in the terms used to describe a given anatomical structure, (ii) voxel-wise parameterization leads to higher likelihood of locations reported in unseen documents, (iii) least-deviation cost outperforms least-square. As a proof of concept for our method, we use our model of spatial distributions to predict the distribution of specific neurological conditions from text-only reports.

A standardised representation for non-parametric fMRI results

Abstract: Introduction : Reuse of data collected and analysed at another site is becoming more prevalent in the neuroimaging community (cf. for example (Milham et al. 2017)) but this process usually relies on intensive data and metadata curation. Given the ever-increasing number of research datasets produced and shared, it is desirable to rely on standards that will enable automatic data and metadata retrieval for large-scale analyses (Wilkinson et al. 2016). We recently introduced NIDM-Results (Maumet et al. 2016), a data model to represent and publish data and metadata created as part of a mass univariate neuroimaging study (typically functional magnetic resonance imaging). Here we extend this model to allow for the representation of non-parametric analyses and we introduce a JSON API that will facilitate export into NIDM-Results.

Feature Grouping as a Stochastic Regularizer for High-Dimensional Structured Data

Abstract: In many applications where collecting data is expensive, for example neuroscience or medical imaging, the sample size is typically small compared to the feature dimension. It is challenging in this setting to train expressive, non-linear models without overfitting. These datasets call for intelligent regularization that exploits known structure, such as correlations between the features arising from the measurement device. However, existing structured regularizers need specially crafted solvers, which are difficult to apply to complex models. We propose a new regularizer specifically designed to leverage structure in the data in a way that can be applied efficiently to complex models. Our approach relies on feature grouping, using a fast clustering algorithm inside a stochastic gradient descent loop: given a family of feature groupings that capture feature covariations, we randomly select these groups at each iteration. We show that this approach amounts to enforcing a denoising regularizer on the solution. The method is easy to implement in many model architectures, such as fully connected neural networks, and has a linear computational cost. We apply this regularizer to a real-world fMRI dataset and the Olivetti Faces datasets. Experiments on both datasets demonstrate that the proposed approach produces models that generalize better than those trained with conventional regularizers, and also improves convergence speed.

Extracting representations of cognition across neuroimaging studies improves brain decoding

Abstract: Cognitive brain imaging is accumulating datasets about the neural substrate of many different mental processes. Yet, most studies are based on few subjects and have low statistical power. Analyzing data across studies could bring more statistical power; yet the current brain-imaging analytic framework cannot be used at scale as it requires casting all cognitive tasks in a unified theoretical framework. We introduce a new methodology to analyze brain responses across tasks without a joint model of the psychological processes. The method boosts statistical power in small studies with specific cognitive focus by analyzing them jointly with large studies that probe less focal mental processes. Our approach improves decoding performance for 80% of 35 widely-different functional-imaging studies. It finds commonalities across tasks in a data-driven way, via common brain representations that predict mental processes. These are brain networks tuned to psychological manipulations. They outline interpretable and plausible brain structures. The extracted networks have been made available; they can be readily reused in new neuro-imaging studies. We provide a multi-study decoding tool to adapt to new data.