Showing papers by "Bertrand Thirion published in 2019"

PyBIDS: Python tools for BIDS datasets.

Abstract: Tal Yarkoni1, Christopher J Markiewicz2, Alejandro de la Vega1, Krzysztof J Gorgolewski2, Taylor Salo3, Yaroslav O Halchenko4, Quinten McNamara1, Krista DeStasio5, Jean-Baptiste Poline6, Dmitry Petrov7, Valérie Hayot-Sasson8, Dylan M Nielson9, Johan Carlin10, Gregory Kiar11, Kirstie Whitaker12, Elizabeth DuPre11, Adina Wagner13, Lee S Tirrell14, Mainak Jas15, Michael Hanke13, Russell A Poldrack2, Oscar Esteban2, Stefan Appelhoff16, Chris Holdgraf17, Isla Staden18, Bertrand Thirion19, Dave F Kleinschmidt20, John A Lee9, Matteo Visconti di Oleggio Castello17, Michael P Notter21, and Ross Blair2

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 catalog of cognitive functions, we developed a data-driven machine-learning strategy and provide a proof of principle in a multisite clinical dataset (n = 324). Existing neuroscientific knowledge on diverse cognitive domains was first condensed into neurotopographical 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.

Recursive Nearest Agglomeration (ReNA): Fast Clustering for Approximation of Structured Signals

Abstract: In this work, we revisit fast dimension reduction approaches, as with random projections and random sampling. Our goal is to summarize the data to decrease computational costs and memory footprint of subsequent analysis. Such dimension reduction can be very efficient when the signals of interest have a strong structure, such as with images. We focus on this setting and investigate feature clustering schemes for data reductions that capture this structure. An impediment to fast dimension reduction is then that good clustering comes with large algorithmic costs. We address it by contributing a linear-time agglomerative clustering scheme, Recursive Nearest Agglomeration (ReNA). Unlike existing fast agglomerative schemes, it avoids the creation of giant clusters. We empirically validate that it approximates the data as well as traditional variance-minimizing clustering schemes that have a quadratic complexity. In addition, we analyze signal approximation with feature clustering and show that it can remove noise, improving subsequent analysis steps. As a consequence, data reduction by clustering features with ReNA yields very fast and accurate models, enabling to process large datasets on budget. Our theoretical analysis is backed by extensive experiments on publicly-available data that illustrate the computation efficiency and the denoising properties of the resulting dimension reduction scheme.

SmartPulse, a Machine Learning Approach for Calibration-Free Dynamic RF Shimming: Preliminary Study in a Clinical Environment

Abstract: Purpose A calibration-free pulse design method is introduced to alleviate B 1 + artifacts in clinical routine with parallel transmission at high field, dealing with significant inter-subject variability, found for instance in the abdomen. Theory and methods From a dual-transmit 3T scanner, a database of B 1 + and off-resonance abdominal maps from 50 subjects was first divided into 3 clusters based on mutual affinity between their respective tailored kT -points pulses. For each cluster, a kT -points pulse was computed, minimizing normalized root-mean-square flip angle deviations simultaneously for all subjects comprised in it. Using 30 additional subjects' field distributions, a machine learning classifier was trained on this 80-labeled-subject database to recognize the best pulse from the 3 ones available, relying only on patient features accessible from the preliminary localizer sequence present in all protocols. This so-called SmartPulse process was experimentally tested on an additional 53-subject set and compared with other pulse types: vendor's hard calibration-free dual excitation, tailored static radiofrequency shimming, universal and tailored kT -points pulses. Results SmartPulse outperformed both calibration-free approaches. Tailored static radiofrequency shimming yielded similar flip angle homogeneity for most patients but broke down for some while SmartPulse remained robust. Although flip angle homogeneity was systematically better with tailored kT -points, the difference was barely noticeable on in vivo images. Conclusion The proposed method paves the way toward an efficient trade-off between tailored and universal pulse design approaches for large inter-subject variability. With no need for on-line field mapping or pulse design, it can fit seamlessly into a clinical protocol.

Variability in the analysis of a single neuroimaging dataset by many teams

Abstract: Data analysis workflows in many scientific domains have become increasingly complex and flexible. To assess the impact of this flexibility on functional magnetic resonance imaging (fMRI) results, the same dataset was independently analyzed by 70 teams, testing nine ex-ante hypotheses. The flexibility of analytic approaches is exemplified by the fact that no two teams chose identical workflows to analyze the data. This flexibility resulted in sizeable variation in hypothesis test results, even for teams whose statistical maps were highly correlated at intermediate stages of their analysis pipeline. Variation in reported results was related to several aspects of analysis methodology. Importantly, meta-analytic approaches that aggregated information across teams yielded significant consensus in activated regions across teams. Furthermore, prediction markets of researchers in the field revealed an overestimation of the likelihood of significant findings, even by researchers with direct knowledge of the dataset. Our findings show that analytic flexibility can have substantial effects on scientific conclusions, and demonstrate factors related to variability in fMRI. The results emphasize the importance of validating and sharing complex analysis workflows, and demonstrate the need for multiple analyses of the same data. Potential approaches to mitigate issues related to analytical variability are discussed.

Local Optimal Transport for Functional Brain Template Estimation

Abstract: 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.

Multi-subject MEG/EEG source imaging with sparse multi-task regression

Abstract: Magnetoencephalography and electroencephalography (M/EEG) are non-invasive modalities that measure the weak electromagnetic fields generated by neural activity. Estimating the location and magnitude of the current sources that generated these electromagnetic fields is a challenging ill-posed regression problem known as \emph{source imaging}. When considering a group study, a common approach consists in carrying out the regression tasks independently for each subject. An alternative is to jointly localize sources for all subjects taken together, while enforcing some similarity between them. By pooling all measurements in a single multi-task regression, one makes the problem better posed, offering the ability to identify more sources and with greater precision. The Minimum Wasserstein Estimates (MWE) promotes focal activations that do not perfectly overlap for all subjects, thanks to a regularizer based on Optimal Transport (OT) metrics. MWE promotes spatial proximity on the cortical mantel while coping with the varying noise levels across subjects. On realistic simulations, MWE decreases the localization error by up to 4 mm per source compared to individual solutions. Experiments on the Cam-CAN dataset show a considerable improvement in spatial specificity in population imaging. Our analysis of a multimodal dataset shows how multi-subject source localization closes the gap between MEG and fMRI for brain mapping.

ECKO: Ensemble of Clustered Knockoffs for Robust Multivariate Inference on fMRI Data

Abstract: 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.

Group level MEG/EEG source imaging via optimal transport: minimum Wasserstein estimates

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.

Fast shared response model for fMRI data

Abstract: The shared response model provides a simple but effective framework to analyse fMRI data of subjects exposed to naturalistic stimuli. However when the number of subjects or runs is large, fitting the model requires a large amount of memory and computational power, which limits its use in practice. In this work, we introduce the FastSRM algorithm that relies on an intermediate atlas-based representation. It provides considerable speed-up in time and memory usage, hence it allows easy and fast large-scale analysis of naturalistic-stimulus fMRI data. Using four different datasets, we show that our method matches the performance of the original SRM algorithm while being about 5x faster and 20x to 40x more memory efficient. Based on this contribution, we use FastSRM to predict age from movie watching data on the CamCAN sample. Besides delivering accurate predictions (mean absolute error of 7.5 years), FastSRM extracts topographic patterns that are predictive of age, demonstrating that brain activity during free perception reflects age.

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 stochas-tic 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 archi-tectures, 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.

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 stochas-tic 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 archi-tectures, 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.

Group level MEG/EEG source imaging via optimal transport: minimum Wasserstein estimates

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.

Patterns of Autism Symptoms: Hidden Structure in the ADOS and ADI-R instruments

Abstract: We simultaneously revisited the ADI-R and ADOS with a comprehensive data-analytics strategy. Here, the combination of pattern analysis algorithms and an extensive data resources (n=266 patients aged 7 to 49 years) allowed identifying coherent clinical constellations in and across ADI-R and ADOS assessments widespread in clinical practice. The collective results of the clustering and sparse regression approaches suggest that identifying autism subtypes and severity for a given individual may be most manifested in the social and communication domains of the ADI-R. Additionally, our quantitative investigation revealed that disease-specific patterns of ADI-R and ADOS scores can be uncovered when studying sex, age or level of FIQ in patients.

ECKO: Ensemble of Clustered Knockoffs for multivariate inference on fMRI data

Abstract: 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.