Posts by Collection

portfolio

Brainiak

Short description of portfolio item number 1

publications

Optimizing deep video representation to match brain activity

Published in CCN 2018 - Conference on Cognitive Computational Neuroscience, 2018

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.

Recommended citation: H Richard, A Pinho, B Thirion, G Charpiat - Conference on Cognitive Computational Neuroscience, 2018 https://arxiv.org/pdf/1809.02440.pdf

Fast shared response model for fMRI data

Published in OHBM 2018, 2019

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. The FastSRM algorithm 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.

Recommended citation: H Richard, L Martin, AL Pinho, J Pillow, B Thirion - OHBM 2018 https://arxiv.org/abs/1809.02440

Local optimal transport for functional brain template estimation

Published in International Conference on Information Processing in Medical Imaging, 2019

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 road-blocks 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.

Recommended citation: Bazeille, T., Richard, H., Janati, H., & Thirion, B. (2019, June). Local optimal transport for functional brain template estimation. In International Conference on Information Processing in Medical Imaging (pp. 237-248). Springer, Cham. https://hal.archives-ouvertes.fr/hal-02278663/document

Modeling Shared Responses in Neuroimaging Studies through MultiView ICA

Published in Arxiv, 2020

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 road-blocks 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.

Recommended citation: Richard, H., Gresele, L., Hyvärinen, A., Thirion, B., Gramfort, A., & Ablin, P. (2020). Modeling Shared Responses in Neuroimaging Studies through MultiView ICA. arXiv preprint arXiv:2006.06635. https://arxiv.org/pdf/2006.06635.pdf

software

FastSRM

Identifiable version of FastSRM as a standalone package

talks

teaching

Introduction to Linear Algebra

Undergraduate course, IUT Orsay, 2018

An introduction to linear algebra concluding with an introduction to abstract vector spaces.