Aligning brain functions boosts the decoding of videos in novel subjects

Alexis Thual, Yohann Benchetrit, Felix Geilert, Jérémy Rapin, Iurii Makarov, Hubert Banville, Jean-Remi King

Primary Area: applications to neuroscience & cognitive science

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: fmri, functional alignment, brain decoding, optimal transport, video decoding

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We show that it is possible to better generalize brain decoding models trained on a set of participants to other individuals.

Abstract: Deep learning is leading to major advances in the realm of brain decoding from functional Magnetic Resonance Imaging (fMRI). However, the large inter-subject variability in brain characteristics has limited most studies to train models on one subject at a time. Consequently, this approach hampers the training of deep learning models, which typically requires very large datasets. Here, we propose to boost brain decoding by aligning brain responses to videos across subjects. Compared to the anatomically-aligned baseline, our method improves out-of-subject decoding performance by up to 75%. Moreover, it also outperforms classical single-subject approaches when less than 100 minutes of data is available for the tested subject. Furthermore, we propose a new multi-subject alignment method, which obtains comparable results to that of classical single-subject approaches while easing out-of-subject generalization. Finally, we show that this method aligns neural representations in accordance with brain anatomy. Overall, this study lays foundations to leverage extensive neuroimaging datasets and enhance the decoding of individuals with a limited amount of brain recordings.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 5566