BRAINS: Building Representations with Autoencoders for Individualized Neuroimaging Spaces

Kajal Singla, Pierre-Louis Bazin, Nico Scherf
Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, PMLR 308:189-198, 2026.

Abstract

Functional Magnetic Resonance Imaging (fMRI) provides rich, high-dimensional data on human brain activity, yet traditional dimensionality-reduction techniques primarily capture group-level structure and overlook individual variability. We introduce BRAINS, a framework based on Convolutional Variational Autoencoders (CVAEs) that learns subject-specific latent spaces directly from BOLD signals. These latent representations effectively denoise voxel-wise time series ( 5% tSNR gain) while preserving functional connectivity and anatomical coherence. Using Procrustes alignment, we show that individual latent spaces can be aligned across participants, revealing both shared and idiosyncratic components of cortical organization. Our approach bridges neuroimaging and deep representation learning, offering a geometry-aware foundation for individualized brain analysis and multimodal integration across subjects, tasks, and models. The code is available at: https://github.com/neural-data-science-lab/NEUROAI_AAAI_BRAINS.git.

Cite this Paper

BibTeX
@InProceedings{pmlr-v308-singla26a, title = {BRAINS: Building Representations with Autoencoders for Individualized Neuroimaging Spaces}, author = {Singla, Kajal and Bazin, Pierre-Louis and Scherf, Nico}, booktitle = {Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026}, pages = {189--198}, year = {2026}, editor = {Abbasi-Asl, Reza and Iqbal, Asim and Ito, Shinya and Arkhipov, Anton and Sanborn, Sophia}, volume = {308}, series = {Proceedings of Machine Learning Research}, month = {27 Jan}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v308/main/assets/singla26a/singla26a.pdf}, url = {https://proceedings.mlr.press/v308/singla26a.html}, abstract = {Functional Magnetic Resonance Imaging (fMRI) provides rich, high-dimensional data on human brain activity, yet traditional dimensionality-reduction techniques primarily capture group-level structure and overlook individual variability. We introduce BRAINS, a framework based on Convolutional Variational Autoencoders (CVAEs) that learns subject-specific latent spaces directly from BOLD signals. These latent representations effectively denoise voxel-wise time series ( 5% tSNR gain) while preserving functional connectivity and anatomical coherence. Using Procrustes alignment, we show that individual latent spaces can be aligned across participants, revealing both shared and idiosyncratic components of cortical organization. Our approach bridges neuroimaging and deep representation learning, offering a geometry-aware foundation for individualized brain analysis and multimodal integration across subjects, tasks, and models. The code is available at: https://github.com/neural-data-science-lab/NEUROAI_AAAI_BRAINS.git.} }
Endnote
%0 Conference Paper %T BRAINS: Building Representations with Autoencoders for Individualized Neuroimaging Spaces %A Kajal Singla %A Pierre-Louis Bazin %A Nico Scherf %B Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026 %C Proceedings of Machine Learning Research %D 2026 %E Reza Abbasi-Asl %E Asim Iqbal %E Shinya Ito %E Anton Arkhipov %E Sophia Sanborn %F pmlr-v308-singla26a %I PMLR %P 189--198 %U https://proceedings.mlr.press/v308/singla26a.html %V 308 %X Functional Magnetic Resonance Imaging (fMRI) provides rich, high-dimensional data on human brain activity, yet traditional dimensionality-reduction techniques primarily capture group-level structure and overlook individual variability. We introduce BRAINS, a framework based on Convolutional Variational Autoencoders (CVAEs) that learns subject-specific latent spaces directly from BOLD signals. These latent representations effectively denoise voxel-wise time series ( 5% tSNR gain) while preserving functional connectivity and anatomical coherence. Using Procrustes alignment, we show that individual latent spaces can be aligned across participants, revealing both shared and idiosyncratic components of cortical organization. Our approach bridges neuroimaging and deep representation learning, offering a geometry-aware foundation for individualized brain analysis and multimodal integration across subjects, tasks, and models. The code is available at: https://github.com/neural-data-science-lab/NEUROAI_AAAI_BRAINS.git.
APA
Singla, K., Bazin, P. & Scherf, N.. (2026). BRAINS: Building Representations with Autoencoders for Individualized Neuroimaging Spaces. Proceedings of the First Workshop on NeuroAI Multimodal Intelligence @ AAAI 2026, in Proceedings of Machine Learning Research 308:189-198 Available from https://proceedings.mlr.press/v308/singla26a.html.

Related Material