Brain-Cognition Fingerprinting via Graph-GCCA with Contrastive Learning

TL;DR

This paper introduces CoGraCa, an unsupervised graph-based model that creates individualized brain-cognition fingerprints from longitudinal neuroimaging data, outperforming existing methods in identifying sex and age while providing interpretable modality interactions.

Contribution

The paper presents CoGraCa, a novel unsupervised model combining Graph Attention Networks and generalized CCA with contrastive learning for personalized brain-cognition encoding.

Findings

Effectively captures individual differences in brain and cognition.

Outperforms existing models in sex and age identification.

Provides interpretable insights into brain-cognition interactions.

Abstract

Many longitudinal neuroimaging studies aim to improve the understanding of brain aging and diseases by studying the dynamic interactions between brain function and cognition. Doing so requires accurate encoding of their multidimensional relationship while accounting for individual variability over time. For this purpose, we propose an unsupervised learning model (called \underline{\textbf{Co}}ntrastive Learning-based \underline{\textbf{Gra}}ph Generalized \underline{\textbf{Ca}}nonical Correlation Analysis (CoGraCa)) that encodes their relationship via Graph Attention Networks and generalized Canonical Correlational Analysis. To create brain-cognition fingerprints reflecting unique neural and cognitive phenotype of each person, the model also relies on individualized and multimodal contrastive learning. We apply CoGraCa to longitudinal dataset of healthy individuals consisting of resting-state functional MRI and cognitive measures acquired at multiple visits for each participant. The generated fingerprints effectively capture significant individual differences and outperform current single-modal and CCA-based multimodal models in identifying sex and age. More importantly, our encoding provides interpretable interactions between those two modalities.