Forecasting Brain Activity Based on Models of Spatio-Temporal Brain Dynamics: A Comparison of Graph Neural Network Architectures

TL;DR

This paper compares various spatio-temporal graph neural network architectures for modeling neural activity in fMRI data, demonstrating their robustness and potential for multi-modal brain connectivity analysis.

Contribution

It introduces a systematic comparison of GNN architectures for brain activity modeling and highlights their advantages over traditional VAR models in scalability and multi-modal integration.

Findings

GNNs outperform VAR models in modeling neural dynamics.

GNNs scale effectively to large brain networks with limited data.

Incorporating anatomical connectivity enhances directed connectivity analysis.

Abstract

Comprehending the interplay between spatial and temporal characteristics of neural dynamics can contribute to our understanding of information processing in the human brain. Graph neural networks (GNNs) provide a new possibility to interpret graph structured signals like those observed in complex brain networks. In our study we compare different spatio-temporal GNN architectures and study their ability to model neural activity distributions obtained in functional MRI (fMRI) studies. We evaluate the performance of the GNN models on a variety of scenarios in MRI studies and also compare it to a VAR model, which is currently often used for directed functional connectivity analysis. We show that by learning localized functional interactions on the anatomical substrate, GNN based approaches are able to robustly scale to large network studies, even when available data are scarce. By including anatomical connectivity as the physical substrate for information propagation, such GNNs also provide a multi-modal perspective on directed connectivity analysis, offering a novel possibility to investigate the spatio-temporal dynamics in brain networks.