Spatio-Temporal Attention in Multi-Granular Brain Chronnectomes for Detection of Autism Spectrum Disorder

TL;DR

This paper presents IMAGIN, a novel graph neural network model utilizing spatio-temporal attention on multi-granular brain data to improve autism spectrum disorder detection accuracy from rs-fMRI scans.

Contribution

IMAGIN introduces a multi-granular, multi-atlas spatio-temporal attention mechanism for graph-based brain connectivity analysis, outperforming existing methods.

Findings

Achieves 79.25% accuracy in ASD detection

Surpasses state-of-the-art by 1.5%

Provides neural basis validation through attention analysis

Abstract

The traditional methods for detecting autism spectrum disorder (ASD) are expensive, subjective, and time-consuming, often taking years for a diagnosis, with many children growing well into adolescence and even adulthood before finally confirming the disorder. Recently, graph-based learning techniques have demonstrated impressive results on resting-state functional magnetic resonance imaging (rs-fMRI) data from the Autism Brain Imaging Data Exchange (ABIDE). We introduce IMAGIN, a multI-granular, Multi-Atlas spatio-temporal attention Graph Isomorphism Network, which we use to learn graph representations of dynamic functional brain connectivity (chronnectome), as opposed to static connectivity (connectome). The experimental results demonstrate that IMAGIN achieves a 5-fold cross-validation accuracy of 79.25%, which surpasses the current state-of-the-art by 1.5%. In addition, analysis of the spatial and temporal attention scores provides further validation for the neural basis of autism.