Community-Aware Transformer for Autism Prediction in fMRI Connectome

TL;DR

This paper introduces Com-BrainTF, a hierarchical transformer model that incorporates community awareness in fMRI connectome analysis to improve autism spectrum disorder prediction, outperforming existing methods.

Contribution

The paper proposes a novel community-aware hierarchical transformer architecture that learns intra- and inter-community node embeddings for ASD diagnosis, addressing limitations of previous models.

Findings

Outperforms state-of-the-art models on ABIDE dataset

Provides high interpretability through attention mechanisms

Effectively models community-specific brain interactions

Abstract

Autism spectrum disorder(ASD) is a lifelong neurodevelopmental condition that affects social communication and behavior. Investigating functional magnetic resonance imaging (fMRI)-based brain functional connectome can aid in the understanding and diagnosis of ASD, leading to more effective treatments. The brain is modeled as a network of brain Regions of Interest (ROIs), and ROIs form communities and knowledge of these communities is crucial for ASD diagnosis. On the one hand, Transformer-based models have proven to be highly effective across several tasks, including fMRI connectome analysis to learn useful representations of ROIs. On the other hand, existing transformer-based models treat all ROIs equally and overlook the impact of community-specific associations when learning node embeddings. To fill this gap, we propose a novel method, Com-BrainTF, a hierarchical local-global transformer architecture that learns intra and inter-community aware node embeddings for ASD prediction task. Furthermore, we avoid over-parameterization by sharing the local transformer parameters for different communities but optimize unique learnable prompt tokens for each community. Our model outperforms state-of-the-art (SOTA) architecture on ABIDE dataset and has high interpretability, evident from the attention module. Our code is available at https://github.com/ubc-tea/Com-BrainTF.