MCDGLN: Masked Connection-based Dynamic Graph Learning Network for Autism Spectrum Disorder

TL;DR

This paper introduces MCDGLN, a novel dynamic graph learning network that captures brain connectivity changes over time, refines connections with task-specific masks, and improves ASD classification accuracy using fMRI data.

Contribution

The paper presents a new dynamic graph learning framework with a weighted edge aggregation and attention-based connection encoding for ASD diagnosis from brain imaging.

Findings

Achieved 73.3% classification accuracy on ABIDE I dataset.

Demonstrated the effectiveness of WEA and ACE modules in improving connectivity analysis.

Provided new insights into ASD-specific brain connectivity features.

Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder characterized by complex physiological processes. Previous research has predominantly focused on static cerebral interactions, often neglecting the brain's dynamic nature and the challenges posed by network noise. To address these gaps, we introduce the Masked Connection-based Dynamic Graph Learning Network (MCDGLN). Our approach first segments BOLD signals using sliding temporal windows to capture dynamic brain characteristics. We then employ a specialized weighted edge aggregation (WEA) module, which uses the cross convolution with channel-wise element-wise convolutional kernel, to integrate dynamic functional connectivity and to isolating task-relevant connections. This is followed by topological feature extraction via a hierarchical graph convolutional network (HGCN), with key attributes highlighted by a self-attention module. Crucially, we refine static functional connections using a customized task-specific mask, reducing noise and pruning irrelevant links. The attention-based connection encoder (ACE) then enhances critical connections and compresses static features. The combined features are subsequently used for classification. Applied to the Autism Brain Imaging Data Exchange I (ABIDE I) dataset, our framework achieves a 73.3\% classification accuracy between ASD and Typical Control (TC) groups among 1,035 subjects. The pivotal roles of WEA and ACE in refining connectivity and enhancing classification accuracy underscore their importance in capturing ASD-specific features, offering new insights into the disorder.