Multi view graph learning improves brain disorder detection from fMRI data
MCDA: Multi-View Graph Contrastive Learning with Dynamic Topology Augmentation for Functional MRI Analysis
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Resting-state fMRI helps doctors study brain disorders without surgery by measuring brain activity. The paper presents MCDA, a new technique to analyze brain connectivity better by creating and comparing multiple versions of brain network graphs. This approach updates its network views dynamically to capture both individual brain patterns and differences between people. The method showed improved accuracy in diagnosing brain disorders across two large datasets.
What this means in practice
- •For clinical neuroimaging teams: Improve diagnosis accuracy of brain disorders by analyzing fMRI connectivity patterns with dynamic multi-view graph learning.
- •For medical ai developers: Develop advanced neurodiagnostic tools that use dynamic topology augmented graph learning to detect brain disorders from fMRI data.$Commercial implications: Enables building superior diagnostic software products targeting hospitals and clinical research centers with enhanced accuracy from fMRI analysis.
Authors
Hao Zhang, Xiaoyun Liu, Shuo Huang, Yue Ma, Liang Cao, Mingxia Liu, Li Zhang
Abstract
Resting-state fMRI (rs-fMRI) is a vital non-invasive tool for diagnosing brain disorders and uncovering pathological mechanisms. However, existing graph contrastive learning (GCL) methods often underexploit augmentation histories across training epochs and the relationships among different augmented views. In this paper, we introduce a topology-guided Multi-view graph Contrastive learning framework with Dynamic graph topology Augmentation (MCDA) for fMRI analysis. Unlike traditional GCL that uses fixed noise or edge-dropping, MCDA employs a Dynamic Augmentation Update (DAU) module that iteratively refines the augmented topology. Specifically, we incorporate self-aware and cross-sample augmentation strategies to simultaneously capture individual-specific functional signatures and inter-subject heterogeneity. We then design a topology-guided multi-view graph contrastive learning scheme that explores interrelationships not only between the original network and its augmented views, but also across different augmented views to maximize structural information preservation. We characterize the score-level optimization directions and establish a lower bound for the contrastive objective. The framework combines classification and contrastive losses for brain disorder diagnosis and examines discriminative functional connectivity patterns as potential biomarkers. Experiments on two public rs-fMRI datasets comprising 1,236 subjects demonstrate that MCDA outperforms the state-of-the-art methods. The code has been made publicly available at: \url{https://github.com/goodcodingagoodboy/MCDA}.