Learning the Hierarchical Organization in Brain Network for Brain Disorder Diagnosis

TL;DR

This paper introduces BrainHO, a hierarchical learning model for brain network analysis that captures complex connectivity patterns without relying on predefined sub-networks, leading to improved disorder diagnosis and interpretable biomarkers.

Contribution

BrainHO is the first method to learn hierarchical brain network dependencies directly from data, using a novel attention mechanism and constraints to improve interpretability and diagnostic accuracy.

Findings

Achieves state-of-the-art classification accuracy on ABIDE and REST-meta-MDD datasets.

Uncovers clinically meaningful brain sub-networks related to disorders.

Provides interpretable biomarkers for brain disorder diagnosis.

Abstract

Brain network analysis based on functional Magnetic Resonance Imaging (fMRI) is pivotal for diagnosing brain disorders. Existing approaches typically rely on predefined functional sub-networks to construct sub-network associations. However, we identified many cross-network interaction patterns with high Pearson correlations that this strict, prior-based organization fails to capture. To overcome this limitation, we propose the Brain Hierarchical Organization Learning (BrainHO) to learn inherently hierarchical brain network dependencies based on their intrinsic features rather than predefined sub-network labels. Specifically, we design a hierarchical attention mechanism that allows the model to aggregate nodes into a hierarchical organization, effectively capturing intricate connectivity patterns at the subgraph level. To ensure diverse, complementary, and stable organizations, we incorporate an orthogonality constraint loss, alongside a hierarchical consistency constraint strategy, to refine node-level features using high-level graph semantics. Extensive experiments on the publicly available ABIDE and REST-meta-MDD datasets demonstrate that BrainHO not only achieves state-of-the-art classification performance but also uncovers interpretable, clinically significant biomarkers by precisely localizing disease-related sub-networks.