BrainSTR: Spatio-Temporal Contrastive Learning for Interpretable Dynamic Brain Network Modeling

TL;DR

BrainSTR is a novel spatio-temporal contrastive learning framework that enhances interpretability of dynamic brain networks by identifying critical phases and disease-related connectivity patterns for neuropsychiatric diagnosis.

Contribution

It introduces a data-driven adaptive phase partition, attention-based critical phase detection, and a contrastive learning approach for more interpretable and discriminative brain network modeling.

Findings

Validated on ASD, BD, and MDD datasets with improved diagnosis accuracy.

Discovered critical phases and subnetworks aligning with neuroimaging findings.

Provides interpretable evidence for disease signatures in brain connectivity.

Abstract

Dynamic functional connectivity captures time-varying brain states for better neuropsychiatric diagnosis and spatio-temporal interpretability, i.e., identifying when discriminative disease signatures emerge and where they reside in the connectivity topology. Reliable interpretability faces major challenges: diagnostic signals are often subtle and sparsely distributed across both time and topology, while nuisance fluctuations and non-diagnostic connectivities are pervasive. To address these issues, we propose BrainSTR, a spatio-temporal contrastive learning framework for interpretable dynamic brain network modeling. BrainSTR learns state-consistent phase boundaries via a data-driven Adaptive Phase Partition module, identifies diagnostically critical phases with attention, and extracts disease-related connectivity within each phase using an Incremental Graph Structure Generator regularized by binarization, temporal smoothness, and sparsity. Then, we introduce a spatio-temporal supervised contrastive learning approach that leverages diagnosis-relevant spatio-temporal patterns to refine the similarity metric between samples and capture more discriminative spatio-temporal features, thereby constructing a well-structured semantic space for coherent and interpretable representations. Experiments on ASD, BD, and MDD validate the effectiveness of BrainSTR, and the discovered critical phases and subnetworks provide interpretable evidence consistent with prior neuroimaging findings. Our code: https://anonymous.4open.science/r/BrainSTR1.