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

2026-03-10

AI Summary

This work addresses the challenge of weak and spatiotemporally sparse diagnostic signals in dynamic brain networks, compounded by pervasive confounding connections that hinder model interpretability. To this end, the authors propose BrainSTR, a novel framework that adaptively identifies critical diagnostic time windows through phase segmentation, and leverages an attention mechanism coupled with a structurally constrained incremental graph generator to extract disease-relevant functional connections. For the first time, spatiotemporal supervised contrastive learning is introduced to construct a highly discriminative and interpretable semantic representation space. Experiments on ASD, BD, and MDD datasets demonstrate that the identified critical time windows and subnetworks align well with established neuroimaging evidence, significantly improving both diagnostic accuracy and model interpretability.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• dynamic functional connectivity
• spatio-temporal interpretability
• neuropsychiatric diagnosis
• disease signatures
• brain network modeling

Innovation

• spatio-temporal contrastive learning
• dynamic brain network
• interpretable modeling
• adaptive phase partition
• incremental graph structure