Journal Article

Multi-channel spatio-temporal graph attention contrastive network for brain disease diagnosis

Wang, Ran, Zhang, Daoqiang, Ma, Kai, Meng, Xiangshui, Li, Shengrong, Zhu, Qi, Li, Chaojun

2025

Overview

Dynamic brain networks (DBNs) can capture the intricate connections and temporal evolution among brain regions, becoming increasingly crucial in the diagnosis of neurological disorders. However, most existing researches tend to focus on isolated brain network sequence segmented by sliding windows, and they are difficult to effectively uncover the higher-order spatio-temporal topological pattern in DBNs. Meantime, it remains a challenge to utilize the structure connectivity prior in the DBNs analysis. To address these problems, we propose a multi-channel spatio-temporal graph attention contrastive network for DBNs analysis. Specifically, we first construct dynamic brain functional networks from fMRI data with sliding windows, and embed the structural connectivity derived from diffusion tensor imaging (DTI) to the dynamic functional connectivity graph representation to construct multi-modal brain network. Second, we develop a multi-channel spatial attention contrastive network to extract topological features from the brain network within each time window. This network incorporates an intra-window graph contrastive constraint to enhance the discriminative ability of the extracted features. Moreover, temporal dependencies across windows are captured by integrating feature embeddings through a self-attention mechanism, and the inter-window recurrent contrastive constraint is devised to extract higher-order spatio-temporal topological features. Finally, a multi-layer perceptron (MLP) is used to classify the brain networks. Experiments on epilepsy and ADNI datasets show that our method outperforms several state-of-the-art approaches in diagnosing performance, and it provides discriminative graph features for related brain diseases. •A deep graph model is introduced for DBNs analysis, enabling higher-order spatio-temporal information propagation.•A multi-modal method integrates structural and functional brain connectivity into a unified graph representation.•A graph attention network with contrastive loss improves spatio-temporal feature discrimination.•Our method outperforms state-of-the-art approaches on epilepsy and ADNI datasets, and demonstrates potential in identifying neurological biomarkers.

• Publisher: Elsevier Inc,Elsevier Limited,Elsevier
• Subject: Adult / Attention / Brain - diagnostic imaging / Brain - physiopathology / Brain disease diagnosis / Brain Diseases - diagnostic imaging / Brain Diseases - physiopathology / Brain mapping / Connectome - methods / Diagnosis / Diffusion Tensor Imaging - methods / Dynamic brain networks / Epilepsy / Female / Functional magnetic resonance imaging / Graph contrastive learning / Graph representations / Humans / Magnetic Resonance Imaging - methods / Male / Nerve Net - diagnostic imaging / Nerve Net - physiopathology / Neural networks / Neuroimaging / Neurological diseases / Radiology/Diagnostic Imaging / Spatio-temporal features / Structure-function relationships