Enhanced multimodal MRI classification of schizophrenia through cross-attention graph neural networks.

Jing-Jing Gao J. Wu Mao-Min Qian Zhengning Wang Yanling Li Na Luo Xin Dai Weiyang Shi Peng Li Jun Chen Yunchun Chen Huaning Wang Wenming Liu Zhigang Li Yongfeng Yang Hua Guo P. Wan Luxian Lv Lin Lu Jun Yan Yuqing Song Huiling Wang Hongxing Zhang Yuhui Du Yuqi Cheng Jian Xu Xiufeng Xu Dai Zhang Tianzai Jiang

Jul 2026 · Medical Image Analysis · Vol 113, pp. 104218 · 0 citations · 67 references

Medicine

Abstract

We propose TB-GCAN, a tri-branch cross-attention graph neural network for schizophrenia classification using multimodal MRI, including sMRI, fMRI, and DTI. Built on a multi-site dataset of 1191 samples from seven scanning sites, the model exploits atlas-defined one-to-one anatomical correspondence across modalities to enable node-level cross-attention during intermediate representation learning. In 7-site leave-one-site-out evaluation, TB-GCAN achieved 84.63% accuracy and outperformed GAT, GCN, CNN, SVM, and MMGNN in the tri-modal setting. Attention-based region ranking highlighted biologically plausible schizophrenia-related regions, and downstream analyses linked the learned imaging representations to PANSS dimensions and transcriptional programs. Unlike generic multimodal GNNs that learn cross-modal relations from data, TB-GCAN directly leverages atlas-aligned regional correspondence to perform anatomically constrained node-level interaction. These findings indicate that anatomically grounded node-level multimodal fusion can improve classification performance while preserving neurobiological interpretability, thereby providing a principled framework for multimodal schizophrenia classification and biomarker discovery.

DOI PubMed Semantic Scholar

View source