精神分裂症分类的图神经网络和多模态DTI特征
北京大学研究团队报道了精神分裂症分类的图神经网络和多模态DTI特征。这一研究成果于2025年3月18日发表在国际顶尖学术期刊《神经科学通报》上。
精神分裂症（SZ）是一种严重的精神疾病。本研究将扩散张量成像（DTI）数据与图神经网络相结合用于SZ患者与正常对照（NCs）的区分，并展示了结合分数各向异性和纤维数脑网络特征的图神经网络的优越性能，区分SZ患者与NCs的准确率达到73.79%。他们的研究超越了单纯的区分，通过可解释模型分析和基因表达分析，深入探讨了利用脑白质网络特征识别SZ患者的优势。这些分析揭示了脑成像标记物和遗传生物标记物之间复杂的相互关系，为SZ的神经病理学基础提供了新的见解。总之，他们的发现强调了图神经网络应用于多模态DTI数据的潜力，通过对神经成像和遗传特征的综合分析来增强SZ检测。
附：英文原文
Title: Graph Neural Networks and Multimodal DTI Features for Schizophrenia Classification: Insights from Brain Network Analysis and Gene Expression
Author: Gao, Jingjing, Tang, Heping, Wang, Zhengning, Li, Yanling, Luo, Na, Song, Ming, Xie, Sangma, Shi, Weiyang, Yan, Hao, Lu, Lin, Yan, Jun, Li, Peng, Song, Yuqing, Chen, Jun, Chen, Yunchun, Wang, Huaning, Liu, Wenming, Li, Zhigang, Guo, Hua, Wan, Ping, Lv, Luxian, Yang, Yongfeng, Wang, Huiling, Zhang, Hongxing, Wu, Huawang, Ning, Yuping, Zhang, Dai, Jiang, Tianzi
Issue&Volume: 2025-03-18
Abstract: Schizophrenia (SZ) stands as a severe psychiatric disorder. This study applied diffusion tensor imaging (DTI) data in conjunction with graph neural networks to distinguish SZ patients from normal controls (NCs) and showcases the superior performance of a graph neural network integrating combined fractional anisotropy and fiber number brain network features, achieving an accuracy of 73.79% in distinguishing SZ patients from NCs. Beyond mere discrimination, our study delved deeper into the advantages of utilizing white matter brain network features for identifying SZ patients through interpretable model analysis and gene expression analysis. These analyses uncovered intricate interrelationships between brain imaging markers and genetic biomarkers, providing novel insights into the neuropathological basis of SZ. In summary, our findings underscore the potential of graph neural networks applied to multimodal DTI data for enhancing SZ detection through an integrated analysis of neuroimaging and genetic features.
DOI: 10.1007/s12264-025-01385-5
Source: Graph Neural Networks and Multimodal DTI Features for Schizophrenia Classification: Insights from Brain Network Analysis and Gene Expression | Neuroscience Bulletin