BrainIB plus plus : Leveraging graph neural networks and information bottleneck for functional brain biomarkers in schizophrenia

	BrainIB plus plus : Leveraging graph neural networks and information bottleneck for functional brain biomarkers in schizophrenia
	Hu, TZ; Li, Q; Liu, S; Calhoun, VD; van Wingen, G; Yu, SJ
	2026
发表期刊	Biomed. Signal Process. Control
ISSN	1746-8094
卷号	112
摘要	The development of diagnostic models is gaining traction in the field of psychiatric disorders. Recently, machine learning classifiers based on resting-state functional magnetic resonance imaging (rs-fMRI) have been developed to identify brain biomarkers that differentiate psychiatric disorders from healthy controls. However, conventional machine learning-based diagnostic models often depend on extensive feature engineering, which introduces bias through manual intervention. While deep learning models are expected to operate without manual involvement, their lack of interpretability poses significant challenges in obtaining explainable and reliable brain biomarkers to support diagnostic decisions, ultimately limiting their clinical applicability. In this study, we introduce an end-to-end innovative graph neural network framework named BrainIB++, which applies the information bottleneck (IB) principle to identify the most informative data-driven brain regions as subgraphs during model training for interpretation. We evaluate the performance of our model against nine established brain network classification methods across three multi-cohort schizophrenia datasets. It consistently demonstrates superior diagnostic accuracy and exhibits generalizability to unseen data. Furthermore, the subgraphs identified by our model also correspond with established clinical biomarkers in schizophrenia, particularly emphasizing abnormalities in the visual, sensorimotor, and higher cognition brain functional network. This alignment enhances the model's interpretability and underscores its relevance for real-world diagnostic applications. The code of our BrainIB++ is available at https://github.com/TianzhengHU/BrainIB_ coding/tree/main/BrainIB_GIB.
收录类别	SCIE
语种	英语
文献类型	期刊论文
条目标识符	http://ir.kiz.ac.cn/handle/152453/14747
专题	科研部门_生物统计与影像遗传（刘书）
推荐引用方式 GB/T 7714	Hu, TZ,Li, Q,Liu, S,et al. BrainIB plus plus : Leveraging graph neural networks and information bottleneck for functional brain biomarkers in schizophrenia[J]. Biomed. Signal Process. Control,2026,112.
APA	Hu, TZ,Li, Q,Liu, S,Calhoun, VD,van Wingen, G,&Yu, SJ.(2026).BrainIB plus plus : Leveraging graph neural networks and information bottleneck for functional brain biomarkers in schizophrenia.Biomed. Signal Process. Control,112.
MLA	Hu, TZ,et al."BrainIB plus plus : Leveraging graph neural networks and information bottleneck for functional brain biomarkers in schizophrenia".Biomed. Signal Process. Control 112(2026).

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2026070601.pdf（2872KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	请求全文