Dementia analysis from functional connectivity network with graph neural networks. Issue 3 (May 2022)

• Record Type: Journal Article
• Authors: Wang, Lujing; Yuan, Weifeng; Zeng, Lu; Xu, Jie; Mo, Yujie; Zhao, Xinxiang; Peng, Liang
• Is Part Of: Information processing & management. Volume 59:Issue 3(2022)
• Publication Date: 2022-05
• Subjects: Brain Functional Connectivity -- Graph neural networks -- Structure learning -- Self-attention -- Feature selection; Information storage and retrieval systems -- Periodicals; Information science -- Periodicals; Systèmes d'information -- Périodiques; Sciences de l'information -- Périodiques; Information science; Information storage and retrieval systems; Periodicals; 658.4038
• DOI: 10.1016/j.ipm.2022.102901
• Languages: English
• ISSNs: 0306-4573

Abstract

Abstract: Deep learning methods have been widely applied for disease diagnosis on resting-state fMRI (rs-fMRI) data, but they are incapable of investigating global relationships between different brain regions as well as ignoring the interpretability. To address these issues, this paper presents a new graph neural network framework for brain disease diagnosis via jointly learning global relationships and selecting the most discriminative brain regions. Specifically, we first design a self-attention structure learning to capture the global interactions between brain regions for achieving diagnosis effectiveness, and theoretically integrate a feature selection method to reduce the noise influence as well as achieve interpretability. Experiment results on three neurological diseases datasets show the effectiveness of our method, compared to the comparison methods, in terms of diagnostic performance and interpretability. Highlights: A novel framework with self-attention structure learning to characterize the relations among the brain regions. Our model can provide an interpretable result, which has substantial clinical implications for brain disease diagnosis. This paper is the first effort that jointly learns deep graph learning and selects discriminative brain regions.