Hierarchical graph learning with convolutional network for brain disease prediction

• Published in: Multimedia tools and applications Vol. 83; no. 15; pp. 46161 - 46179
• Main Authors: Liu, Tong, Liu, Fangqi, Wan, Yingying, Hu, Rongyao, Zhu, Yongxin, Li, Li
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.05.2024; Springer Nature B.V
• Subjects: Brain; Brain diseases; Classification; Commonality; Computer Communication Networks; Computer Science; Data Structures and Information Theory; Diagnostic systems; Graph representations; Learning; Machine learning; Multimedia; Multimedia Information Systems; Neural networks; Neurological diseases; Neurological disorders; Science; Special Purpose and Application-Based Systems; Track 2: Medical Applications of Multimedia; Functional connectivity; Neurological disorders diagnosis; Graph learning; Graph neural network
• ISSN: 1573-7721; 1380-7501; 1573-7721
• DOI: 10.1007/s11042-023-17187-8

In computer-aided diagnostic systems, the functional connectome approach has become a common method for detecting neurological disorders. However, the existing methods either ignore the uniqueness of different subjects across the functional connectivities or neglect the commonality of the same disease for the functional connectivity of each subject, resulting in a lack of capacity of capturing a comprehensive functional model. To solve the issues, we develop a hierarchical graph learning with convolutional network that not only considers the unique information of each subject, but also takes the common information across subjects into account. Specifically, the proposed method consists of two structures, one is the individual graph model which selects the representative brain regions by combining each subject feature and its related brain region-based graph. The other is the population graph model to directly conduct classification performance by updating the information of each subject which considers both the subject itself and the nearest neighbours. Experimental results indicate that the proposed method on four real datasets outperforms the state-of-the-art approaches.