Exploring Multiconnectivity and Subdivision Functions of Brain Network via Heterogeneous Graph Network for Cognitive Disorder Identification

• Published in: IEEE transaction on neural networks and learning systems Vol. 36; no. 7; pp. 12400 - 12414
• Main Authors: Chen, Dongdong, Liu, Mengjun, Shen, Zhenrong, Yao, Linlin, Zhao, Xiangyu, Song, Zhiyun, Yuan, Haolei, Wang, Qian, Zhang, Lichi
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.07.2025
• Subjects: Algorithms; Alzheimer Disease; Brain; Brain - diagnostic imaging; Brain - physiopathology; Brain modeling; Brain network analysis; Cause effect analysis; Cognition Disorders - diagnosis; Cognition Disorders - diagnostic imaging; Cognition Disorders - physiopathology; Cognitive processes; Feature extraction; Functional magnetic resonance imaging; graph neural network (GNN); Graph neural networks; heterogeneous graph; Humans; Magnetic Resonance Imaging; Models, Neurological; Nerve Net - diagnostic imaging; Nerve Net - physiopathology; Network analyzers; Neural Networks, Computer; Neural Pathways - physiopathology; Neurons; self-attention; Vectors
• DOI: 10.1109/TNNLS.2024.3481667
• ISSN: 2162-237X; 2162-2388

Brain serves as a critical cornerstone of human intelligence, which involves a series of complex neuropsychological activities that lead to the coordination of various functions in the brain network. In recent years, brain network analysis methods based on graph neural networks (GNNs) have attracted increasing attention for the identification of brain disorders. However, these methods generally assume that the brain network is a homogeneous graph while ignoring its heterogeneity among human brain activities, which is reflected in both the complex connectivity of the brain network and distinctive brain functions. To overcome this problem, we propose a heterogeneous subdivision GNN (HSGNN), which captures the heterogeneous connections and functions of the brain network simultaneously. Specifically, we first employ two fundamental brain connectivity patterns to capture both statistical dependency and directional information flow among different brain regions and construct a heterogeneous brain connectivity network for each subject. Then, we develop a functional subdivision method that encodes brain networks into multiple latent feature subspaces corresponding to heterogeneous brain functions and extracts features of brain networks accordingly. Considering the intricate interactions of brain functions to facilitate cognitive activities within the brain network, we further employ the self-attention mechanism to obtain comprehensive representations of brain networks in a joint latent space. Finally, we propose a composite loss function to train the model for obtaining the heterogeneous brain network representation, which can be utilized for disease classification. The experimental results in the Alzheimer's Disease Neuroimaging Initiative (ADNI) and Autism Brain Imaging Data Exchange (ABIDE) datasets demonstrate that our method outperforms several state-of-the-art (SOTA) methods to identify different types of brain cognitive-related disorders.