Clustering of Brain Function Network Based on Attribute and Structural Information and Its Application in Brain Diseases

• Published in: Frontiers in neuroinformatics Vol. 13; p. 79
• Main Authors: Cui, Xiaohong, Xiao, Jihai, Guo, Hao, Wang, Bin, Li, Dandan, Niu, Yan, Xiang, Jie, Chen, Junjie
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 07.02.2020; Frontiers Media S.A
• Subjects: Alzheimer's disease; Bipolar disorder; Brain diseases; Brain mapping; Brain research; Clustering; Datasets; Functional magnetic resonance imaging; graph mining; Labeling; Medical imaging; Mental disorders; Methods; Neurodegenerative diseases; Neuroimaging; Neuroscience; Researchers; Schizophrenia; similarity; spectral clustering; Studies; sub-network kernels; Time series; graph mining; Alzheimer's disease; similarity; spectral clustering; sub-network kernels
• DOI: 10.3389/fninf.2019.00079
• ISSN: 1662-5196

At present, the diagnosis of brain disease is mainly based on the self-reported symptoms and clinical signs of the patient, which can easily lead to psychiatrists' bias. The purpose of this study is to develop a brain network clustering model to accurately identify brain diseases based on resting state functional magnetic resonance imaging (fMRI) in the absence of clinical information. We use cosine similarity and sub-network kernels to measure attribute similarity and structure similarity, respectively. By integrating the structure similarity and attribute similarity into one matrix, spectral clustering is used to achieve brain network clustering. Finally, we evaluate this method on three diseases: Alzheimer's disease, Bipolar disorder patients, and Schizophrenia. The performance of methods is evaluated by measuring clustering consistency. Clustering consistency is similar to clustering accuracy, which is used to evaluate the consistency between the clustering labels and clinical diagnostic labels of the subjects. The experimental results show that our proposed method can significantly improve clustering performance, with a consistency of 60.6% for Alzheimer's disease, with a consistency of 100% for Schizophrenia, with a consistency of 100% for Bipolar disorder patients.