Brain functional connectivity analysis based on multi-graph fusion

• Published in: Medical image analysis Vol. 71; p. 102057
• Main Authors: Gan, Jiangzhang, Peng, Ziwen, Zhu, Xiaofeng, Hu, Rongyao, Ma, Junbo, Wu, Guorong
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.07.2021; Elsevier BV
• Subjects: Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Brain; Brain - diagnostic imaging; Brain functional connectivity network analysis; Brain Mapping; Classification; Connectivity analysis; Data fusion; Dementia disorders; Diagnosis; Feature selection; fMRI data; Frontotemporal dementia; Functional magnetic resonance imaging; Graph theory; Heterogeneity; Humans; Magnetic Resonance Imaging; Medical diagnosis; Neural networks; Neurodegenerative diseases; Neuroimaging; Obsessive compulsive disorder; Data fusion; Brain functional connectivity network analysis; Feature selection; fMRI data; Classification
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2021.102057

•The paper proposes a novel multi-graph fusion method to fuse FCNs and automatically learn the connections of brain regions.•The proposed framework employs L1SVM to integrate the disease diagnosis and related brain regions selection in a unified framework. It is noteworthy that previous methods focused on separately conducting brain regions selection and disease diagnosis. [Display omitted] In this paper, we propose a framework for functional connectivity network (FCN) analysis, which conducts the brain disease diagnosis on the resting state functional magnetic resonance imaging (rs-fMRI) data, aiming at reducing the influence of the noise, the inter-subject variability, and the heterogeneity across subjects. To this end, our proposed framework investigates a multi-graph fusion method to explore both the common and the complementary information between two FCNs, i.e., a fully-connected FCN and a 1 nearest neighbor (1NN) FCN, whereas previous methods only focus on conducting FCN analysis from a single FCN. Specifically, our framework first conducts the graph fusion to produce the representation of the rs-fMRI data with high discriminative ability, and then employs the L1SVM to jointly conduct brain region selection and disease diagnosis. We further evaluate the effectiveness of the proposed framework on various data sets of the neuro-diseases, i.e., Fronto-Temporal Dementia (FTD), Obsessive-Compulsive Disorder (OCD), and Alzheimers Disease (AD). The experimental results demonstrate that the proposed framework achieves the best diagnosis performance via selecting reasonable brain regions for the classification tasks, compared to state-of-the-art FCN analysis methods.