Classification of Neuropsychiatric Disorders via Brain-Region-Selected Graph Convolutional Network

Abstract

For the classification of patients with neuropsychiatric disorders based on rs-fMRI data, this paper proposed a Brain-Region-Selected graph convolutional network (BRS-GCN). In order to effectively identify the most significant biomarkers associated with disease, we designed a novel ROI pooling score function. Additionally, we also designed a comprehensive loss function, including a group-level consistency loss function for preserving the same brain regions in subjects of the same category, and an anti-consistency function for maximizing brain region preservation differences between subjects of different categories. On the basis of the ROI graph, we directly incorporate the non-imaging information of the subjects in the network training. Experimental results on two public datasets, ABIDE and ADNI, validate the superiority of the model proposed in this paper, and the qualitative results of the biomarkers demonstrate the potential application of the model in medical diagnosis and treatment of neuropsychiatric disorders.