A03Extraction of versatile features from resting state fMRI using deep neural networks

 In this research project, we investigate a novel technique for extracting versatile features reflecting neurophysiological and cognitive characteristics from resting state functional magnetic resonance imaging (rsfMRI) data using deep neural networks. rsfMRI is a functional brain imaging method for evaluating regional interactions (functional connectivity: FC) that occur when a subject is not performing an explicit task. Resting state FC analysis provides useful information corresponding to the functional organization of individuals’ brain in healthy subjects, neurological or psychiatric disorder patients. However, even though rsfMRI includes a lot of temporal information, methods for extracting useful information with temporal dynamics of rsfMRI remains unestablished yet. In order to address this issue, in the current project, we investigate a novel technique for extracting self-organized versatile features reflecting neurophysiological and cognitive characteristics from rsfMRI data using deep neural networks. We expect that these extracted features could reflect individual’s brain states which are useful for the evaluation and treatment of psychiatric disorders. The proposed technique could be one of the base technologies of examination and evaluation for psychiatric disorders.