AUTHOR=Wang Donglin , Wu Qiang , Hong Don TITLE=Extracting default mode network based on graph neural network for resting state fMRI study JOURNAL=Frontiers in Neuroimaging VOLUME=Volume 1 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/neuroimaging/articles/10.3389/fnimg.2022.963125 DOI=10.3389/fnimg.2022.963125 ISSN=2813-1193 ABSTRACT=Functional magnetic resonance imaging (fMRI)-based study for the functional connections in the brain has been highlighted by numerous human and animal studies recently, which have provided significant information to explain a wide range of pathological conditions and behavioral characteristics. In this paper, we propose the use of graph neural network, a deep learning technique called graphSAGE, to investigate resting state fMRI (rs-fMRI) and extract the default mode network (DMN). Comparing typical methods such as seed-based correlation, the independent component analysis, and the dictionary learning, the real data experiment results showed that the graphSAGE is more robust, reliable and defines more clear region of interests. In addition, the graphSAGE requires less and more relaxing assumptions, as well as considers the single subject analysis and group subjects analysis simultaneously.