Spatio-temporal deep learning method for ADHD fMRI classification

Zhenyu Mao, Yi Su, Guangquan Xu, Xueping Wang, Yu Huang, Weihua Yue, Li Sun, Naixue Xiong

Abstract: Highlights•Fusing spatial and temporal features is effective in fMRI classification.•Models considering sequence achieve better results than timing invariant models.•fMRI scans longer than one minute contain enough information for ADHD diagnosis.•deep-learned features outperform hand-crafted features in fMRI analysis.