Leveraging Brain Modularity Prior for Interpretable Representation Learning of fMRI

• Published in: IEEE transactions on biomedical engineering Vol. 71; no. 8; pp. 2391 - 2401
• Main Authors: Wang, Qianqian, Wang, Wei, Fang, Yuqi, Yap, Pew-Thian, Zhu, Hongtu, Li, Hong-Jun, Qiao, Lishan, Liu, Mingxia
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2024; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adult; Algorithms; Autism; Biomarker; Biomarkers; Biomedical engineering; Brain; Brain - diagnostic imaging; Brain - physiology; brain disorder; Brain mapping; Brain Mapping - methods; Brain modeling; brain modularity; Cognition; Constraints; Deep learning; Female; Functional magnetic resonance imaging; functional MRI; Graph neural networks; Graphical representations; Humans; Image Processing, Computer-Assisted - methods; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Modular structures; Modularity; Modules; Network topologies; Network topology; Neural networks; Neural Networks, Computer; Neuroimaging; Representation learning; Topology

Resting-state functional magnetic resonance imaging (rs-fMRI) can reflect spontaneous neural activities in the brain and is widely used for brain disorder analysis. Previous studies focus on extracting fMRI representations using machine/deep learning methods, but these features typically lack biolog...