Federated Multi-Task Learning for Joint Diagnosis of Multiple Mental Disorders on MRI Scans

• Published in: IEEE transactions on biomedical engineering Vol. 70; no. 4; pp. 1 - 12
• Main Authors: Huang, Zhi-An, Hu, Yao, Liu, Rui, Xue, Xiaoming, Zhu, Zexuan, Song, Linqi, Tan, Kay Chen
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.04.2023; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Attention deficit hyperactivity disorder; Autism; autism spectrum disorder; Autism Spectrum Disorder - diagnostic imaging; Biomarkers; Data models; Datasets; Deep learning; Diagnosis; domain shift; Feature extraction; Federated multi-task learning; Functional magnetic resonance imaging; Humans; joint diagnosis; Machine learning; Magnetic Resonance Imaging; Medical diagnostic imaging; Medical imaging; Mental disorders; Mental Disorders - diagnostic imaging; Multitasking; Optimization; Phenotypes; Privacy; Schizophrenia; Task analysis; Training

Objective: Deep learning (DL) techniques have been introduced to assist doctors in the interpretation of medical images by detecting image-derived phenotype abnormality. Yet the privacy-preserving policy of medical images disables the effective training of DL model using sufficiently large datasets....