Toward neuroimaging-based diagnostic support: a deep learning approach with a closed-loop system for psychiatric classification.
Authors
Affiliations (8)
Affiliations (8)
- Shanghai Mental Health Center, Shanghai Jiao Tong University School of Medicine, Shanghai 200030, China.
- Institute of Psychological and Behavioral Science, Shanghai Jiao Tong University, Shanghai 200030, China.
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai 200030, China.
- School of Biomedical Engineering, Shanghai Technology University, Shanghai 201210, China.
- United Imaging Intelligence, Shanghai 200030, China.
- Harvard Medical School, Boston, MA 02115, USA.
- Beijing Key Laboratory of Mental Disorders, National Clinical Research Center for Mental Disorders & National Center for Mental Disorders, Beijing Anding Hospital, Capital Medical University, Beijing 100088, China.
- Advanced Innovation Center for Human Brain Protection, Capital Medical University, Beijing 100088, China.
Abstract
While neuroimaging offers valuable insights into brain alterations associated with psychiatric disorders, its translation into routine clinical practice remains challenging. we developed the patch-based hierarchical network (PHN), a deep learning framework for classifying multiple psychiatric disorders from structural MRI. Trained on a large, curated dataset (<i>n</i> = 2,490) of four major disorders and controls, the PHN's generalizability was confirmed on independent research datasets (<i>n</i> = 1,346) and real-world clinical data (<i>n</i> = 344). The model demonstrated robust performance, showing promise in real-world evaluations by reflecting complex presentations such as comorbidities. A key contribution is the implementation and deployment of a closed-loop, neuroimaging-based diagnostic support system integrating the PHN into an active clinical workflow. This work provides a tangible step toward bridging the research-to-practice gap, leveraging artificial intelligence to provide objective support for psychiatric diagnosis.