A vision–language foundation model for Alzheimer's disease diagnosis using MRI and clinical data
A novel vision-language foundation model (Alzheimer's Disease Language and Image Pre-Training [ADLIP]) integrates 3D magnetic resonance imaging and clinical text for Alzheimer's disease diagnosis. ADLIP enables zero-shot prediction of unseen data and cognitive scores without task-specific fine-tuning. The model demonstrates strong generalizability across racially diverse cohorts, supporting equitable clinical use. Longitudinal evaluation shows alignment with disease progression, highlighting utility for monitoring applications.
Authors
- Zhaowei Jiang
- Peng Lin (ORCID: https://orcid.org/0000-0002-3863-5541)
- Liqi Shu (ORCID: https://orcid.org/0000-0002-9784-8475)
- Yingxu Liu (ORCID: https://orcid.org/0000-0002-5053-4911)
- Jinyao Sun
- Yining Qi (ORCID: https://orcid.org/0009-0001-3685-5989)
- Mingyang Xia
- for the Health and Aging Brain Study (HABS‐HD) Study Team Alzheimer's Disease Neuroimaging Initiative
- Shuo Ni
- Arthur W. Toga
- Wei Li
Institutions
- University of Southern California (US)
- University of Pittsburgh (US)
- Chinese Academy of Sciences (CN)
- Brown University (US)
- Shandong Institute of Automation (CN)
- Tsinghua University (CN)
Publication Details
- Journal
- Alzheimer s & Dementia
- Published
- 2025-12-01
- DOI
- https://doi.org/10.1002/alz.71029
- Citations
- 1
- Primary Topic
- Dementia and Cognitive Impairment Research
- Type
- article
- Field-Weighted Citation Impact
- 1.47
Funders
- U.S. Department of Defense
- National Institutes of Health
- NIH Office of the Director