Performance of vision language models for optic disc swelling identification on fundus photographs
Non-specialty-trained VLMs could classify photographs of swollen and normal optic discs better than chance, with performance varying by model. Increasing prompt complexity did not consistently improve performance. Specialty-specific VLMs may be necessary to improve ophthalmic image analysis performance.
Authors
- Tuan Anh Nguyen (ORCID: https://orcid.org/0000-0002-9528-9278)
- Kelvin Zhenghao Li (ORCID: https://orcid.org/0000-0002-9993-5118)
- Heather E. Moss (ORCID: https://orcid.org/0000-0003-4373-447X)
Institutions
- Nanyang Technological University (SG)
- Tan Tock Seng Hospital (SG)
- University of California, Davis (US)
- Stanford University (US)
Publication Details
- Journal
- Frontiers in Digital Health
- Published
- 2025-08-25
- DOI
- https://doi.org/10.3389/fdgth.2025.1660887
- Citations
- 1
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 1.36
Funders
- Research to Prevent Blindness
- National Institutes of Health