Uncertainty-Aware Training for Ophthalmic Segmentation Using MedSAM
UAT uses interpretable uncertainty maps to enhance DL segmentation performance. Its lightweight integration makes it practical for adoption and leads to improved model performance on ophthalmic segmentation tasks.
Authors
- Yoga Advaith Veturi (ORCID: https://orcid.org/0000-0001-6158-8408)
- Praveer Singh (ORCID: https://orcid.org/0000-0001-6641-2030)
- Giacomo Nebbia (ORCID: https://orcid.org/0000-0002-4766-6278)
- Scott Kinder
- Malik Y. Kahook
- Christopher William Clark
- Steven McNamara
- Jayashree Kalpathy-Cramer
- Niranjan Manoharan
- Talisa Forest
Institutions
- University of Colorado Denver (US)
Publication Details
- Journal
- Translational Vision Science & Technology
- Published
- 2026-02-17
- DOI
- https://doi.org/10.1167/tvst.15.2.19
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Research to Prevent Blindness
- Regeneron Pharmaceuticals
- European Commission
- Genentech
- HORIZON EUROPE Framework Programme