Compact vision language models enable efficient and interpretable optical coherence tomography through layer-specific multimodal learning
By reconciling interpretability with computational efficiency, LO-VLM establishes a paradigm for efficient AI models in OCT interpretation.
Authors
- Theodore Leng (ORCID: https://orcid.org/0000-0002-8461-3562)
- Jared T. Sokol
- Atalie C. Thompson (ORCID: https://orcid.org/0000-0002-2817-6417)
- Hamed Tabkhi (ORCID: https://orcid.org/0000-0001-5420-1121)
- Minhaj Nur Alam (ORCID: https://orcid.org/0000-0003-3095-2232)
- Tania Haghighi
- Jennifer I. Lim
- Sina Gholami
- Aayush Biswas
Institutions
- University of North Carolina at Charlotte (US)
- Atrium Health Wake Forest Baptist (US)
- University of Illinois Chicago (US)
- Stanford University (US)
Publication Details
- Journal
- Communications Medicine
- Published
- 2025-12-27
- DOI
- https://doi.org/10.1038/s43856-025-01293-9
- Primary Topic
- Optical Coherence Tomography Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00