Multimodal Deep Learning Differentiates Papilledema and Non-Arteritic Anterior Ischemic Optic Neuropathy From Healthy Eyes
Combining OCT and fundus photographs improves the classification of IIH, NAION, and healthy eyes, showing the value of using complementary imaging modalities. This approach supports the use of DL to aid diagnosis and clinical management of optic nerve head swelling. It may also be extended to leverage DL from additional data sources, such as macular scans or visual field tests.
Authors
- MICHAEL WALL
- Randy H. Kardon (ORCID: https://orcid.org/0000-0002-3173-7123)
- Brett A. Johnson (ORCID: https://orcid.org/0000-0002-9260-245X)
- Mona K. Garvin (ORCID: https://orcid.org/0000-0003-3299-3150)
- Brian Woods
- Mark J. Kupersmith
- Edward F. Linton (ORCID: https://orcid.org/0000-0001-7058-9576)
- David Szanto (ORCID: https://orcid.org/0000-0002-4640-4655)
- Asala Erekat
- Jui-Kai Wang
Institutions
- University of Iowa (US)
- Ollscoil na Gaillimhe – University of Galway (IE)
- New York Eye and Ear Infirmary (US)
- University of Iowa Hospitals and Clinics (US)
- University Hospital Galway (IE)
- Iowa City VA Health Care System (US)
- The University of Texas Southwestern Medical Center (US)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- Investigative Ophthalmology & Visual Science
- Published
- 2026-01-07
- DOI
- https://doi.org/10.1167/iovs.67.1.12
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- U.S. Department of Veterans Affairs
- Research to Prevent Blindness
- Office of Research and Development
- New York Eye and Ear Infirmary of Mount Sinai
- National Institutes of Health
- National Eye Institute
- National Center for Advancing Translational Sciences