Multimodal Deep Learning Differentiates Papilledema and Non-Arteritic Anterior Ischemic Optic Neuropathy From Healthy Eyes
Investigative Ophthalmology & Visual Science · 2026
DOI: 10.1167/iovs.67.1.12 ↗At a glance
Journal article in Investigative Ophthalmology & Visual Science, 2026. Written by David Szanto and 9 co-authors. Institution: Department of Ophthalmology, New York Eye and Ear Infirmary at Mount Sinai, New York, New York, United States. Major MEDLINE topics: Optic Neuropathy, Ischemic, Papilledema, Deep Learning, Optic Disk. Cited 1 times so far (Crossref); 37 references. The full text is freely available (open access, CC BY 4.0). Funded by: NEI NIH HHS, RRD VA, NCATS NIH HHS.
Abstract (original language)
Purpose
Optic nerve head (ONH) swelling, a critical feature in idiopathic intracranial hypertension (IIH) and non-arteritic anterior ischemic optic neuropathy (NAION), can present diagnostic challenges. We explored a multimodal deep learning (DL) approach integrating optical coherence tomography (OCT) scans and fundus photographs to enhance diagnostic accuracy for differentiating IIH, NAION, and healthy eyes.
Methods
We developed two separate models using 7019 OCT scans (3D-ResNet-18) and 17,657 fundus photos (ResNet-50) to classify eyes with papilledema (2315 OCT, 6349 fundus), NAION (841 OCT, 1814 fundus), and healthy eyes (3863 OCT, 9494 fundus). We arranged the dataset so that the test set consisted entirely of same-day OCT scans and fundus photos, with each modality (OCT and fundus) contributing at least 15% of the data for each class. We combined output probabilities from both models using two methods: an F1-weighted sum by class (F1WS), as well as an XGBoost model. Performance of each was evaluated with AUC-ROC, accuracy, precision, recall, and F1 scores.
Results
The OCT model alone achieved a test accuracy of 93.5%, with the fundus photo model reaching 93.9%. The multimodal F1WS and XGBoost models achieved an accuracy of 97.5% and 98.3%, respectively.
Conclusions
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.
Subjects
MeSH terms (MEDLINE)
Authors and institutions
- Department of Ophthalmology, New York Eye and Ear Infirmary at Mount Sinai, New York, New York, United States.
- Department of Neurology, Icahn School of Medicine at Mount Sinai, New York, New York, United States.
- Irish Clinical Academic Training Programme, Department of Ophthalmology, Galway University Hospital, Galway, Ireland.
- Physics Department, School of Natural Sciences, University of Galway, Galway, Ireland.
- Department of Ophthalmology, University of Texas Southwestern Medical Center, Dallas, Texas, United States.
- Center for the Prevention and Treatment of Visual Loss, Iowa City VA Health System, Iowa City, Iowa, United States.
Funding
- NEI NIH HHS
- RRD VA
- NCATS NIH HHS
Cite
APA
Szanto, D., Erekat, A., Woods, B., Wang, J. K., Garvin, M., Johnson, B., Kardon, R., Wall, M., Linton, E., & Kupersmith, M. J. (2026). Multimodal Deep Learning Differentiates Papilledema and Non-Arteritic Anterior Ischemic Optic Neuropathy From Healthy Eyes. Investigative Ophthalmology & Visual Science. https://doi.org/10.1167/iovs.67.1.12
Vancouver
Szanto D, Erekat A, Woods B, Wang JK, Garvin M, Johnson B, et al. Multimodal Deep Learning Differentiates Papilledema and Non-Arteritic Anterior Ischemic Optic Neuropathy From Healthy Eyes. Investigative Ophthalmology & Visual Science. 2026. doi:10.1167/iovs.67.1.12
BibTeX
@article{Szanto2026,
author = {Szanto, David and Erekat, Asala and Woods, Brian and Wang, Jui-Kai and Garvin, Mona and Johnson, Brett and Kardon, Randy and Wall, Michael and Linton, Edward and Kupersmith, Mark J},
title = {Multimodal Deep Learning Differentiates Papilledema and Non-Arteritic Anterior Ischemic Optic Neuropathy From Healthy Eyes},
journal = {Investigative Ophthalmology & Visual Science},
year = {2026},
doi = {10.1167/iovs.67.1.12}
}
EUVIMED