Journal article
Multimodal Deep Learning Differentiates Papilledema and Non-Arteritic Anterior Ischemic Optic Neuropathy From Healthy Eyes
Investigative ophthalmology & visual science, Vol.67(1), 12
01/05/2026
DOI: 10.1167/iovs.67.1.12
PMCID: PMC12798753
PMID: 41533910
Abstract
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.
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.
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.
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.
Details
- Title: Subtitle
- Multimodal Deep Learning Differentiates Papilledema and Non-Arteritic Anterior Ischemic Optic Neuropathy From Healthy Eyes
- Creators
- David Szanto - New York Eye and Ear InfirmaryAsala Erekat - Icahn School of Medicine at Mount SinaiBrian Woods - Ollscoil na Gaillimhe – University of GalwayJui-Kai Wang - The University of Texas Southwestern Medical CenterMona Garvin - University of IowaBrett Johnson - University of IowaRandy Kardon - University of IowaMichael Wall - University of IowaEdward Linton - University of IowaMark J Kupersmith - New York Eye and Ear Infirmary
- Resource Type
- Journal article
- Publication Details
- Investigative ophthalmology & visual science, Vol.67(1), 12
- DOI
- 10.1167/iovs.67.1.12
- PMID
- 41533910
- PMCID
- PMC12798753
- NLM abbreviation
- Invest Ophthalmol Vis Sci
- ISSN
- 1552-5783
- eISSN
- 1552-5783
- Publisher
- ARVO
- Grant note
- Iowa Healthy EyesNew York Eye and Ear Infirmary Foundation, New York, N.Y.NEI: R01 EY015473 Research to Prevent Blindness, Inc., New York, NY - Health Research Board: ICAT-2022-001 ICAT ProgrammeNational Center for Advancing Translational Sciences of the National Institutes of Health: NIH CTSA UL1TR002537, UL1TR003163 NIH (NEI): R01 EY034194-02 Research to Prevent Blindness Challenge Grant at UTSW: P30 EY030413 VA Merit Review Grant: I01 RX-001821-01A1 Department of Veteran Affairs (VA) Center for the Prevention and Treatment of Visual Loss, Rehabilitation Research and Development: (RRD) I50 RX003002 VA RRD: I01RX003797, 5IK1RX005029 Department of Veterans Affairs: RRD CDA-1, 1IK1RX005029-01 Department of Veterans Affairs, Veterans Health Administration, Office of Research and DevelopmentBarry Family Center for Ophthalmic Artificial Intelligence and Human Health
The authors thank Anushi Wijayagunaratne, for her invaluable assistance with chart review of the Iowa Healthy Eyes dataset. Supported by the New York Eye and Ear Infirmary Foundation, New York, N.Y.; NEI EY032522; Research to Prevent Blindness, Inc., New York, NY unrestricted grant to the Department of Ophthalmology; Shulman Family NAION Fund at Icahn School of Medicine at Mount Sinai; This research was partially funded by the Health Research Board (ICAT-2022-001) and the ICAT Programme; Research reported in this publication was supported in part by the National Center for Advancing Translational Sciences of the National Institutes of Health under Award Number NIH CTSA UL1TR002537 and UL1TR003163. NIH (NEI) Grant Number: 1R01EY031544-01. Also supported by NIH (NEI) R01 EY034194-02. The content is solely the responsibility of the authors and does not necessarily represent the official views of the NIH. Research to Prevent Blindness Challenge Grant at UTSW, and NIH P30 EY030413. This study was supported by a VA Merit Review Grant 5 I01 RX000140-03. NEI R01 EY015473; Department of Veteran Affairs (VA) Center for the Prevention and Treatment of Visual Loss, Rehabilitation Research and Development (RR&D) I50 RX003002; VA RR&D I01RX003797; 5IK1RX005029. Department of Veterans Affairs, RR&D CDA-1 grant 1IK1RX005029-01. Supported by a VA Merit Review Grant (#I01 RX-001821-01A1) . This material is based upon work supported (or supported in part) by the Department of Veterans Affairs, Veterans Health Administration, Office of Research and Development. The views expressed in this article are those of the authors and do not necessarily reflect the position or policy of the Department of Veterans Affairs or the United States Government. The Barry Family Center for Ophthalmic Artificial Intelligence and Human Health.
- Language
- English
- Date published
- 01/05/2026
- Academic Unit
- Roy J. Carver Department of Biomedical Engineering; Neurology; Electrical and Computer Engineering; Iowa Neuroscience Institute; Ophthalmology and Visual Sciences
- Record Identifier
- 9985121597102771
Metrics
1 Record Views