Journal article
Deep Learning Differentiates Papilledema, NAION, and Healthy Eyes with Unsegmented 3D OCT Volumes
American journal of ophthalmology, Vol.277, pp.249-259
09/2025
DOI: 10.1016/j.ajo.2025.05.036
PMID: 40447246
Abstract
Deep learning (DL) has been used to differentiate papilledema from healthy eyes and optic disc elevation on fundus photos. As we described optic nerve head (ONH) and peripapillary retina (PPR) optical coherence tomography (OCT) features that distinguish non-arteritic anterior ischemic optic neuropathy (NAION) from papilledema, we hypothesized that a DL approach using the full 3D OCT volume could reliably differentiate NAION, papilledema and healthy eyes.
This retrospective review analyzed OCT scans from eyes with acute NAION, papilledema, and healthy eyes from randomized and non-randomized clinical trials.
We investigated a total of 4619 raw spectral domain ONH volume scans from 1539 eyes, including 1138 from eyes with idiopathic intracranial hypertension (IIH, Frisén grade ≥ 1), 648 from eyes with acute NAION, and 2833 scans from healthy eyes. We performed external validation on an additional 1663 scans from 742 eyes across these groups.
We fine-tuned three ResNet 3D-18 models: one with the entire OCT volume, one with the PPR, and one with the optic nerve head excluding the PPR. We then evaluated the models on an external validation set.
The primary outcome measures were accuracy, area under the Receiver Operating Characteristic curve (AUC-ROC), and weighted precision, recall, and F1 scores.
Our model classified the three conditions using the entire scan with an internal validation accuracy of 94.9%, macro-average AUC-ROC of 0.986 with weighted F1 scores ranging from 0.93-0.95. In external validation, the entire scan model had an accuracy of 90.1% with a macro-average AUC-ROC of 0.977 and weighted F1-score range of 0.89-0.94. The PPR alone model attained an accuracy of 94.2%, with a macro-average AUC-ROC of 0.966 and weighted F1-score range of 0.81-0.88. The ONH alone model reached an accuracy of 85.0% with an AUC-ROC of 0.965 and weighted F1-score range of 0.84-0.89.
Our findings demonstrate that the model using the whole ONH OCT scan is a robust diagnostic tool for differentiating causes of swollen ONH. Changes in the PPR due to ONH swelling as well as ONH alone can also differentiate the disorders. The results reinforce the potential of automated approaches in assisting in the diagnosis of acquired optic disc swelling.
Details
- Title: Subtitle
- Deep Learning Differentiates Papilledema, NAION, and Healthy Eyes with Unsegmented 3D OCT Volumes
- Creators
- David Szanto - Icahn School of Medicine at Mount SinaiJui-Kai Wang - The University of Texas Southwestern Medical CenterBrian Woods - University Hospital GalwayMona K Garvin - University of IowaBrett A Johnson - University of IowaRandy H Kardon - University of IowaEdward F Linton - University of IowaMark J Kupersmith - Icahn School of Medicine at Mount Sinai
- Resource Type
- Journal article
- Publication Details
- American journal of ophthalmology, Vol.277, pp.249-259
- DOI
- 10.1016/j.ajo.2025.05.036
- PMID
- 40447246
- NLM abbreviation
- Am J Ophthalmol
- ISSN
- 1879-1891
- eISSN
- 1879-1891
- Publisher
- ELSEVIER SCIENCE INC
- Grant note
- New York Eye and Ear Infirmary Foundation, New York, N.Y.NEI: EY032522 Research to Prevent Blindness, Inc., New York, NYHealth Research Board: ICAT-2022-001 ICAT ProgrammeNational Center for Advancing Translational Sciences of the National Institutes of Health: NIH CTSA UL1TR002537, UL1TR003163
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.
- Language
- English
- Electronic publication date
- 05/28/2025
- Date published
- 09/2025
- Academic Unit
- Electrical and Computer Engineering; Iowa Neuroscience Institute; Ophthalmology and Visual Sciences
- Record Identifier
- 9984824184102771
Metrics
3 Record Views