Deep Learning with Disc Photos or OCT Scans in Glaucoma Detection
Ophthalmology Science · 2025-11 · 5 (6) · 100877
DOI: 10.1016/j.xops.2025.100877 ↗Kurz gefasst
Fachartikel in der Zeitschrift Ophthalmology Science, 2025-11. Verfasst von Abhilash Katuru und 4 weiteren Autor:innen. Beteiligte Einrichtung: Harvard Ophthalmology AI Lab, Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School, Boston, MA. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 52 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: NEI NIH HHS, National Eye Institute, Glaucoma Foundation.
Abstract (Originalsprache)
Objective
To determine whether a deep learning (DL) model using retinal nerve fiber layer thickness (RNFLT) maps from OCT scans can detect glaucoma, defined by functional visual field (VF) impairment, more accurately than a DL model using disc photos (DPs). A secondary objective was to assess the diagnostic performance of these DL models across demographic groups (race, sex, and ethnicity).
Design
Retrospective cohort study at a tertiary glaucoma center utilizing OCT and DP datasets collected between 2011 and 2022.
Participants
Out of the 16 936 DP and OCT image sets, patients with Cirrus OCT images with a quality score ≥6 of 10 and reliable 24-2 Humphrey VF tests (fixation loss ≤33%, false-negative rate ≤20%, false-positive rate ≤20%), taken within 30 days of OCT, were included. Disc photos were obtained within 6 months of OCT. Data were randomly selected for training and testing of the DL models. Testing: Development of DL models utilizing either OCT RNFLT maps or DPs to detect glaucoma based on VF-defined functional impairment. Main Outcome Measures: The primary outcome was the area under the curve (AUC) for glaucoma detection, comparing the OCT-based DL model with the DP-based model. The secondary outcome was the AUC across demographic groups. Results: < 0.005).
Conclusions
When glaucoma diagnosis was based on functional deficit, the OCT-based DL model offered greater accuracy in detecting glaucoma than the DP-based model, likely due to its use of objective and quantitative RNFLT measurements. This work supports the use of OCT-based DL models for glaucoma detection, while observed demographic disparities underscore the need for equitable datasets to ensure fair DL-driven glaucoma diagnosis across populations. Financial Disclosures: Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Harvard Ophthalmology AI Lab, Schepens Eye Research Institute of Massachusetts Eye and Ear, Harvard Medical School, Boston, MA.
- Department of Ophthalmology, Massachusetts Eye and Ear, Harvard Medical School, Boston, MA.
- Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University, Boston, MA.
- Broad Institute of MIT and Harvard, Boston, MA.
Förderung
- NEI NIH HHS
- National Eye Institute
- Glaucoma Foundation
- Massachusetts Lions Eye Research Fund
- National Institutes of Health
Zitieren
APA
Katuru, A., Chung, I. Y., Majid, I., Shen, L. Q., & Wang, M. (2025). Deep Learning with Disc Photos or OCT Scans in Glaucoma Detection. Ophthalmology Science, 5(6), 100877. https://doi.org/10.1016/j.xops.2025.100877
Vancouver
Katuru A, Chung IY, Majid I, Shen LQ, Wang M. Deep Learning with Disc Photos or OCT Scans in Glaucoma Detection. Ophthalmology Science. 2025;5(6):100877. doi:10.1016/j.xops.2025.100877
BibTeX
@article{Katuru2025,
author = {Katuru, Abhilash and Chung, In Young and Majid, Iyad and Shen, Lucy Q and Wang, Mengyu},
title = {Deep Learning with Disc Photos or OCT Scans in Glaucoma Detection},
journal = {Ophthalmology Science},
year = {2025},
volume = {5},
number = {6},
pages = {100877},
doi = {10.1016/j.xops.2025.100877}
}
EUVIMED