Related Experiment Video
Updated: Sep 7, 2026
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
Deriving OCT-Equivalent Retinal Nerve Fiber Layer Thickness Maps from Fundus Photographs with Deep Learning Improves
Lily Shi1, Min Shi2, In Young Chung3
1Harvard Ophthalmology AI Lab, Schepens Eye Research Institute, Massachusetts Eye and Ear, Harvard Medical School, Boston, Massachusetts.
Purpose:
To develop and evaluate a deep learning model that predicts OCT-equivalent retinal nerve fiber layer thickness (RNFLT) maps directly from color fundus photographs and to assess their diagnostic value for detecting glaucomatous visual field (VF) loss.
Design:
Retrospective model development and evaluation study.
Participants:
15 031 paired fundus photographs and spectral-domain OCT scans collected at Massachusetts Eye and Ear, 2011 to 2022.
Methods:
Paired fundus and OCT images were used to train a U-Net-based model to predict pixel-wise RNFLT maps with artifact-corrected supervision. Diagnostic performance was evaluated across single-modality models (fundus photos only, real RNFLT maps, and predicted RNFLT maps) and multimodal fusion models (fundus + predicted RNFLT maps). Stratified analyses examined model performance across glaucoma severity and demographic subgroups. Glaucoma was defined based on standard criteria applied to Humphrey 24-2 VF testing.
Main Outcome Measures:
Mean absolute error and structural similarity index for RNFLT map prediction. Area under the receiver operating characteristic curve (AUC) and accuracy for glaucoma detection.
Results:
RNFLT map prediction achieved mean absolute error = 15.4 μm and structural similarity index = 0.65, measured against artifact-corrected RNFLT maps derived from OCT. For glaucoma detection, the predicted RNFLT-only classifier outperformed the fundus-only classifier (AUC: 0.889 vs. 0.883, P < 0.005; accuracy 82.0% vs. 78.0%), but performed worse than the real-RNFLT-only classifier (AUC: 0.889 vs. 0.903, P < 0.005). Multimodal fusion of fundus images with predicted RNFLT maps improved performance, achieving an AUC of 0.909, outperforming all single-modality inputs (P < 0.005 vs. fundus-only, predicted-RNFLT-only, and real-RNFLT-only). Performance gains from fundus-only to multimodal classifier were greater in early-stage glaucoma compared to severe cases: accuracy increased from 55.3% to 64.0% in mild cases, from 71.5% to 80.4% in moderate cases, and from 90.0% to 94.6% in severe cases.
Conclusions:
Predicted RNFLT maps derived from fundus photographs provide quantitative, OCT-like structural information and improve detection of glaucomatous VF loss. Unlike prior work that predicted only summary RNFLT values, our model generates full RNFLT maps that better support glaucoma classification than fundus images alone. This approach offers a scalable pathway for early glaucoma screening and expands diagnostic access in resource-limited settings.
Financial Disclosures:
Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.