Development of Deep Learning Models to Predict Best-Corrected Visual Acuity from Optical Coherence Tomography

Abstract

Purpose To develop deep learning (DL) models to predict best-corrected visual acuity (BCVA) from optical coherence tomography (OCT) images from patients with neovascular age-related macular degeneration (nAMD). Methods Retrospective analysis of OCT images and associated BCVA measurements from the phase 3 HARBOR trial (NCT00891735). DL regression models were developed to predict BCVA at the concurrent visit and 12 months from baseline using OCT images. Binary classification models were developed to predict BCVA of Snellen equivalent of <20/40, <20/60, and ≤20/200 at the concurrent visit and 12 months from baseline. Results The regression model to predict BCVA at the concurrent visit had R 2 = 0.67 (root-mean-square error [RMSE] = 8.60) in study eyes and R 2 = 0.84 (RMSE = 9.01) in fellow eyes. The best classification model to predict BCVA at the concurrent visit had an area under the receiver operating characteristic curve (AUC) of 0.92 in study eyes and 0.98 in fellow eyes. The regression model to predict BCVA at month 12 using baseline OCT had R 2 = 0.33 (RMSE = 14.16) in study eyes and R 2 = 0.75 (RMSE = 11.27) in fellow eyes. The best classification model to predict BCVA at month 12 had AUC = 0.84 in study eyes and AUC = 0.96 in fellow eyes. Conclusions DL shows promise in predicting BCVA from OCTs in nAMD. Further research should elucidate the utility of models in clinical settings. Translational Relevance DL models predicting BCVA could be used to enhance understanding of structure–function relationships and develop more efficient clinical trials.

Deep Learning-Based Optical Coherence Tomography and Optical Coherence Tomography Angiography Image Analysis: An Updated Summary

“…65 Advancements in DL can provide promising tools for visual function predictions from structural changes detected on OCT images. Kawczynki et al 66 proposed a DL-based regression model to predict the best-corrected visual acuity (BCVA) from OCT images of treatment-naı ¨ve nAMD patients. They used volumetric OCT scans as the input to predict the BCVA and classify poorer BCVA from better BCVA.…”

Performance of Deep Learning Models in Automatic Measurement of Ellipsoid Zone Area on Baseline Optical Coherence Tomography (OCT) Images From the Rate of Progression of USH2A-Related Retinal Degeneration (RUSH2A) Study

“…Recent advances in deep learning (DL) based neural networks have provided new techniques for clinical applications in ophthalmology (2). DL approaches have demonstrated the potential of automatic retinal disease detection and classification from fundus photos and optical coherence tomography (OCT) scan images (3,4), automatic segmentation of retinal layers and structural features from OCT scan images for quantitative measurements (5)(6)(7)(8), and visual function prediction from OCT images (9)(10)(11)(12). For instance, deep neural networks have been developed and trained for automatic identification of diabetic retinopathy in retinal fundus photographs (4,13,14), for automatic segmentation of retinal layer boundaries in OCT images of dry age-related macular degeneration (AMD) (5), for automated detection and quantification of intraretinal cystoid fluid and subretinal fluid in OCT images of neo-vascular AMD (8), and for predicting glaucomatous visual field damage from OCT optic nerve head en face images and retinal nerve fiber layer thickness maps (10).…”

A Systematic Review of Deep Learning Applications for Optical Coherence Tomography in Age-Related Macular Degeneration

“…Six articles used deep learning applications to predict and identify biomarkers associated with visual function. Kawczynski et al 27 trained a CNN to directly predict 12-month visual acuity from OCT images in patients with neovascular AMD. The remaining studies used deep learning for biomarker segmentation, and the output was then associated with present or future visual acuity or changes in visual acuity.…”