Predicting incremental and future visual change in neovascular age-related macular degeneration using deep learning.

Abstract Purpose To evaluate the predictive utility of quantitative imaging biomarkers, acquired automatically from optical coherence tomography (OCT) scans, of cross-sectional and future visual outcomes of patients with neovascular age-related macular degeneration (AMD) starting anti-vascular endothelial growth factor (VEGF) therapy. Design Retrospective cohort study. Participants Treatment-naive, first-treated eyes of patients with neovascular AMD between 2007 and 2017 at Moorfields Eye Hospital (a large, UK single-centre) undergoing anti-VEGF therapy Methods Automatic segmentation was carried out by applying a deep learning segmentation algorithm to 137,379 OCT scans from 6467 eyes of 3261 patients with neovascular AMD. After applying selection criteria 926 eyes of 926 patients were taken forward for analysis. Main outcome measures Correlation coefficients (R2) and mean absolute error (MAE) between quantitative OCT (qOCT) parameters and cross-sectional visual-function. The predictive value of these parameters for short-term visual change i.e. incremental visual acuity [VA] resulting from an individual injection, as well as, VA at distant timepoints (up to 12 months post-baseline). Results VA at distant timepoints could be predicted: R2 0.80 (MAE 5.0 ETDRS letters) and R2 0.7 (MAE 7.2) post-injection 3 and at 12 months post-baseline (both p Conclusions Automatic segmentation enables rapid acquisition of quantitative and reproducible OCT biomarkers with potential to inform treatment decisions in the care of neovascular AMD. This furthers development of point-of-care decision-aid systems for personalized medicine.