Predicting Incremental and Future Visual Change in Neovascular Age-Related Macular Degeneration Using Deep Learning

Published:January 28, 2021DOI:


      To evaluate the predictive usefulness of quantitative imaging biomarkers, acquired automatically from 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.


      Retrospective cohort study.


      Treatment-naive, first-treated eyes of patients with neovascular AMD between 2007 and 2017 at Moorfields Eye Hospital (a large, United Kingdom single center) undergoing anti-VEGF therapy.


      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 analyzed.

      Main Outcome Measures

      Correlation coefficients (R2 values) and mean absolute error (MAE) between quantitative OCT (qOCT) parameters and cross-sectional visual function, as well as the predictive value of these parameters for short-term visual change, that is, incremental visual acuity (VA) resulting from an individual injection, as well as VA at distant time points (up to 12 months after baseline).


      Visual acuity at distant time points could be predicted: R2 = 0.80 (MAE, 5.0 Early Treatment Diabetic Retinopathy Study [ETDRS] letters) and R2 = 0.7 (MAE, 7.2 ETDRS letters) after injection at 3 and at 12 months after baseline (P < 0.001 for both), respectively. Best performing models included both baseline qOCT parameters and treatment response. Furthermore, we present proof-of-principle evidence that the incremental change in VA from an injection can be predicted: R2 = 0.14 (MAE, 5.6 ETDRS letters) for injection 2 and R2 = 0.11 (MAE, 5.0 ETDRS letters) for injection 3 (P < 0.001 for both).


      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.


      Abbreviations and Acronyms:

      AMD (age-related macular degeneration), AUC (area under the receiver operating characteristic curve), ETDRS (Early Treatment Diabetic Retinopathy Study), HRF (hyperreflective foci), IRF (intraretinal fluid), MAE (mean absolute error), PED (pigment epithelial detachment), qOCT (quantitative OCT), RPE (retinal pigment epithelium), SHRM (subretinal hyperreflective material), SRF (subretinal fluid), VA (visual acuity), VEGF (vascular endothelial growth factor)
      To read this article in full you will need to make a payment
      Subscribe to Ophthalmology Retina
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect


        • Bressler N.M.
        Age-related macular degeneration is the leading cause of blindness.
        JAMA. 2004; 291: 1900-1901
        • Jager R.D.
        • Mieler W.F.
        • Miller J.W.
        Age-related macular degeneration.
        N Engl J Med. 2008; 358: 2606-2617
        • Rosenfeld P.J.
        • Brown D.M.
        • Heier J.S.
        • et al.
        Ranibizumab for neovascular age-related macular degeneration.
        N Engl J Med. 2006; 355: 1419-1431
        • Heier J.S.
        • Brown D.M.
        • Chong V.
        • et al.
        Intravitreal aflibercept (VEGF Trap-Eye) in wet age-related macular degeneration.
        Ophthalmology. 2012; 119: 2537-2548
        • Regillo C.D.
        • Brown D.M.
        • Abraham P.
        • et al.
        Randomized, double-masked, sham-controlled trial of ranibizumab for neovascular age-related macular degeneration: PIER Study year 1.
        Am J Ophthalmol. 2008; 145: 239-248
        • Chin-Yee D.
        • Eck T.
        • Fowler S.
        • et al.
        A systematic review of as needed versus treat and extend ranibizumab or bevacizumab treatment regimens for neovascular age-related macular degeneration.
        Br J Ophthalmol. 2016; 100: 914-917
        • Schmidt-Erfurth U.
        • Chong V.
        • Loewenstein A.
        • et al.
        Guidelines for the management of neovascular age-related macular degeneration by the European Society of Retina Specialists (EURETINA).
        Br J Ophthalmol. 2014; 98: 1144-1167
      1. National Institute of Clinical Excellence.
        NICE guideline [NG82]Age-related macular degeneration. 2018; (Available at:) (Accessed December 22, 2020)
        • American Academy of Ophthalmology
        Age-related macular degeneration Preferred Practice Pattern.
        (Accessed December 22, 2020)
        • Jaffe G.J.
        • Martin D.F.
        • Toth C.A.
        • et al.
        Macular morphology and visual acuity in the Comparison of Age-Related Macular Degeneration Treatments Trials.
        Ophthalmology. 2013; 120: 1860-1870
        • Simader C.
        • Ritter M.
        • Bolz M.
        • et al.
        Morphologic parameters relevant for visual outcome during anti-angiogenic therapy of neovascular age-related macular degeneration.
        Ophthalmology. 2014; 121: 1237-1245
        • Waldstein S.M.
        • Philip A.-M.
        • Leitner R.
        • et al.
        Correlation of 3-dimensionally quantified intraretinal and subretinal fluid with visual acuity in neovascular age-related macular degeneration.
        JAMA Ophthalmol. 2016; 134: 182-190
        • Keenan T.D.
        • Clemons T.E.
        • Domalpally A.
        • et al.
        Retinal specialist versus artificial intelligence detection of retinal fluid from optical coherence tomography: AREDS2 10-year follow-On.
        Ophthalmology. 2020; 128: 100-109
        • Mehta H.
        • Tufail A.
        • Daien V.
        • et al.
        Real-world outcomes in patients with neovascular age-related macular degeneration treated with intravitreal vascular endothelial growth factor inhibitors.
        Prog Retin Eye Res. 2018; 65: 127-146
        • Comparison of Age-Related Macular Degeneration Treatments Trials Research Group
        • Martin D.F.
        • Maguire M.G.
        • et al.
        Ranibizumab and bevacizumab for neovascular age-related macular degeneration.
        N Engl J Med. 2011; 364: 1897-1908
        • Schlegl T.
        • Waldstein S.M.
        • Vogl W.D.
        • et al.
        Predicting semantic descriptions from medical images with convolutional neural networks.
        Inf Process Med Imaging. 2015; 24: 437-448
        • De Fauw J.
        • Ledsam J.R.
        • Romera-Paredes B.
        • et al.
        Clinically applicable deep learning for diagnosis and referral in retinal disease.
        Nat Med. 2018; 24: 1342-1350
        • Schmidt-Erfurth U.
        • Vogl W.D.
        • Jampol L.M.
        • Bogunović H.
        Application of automated quantification of fluid volumes to anti-VEGF therapy of neovascular age-related macular degeneration.
        Ophthalmology. 2020; 127: 1211-1219
        • Fasler K.
        • Moraes G.
        • Wagner S.
        • et al.
        One- and two-year visual outcomes from the Moorfields age-related macular degeneration database: a retrospective cohort study and an open science resource.
        BMJ Open. 2019; 9e027441
        • Moraes G.
        • Fu D.J.
        • Wilson M.
        • et al.
        Quantitative analysis of OCT for neovascular age-related macular degeneration using deep learning.
        Ophthalmology. 2020; (In press)
        • Lai T.T.
        • Hsieh Y.T.
        • Yang C.M.
        • et al.
        Biomarkers of optical coherence tomography in evaluating the treatment outcomes of neovascular age-related macular degeneration: a real-world study.
        Sci Rep. 2019; 9: 529
        • Schmidt-Erfurth U.
        • Waldstein S.M.
        A paradigm shift in imaging biomarkers in neovascular age-related macular degeneration.
        Prog Retin Eye Res. 2016; 50: 1-24
        • RStudio P.B.C.
        RStudio: Integrated Development for R.
        RStudio, PBC, Boston2020
        • Csaky K.
        • et al.
        Report from the NEI/FDA endpoints workshop on age-related macular degeneration and inherited retinal diseases.
        Invest Ophthalmol Vis Sci. 2017; 58: 3456-3463
        • Csaky K.G.
        • Richman E.A.
        • Ferris 3rd, F.L.
        Report from the NEI/FDA Ophthalmic Clinical Trial Design and Endpoints Symposium.
        Invest Ophthalmol Vis Sci. 2008; 49: 479-489
        • Kaiser P.K.
        • Brown D.M.
        • Zhang K.
        • et al.
        Ranibizumab for predominantly classic neovascular age-related macular degeneration: subgroup analysis of first-year ANCHOR results.
        Am J Ophthalmol. 2007; 144: 850-857
        • Boyer D.S.
        • Antoszyk A.N.
        • Awh C.C.
        • et al.
        Subgroup analysis of the MARINA study of ranibizumab in neovascular age-related macular degeneration.
        Ophthalmology. 2007; 114: 246-252
        • Bloch S.B.
        • la Cour M.
        • Sander B.
        • et al.
        Predictors of 1-year visual outcome in neovascular age-related macular degeneration following intravitreal ranibizumab treatment.
        Acta Ophthalmol. 2013; 91: 42-47
        • Sulzbacher F.
        • Kiss C.
        • Kaider A.
        • et al.
        Correlation of SD-OCT features and retinal sensitivity in neovascular age-related macular degeneration.
        Invest Ophthalmol Vis Sci. 2012; 53: 6448-6455
        • Sulzbacher F.
        • Kiss C.
        • Kaider A.
        • et al.
        Correlation of OCT characteristics and retinal sensitivity in neovascular age-related macular degeneration in the course of monthly ranibizumab treatment.
        Invest Ophthalmol Vis Sci. 2013; 54: 1310
        • Ritter M.
        • Simader C.
        • Bolz M.
        • et al.
        Intraretinal cysts are the most relevant prognostic biomarker in neovascular age-related macular degeneration independent of the therapeutic strategy.
        Br J Ophthalmol. 2014; 98: 1629-1635
        • Schmidt-Erfurth U.
        • Bogunovic H.
        • Sadeghipour A.
        • et al.
        Machine learning to analyze the prognostic value of current imaging biomarkers in neovascular age-related macular degeneration.
        Ophthalmol Retina. 2018; 2: 24-30
        • Kurihara T.
        • Westenskow P.D.
        • Bravo S.
        • et al.
        Targeted deletion of Vegfa in adult mice induces vision loss.
        J Clin Invest. 2012; 122: 4213-4217
        • Vander J.F.
        Ranibizumab and bevacizumab for neovascular age-related macular degeneration.
        Yearbook of Ophthalmology. 2012; : 145-146
        • Chakravarthy U.
        • Harding S.P.
        • Rogers C.A.
        • et al.
        Alternative treatments to inhibit VEGF in age-related choroidal neovascularisation: 2-year findings of the IVAN randomised controlled trial.
        Lancet. 2013; 382: 1258-1267
        • Ho A.C.
        • Busbee B.G.
        • Regillo C.D.
        • et al.
        Twenty-four-month efficacy and safety of 0.5 mg or 2.0 mg ranibizumab in patients with subfoveal neovascular age-related macular degeneration.
        Ophthalmology. 2014; 121: 2181-2192
        • Keane P.A.
        • Patel P.J.
        • Liakopoulos S.
        • et al.
        Evaluation of age-related macular degeneration with optical coherence tomography.
        Surv Ophthalmol. 2012; 57: 389-414
        • Byun Y.J.
        • Lee S.J.
        • Koh H.J.
        Predictors of response after intravitreal bevacizumab injection for neovascular age-related macular degeneration.
        Jpn J Ophthalmol. 2010; 54: 571-577
        • Ristau T.
        • Keane P.A.
        • Walsh A.C.
        • et al.
        Relationship between visual acuity and spectral domain optical coherence tomography retinal parameters in neovascular age-related macular degeneration.
        Ophthalmologica. 2014; 231: 37-44
        • Mathew R.
        • Richardson M.
        • Sivaprasad S.
        Predictive value of spectral-domain optical coherence tomography features in assessment of visual prognosis in eyes with neovascular age-related macular degeneration treated with ranibizumab.
        Am J Ophthalmol. 2013; 155: 720-726, 726.e1
        • Yanagihara R.T.
        • Lee C.S.
        • Ting D.S.W.
        • Lee A.Y.
        Methodological challenges of deep learning in optical coherence tomography for retinal diseases: a review.
        Transl Vis Sci Technol. 2020; 9: 11
        • Writing Committee for the UK Age-Related Macular Degeneration EMR Users Group
        The neovascular age-related macular degeneration database: multicenter study of 92 976 ranibizumab injections: report 1: visual acuity.
        Ophthalmology. 2014; 121: 1092-1101
        • Wennberg J.E.
        Understanding geographic variations in health care delivery.
        N Engl J Med. 1999; 340: 52-53
        • Amoaku W.M.
        • Chakravarthy U.
        • Gale R.
        • et al.
        Defining response to anti-VEGF therapies in neovascular AMD.
        Eye. 2015; 29: 1397-1398
        • Schlegl T.
        • Waldstein S.M.
        • Bogunovic H.
        • et al.
        Fully Automated detection and quantification of macular fluid in OCT using deep learning.
        Ophthalmology. 2018; 125: 549-558
        • Lowery C.
        • Faisal A.A.
        Towards efficient, personalized anesthesia using continuous reinforcement learning for propofol infusion control.
        in: 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER). Institute of Electrical and Electronics Engineers, New York, NY2013: 1414-1417
        • Prasad N.
        • Cheng L.F.
        • Chivers C.
        • et al.
        A reinforcement learning approach to weaning of mechanical ventilation in intensive care units.
        arXiv. 2017; (arXiv:1704.06300)
        • Bothe M.K.
        • Dickens L.
        • Reichel K.
        • et al.
        The use of reinforcement learning algorithms to meet the challenges of an artificial pancreas.
        Expert Rev Med Devices. 2013; 10: 661-673
        • Komorowski M.
        • Celi L.A.
        • Badawi O.
        • et al.
        The artificial intelligence clinician learns optimal treatment strategies for sepsis in intensive care.
        Nat Med. 2018; 24: 1716-1720