Felipe A Medeiros1, Alessandro A Jammal2, Atalie C Thompson2. 1. Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina. Electronic address: felipe.medeiros@duke.edu. 2. Vision, Imaging and Performance (VIP) Laboratory, Duke Eye Center and Department of Ophthalmology, Duke University, Durham, North Carolina.
Abstract
PURPOSE: Previous approaches using deep learning (DL) algorithms to classify glaucomatous damage on fundus photographs have been limited by the requirement for human labeling of a reference training set. We propose a new approach using quantitative spectral-domain (SD) OCT data to train a DL algorithm to quantify glaucomatous structural damage on optic disc photographs. DESIGN: Cross-sectional study. PARTICIPANTS: A total of 32 820 pairs of optic disc photographs and SD OCT retinal nerve fiber layer (RNFL) scans from 2312 eyes of 1198 participants. METHODS: The sample was divided randomly into validation plus training (80%) and test (20%) sets, with randomization performed at the patient level. A DL convolutional neural network was trained to assess optic disc photographs and predict SD OCT average RNFL thickness. MAIN OUTCOME MEASURES: The DL algorithm performance was evaluated in the test sample by evaluating correlation and agreement between the predictions and actual SD OCT measurements. We also assessed the ability to discriminate eyes with glaucomatous visual field loss from healthy eyes with area under the receiver operating characteristic (ROC) curves. RESULTS: The mean prediction of average RNFL thickness from all 6292 optic disc photographs in the test set was 83.3±14.5 μm, whereas the mean average RNFL thickness from all corresponding SD OCT scans was 82.5±16.8 μm (P = 0.164). There was a very strong correlation between predicted and observed RNFL thickness values (Pearson r = 0.832; R2 = 69.3%; P < 0.001), with mean absolute error of the predictions of 7.39 μm. The area under the ROC curves for discriminating glaucomatous from healthy eyes with the DL predictions and actual SD OCT average RNFL thickness measurements were 0.944 (95% confidence interval [CI], 0.912-0.966) and 0.940 (95% CI, 0.902-0.966), respectively (P = 0.724). CONCLUSIONS: We introduced a novel DL approach to assess fundus photographs and provide quantitative information about the amount of neural damage that can be used to diagnose and stage glaucoma. In addition, training neural networks to predict SD OCT data objectively represents a new approach that overcomes limitations of human labeling and could be useful in other areas of ophthalmology.
PURPOSE: Previous approaches using deep learning (DL) algorithms to classify glaucomatous damage on fundus photographs have been limited by the requirement for human labeling of a reference training set. We propose a new approach using quantitative spectral-domain (SD) OCT data to train a DL algorithm to quantify glaucomatous structural damage on optic disc photographs. DESIGN: Cross-sectional study. PARTICIPANTS: A total of 32 820 pairs of optic disc photographs and SD OCT retinal nerve fiber layer (RNFL) scans from 2312 eyes of 1198 participants. METHODS: The sample was divided randomly into validation plus training (80%) and test (20%) sets, with randomization performed at the patient level. A DL convolutional neural network was trained to assess optic disc photographs and predict SD OCT average RNFL thickness. MAIN OUTCOME MEASURES: The DL algorithm performance was evaluated in the test sample by evaluating correlation and agreement between the predictions and actual SD OCT measurements. We also assessed the ability to discriminate eyes with glaucomatous visual field loss from healthy eyes with area under the receiver operating characteristic (ROC) curves. RESULTS: The mean prediction of average RNFL thickness from all 6292 optic disc photographs in the test set was 83.3±14.5 μm, whereas the mean average RNFL thickness from all corresponding SD OCT scans was 82.5±16.8 μm (P = 0.164). There was a very strong correlation between predicted and observed RNFL thickness values (Pearson r = 0.832; R2 = 69.3%; P < 0.001), with mean absolute error of the predictions of 7.39 μm. The area under the ROC curves for discriminating glaucomatous from healthy eyes with the DL predictions and actual SD OCT average RNFL thickness measurements were 0.944 (95% confidence interval [CI], 0.912-0.966) and 0.940 (95% CI, 0.902-0.966), respectively (P = 0.724). CONCLUSIONS: We introduced a novel DL approach to assess fundus photographs and provide quantitative information about the amount of neural damage that can be used to diagnose and stage glaucoma. In addition, training neural networks to predict SD OCT data objectively represents a new approach that overcomes limitations of human labeling and could be useful in other areas of ophthalmology.
Authors: Mauro T Leite; Harsha L Rao; Robert N Weinreb; Linda M Zangwill; Christopher Bowd; Pamela A Sample; Ali Tafreshi; Felipe A Medeiros Journal: Am J Ophthalmol Date: 2010-10-20 Impact factor: 5.258
Authors: Felipe A Medeiros; Pamela A Sample; Linda M Zangwill; Jeffrey M Liebmann; Christopher A Girkin; Robert N Weinreb Journal: Invest Ophthalmol Vis Sci Date: 2006-06 Impact factor: 4.799
Authors: Daniel Shu Wei Ting; Carol Yim-Lui Cheung; Gilbert Lim; Gavin Siew Wei Tan; Nguyen D Quang; Alfred Gan; Haslina Hamzah; Renata Garcia-Franco; Ian Yew San Yeo; Shu Yen Lee; Edmund Yick Mun Wong; Charumathi Sabanayagam; Mani Baskaran; Farah Ibrahim; Ngiap Chuan Tan; Eric A Finkelstein; Ecosse L Lamoureux; Ian Y Wong; Neil M Bressler; Sobha Sivaprasad; Rohit Varma; Jost B Jonas; Ming Guang He; Ching-Yu Cheng; Gemmy Chui Ming Cheung; Tin Aung; Wynne Hsu; Mong Li Lee; Tien Yin Wong Journal: JAMA Date: 2017-12-12 Impact factor: 56.272
Authors: Henry D Jampel; David Friedman; Harry Quigley; Susan Vitale; Rhonda Miller; Frederick Knezevich; Yulan Ding Journal: Am J Ophthalmol Date: 2008-09-13 Impact factor: 5.258
Authors: Eduardo M Normando; Tim E Yap; John Maddison; Serge Miodragovic; Paolo Bonetti; Melanie Almonte; Nada G Mohammad; Sally Ameen; Laura Crawley; Faisal Ahmed; Philip A Bloom; Maria Francesca Cordeiro Journal: Expert Rev Mol Diagn Date: 2020-05-03 Impact factor: 5.225
Authors: Alessandro A Jammal; Atalie C Thompson; Eduardo B Mariottoni; Samuel I Berchuck; Carla N Urata; Tais Estrela; Susan M Wakil; Vital P Costa; Felipe A Medeiros Journal: Am J Ophthalmol Date: 2019-11-12 Impact factor: 5.258
Authors: Mengyu Wang; Lucy Q Shen; Louis R Pasquale; Michael V Boland; Sarah R Wellik; Carlos Gustavo De Moraes; Jonathan S Myers; Thao D Nguyen; Robert Ritch; Pradeep Ramulu; Hui Wang; Jorryt Tichelaar; Dian Li; Peter J Bex; Tobias Elze Journal: Ophthalmology Date: 2019-12-12 Impact factor: 12.079
Authors: An Ran Ran; Clement C Tham; Poemen P Chan; Ching-Yu Cheng; Yih-Chung Tham; Tyler Hyungtaek Rim; Carol Y Cheung Journal: Eye (Lond) Date: 2020-10-07 Impact factor: 3.775