Sidong Liu1, Stuart L Graham2, Angela Schulz2, Michael Kalloniatis3, Barbara Zangerl3, Weidong Cai4, Yang Gao5, Brian Chua6, Hemamalini Arvind7, John Grigg8, Dewei Chu9, Alexander Klistorner10, Yuyi You11. 1. Save Sight Institute, Sydney Medical School, The University of Sydney, Sydney, Australia; Brain and Mind Centre, Sydney Medical School, The University of Sydney, Sydney, Australia. 2. Department of Clinical Medicine, Faculty of Medicine and Health Sciences, Macquarie University, Sydney, Australia. 3. Centre for Eye Health, and School of Optometry and Vision Science, The University of New South Wales, Kensington, Australia. 4. School of Information Technologies, The University of Sydney, Sydney, Australia. 5. School of Instrumentation Sciences and Opto-electronics Engineering, Beihang University, Beijing, China. 6. Glaucoma Unit, Sydney Eye Hospital, Sydney, Australia. 7. Save Sight Institute, Sydney Medical School, The University of Sydney, Sydney, Australia. 8. Save Sight Institute, Sydney Medical School, The University of Sydney, Sydney, Australia; Glaucoma Unit, Sydney Eye Hospital, Sydney, Australia. 9. School of Materials Science and Engineering, The University of New South Wales, Kensington, Australia. 10. Save Sight Institute, Sydney Medical School, The University of Sydney, Sydney, Australia; Department of Clinical Medicine, Faculty of Medicine and Health Sciences, Macquarie University, Sydney, Australia. 11. Save Sight Institute, Sydney Medical School, The University of Sydney, Sydney, Australia; Department of Clinical Medicine, Faculty of Medicine and Health Sciences, Macquarie University, Sydney, Australia. Electronic address: yuyi.you@gmail.com.
Abstract
PURPOSE: To develop and test the performance of a deep learning-based algorithm for glaucomatous disc identification using monoscopic fundus photographs. DESIGN: Fundus photograph database study. PARTICIPANTS: Four thousand three hundred ninety-four fundus photographs, including 3768 images from previous Sydney-based clinical studies and 626 images from publicly available online RIM-ONE and High-Resolution Fundus (HRF) databases with definitive diagnoses. METHODS: We merged all databases except the HRF database, and then partitioned the dataset into a training set (80% of all cases) and a testing set (20% of all cases). We used the HRF images as an additional testing set. We compared the performance of the artificial intelligence (AI) system against a panel of practicing ophthalmologists including glaucoma subspecialists from Australia, New Zealand, Canada, and the United Kingdom. MAIN OUTCOME MEASURES: The sensitivity and specificity of the AI system in detecting glaucomatous optic discs. RESULTS: By using monoscopic fundus photographs, the AI system demonstrated a high accuracy rate in glaucomatous disc identification (92.7%; 95% confidence interval [CI], 91.2%-94.2%), achieving 89.3% sensitivity (95% CI, 86.8%-91.7%) and 97.1% specificity (95% CI, 96.1%-98.1%), with an area under the receiver operating characteristic curve of 0.97 (95% CI, 0.96-0.98). Using the independent online HRF database (30 images), the AI system again accomplished high accuracy, with 86.7% in both sensitivity and specificity (for ophthalmologists, 75.6% sensitivity and 77.8% specificity) and an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.76-1.00). CONCLUSIONS: This study demonstrated that a deep learning-based algorithm can identify glaucomatous discs at high accuracy level using monoscopic fundus images. Given that it is far easier to obtain monoscopic disc images than high-quality stereoscopic images, this study highlights the algorithm's potential application in large population-based disease screening or telemedicine programs.
PURPOSE: To develop and test the performance of a deep learning-based algorithm for glaucomatous disc identification using monoscopic fundus photographs. DESIGN: Fundus photograph database study. PARTICIPANTS: Four thousand three hundred ninety-four fundus photographs, including 3768 images from previous Sydney-based clinical studies and 626 images from publicly available online RIM-ONE and High-Resolution Fundus (HRF) databases with definitive diagnoses. METHODS: We merged all databases except the HRF database, and then partitioned the dataset into a training set (80% of all cases) and a testing set (20% of all cases). We used the HRF images as an additional testing set. We compared the performance of the artificial intelligence (AI) system against a panel of practicing ophthalmologists including glaucoma subspecialists from Australia, New Zealand, Canada, and the United Kingdom. MAIN OUTCOME MEASURES: The sensitivity and specificity of the AI system in detecting glaucomatous optic discs. RESULTS: By using monoscopic fundus photographs, the AI system demonstrated a high accuracy rate in glaucomatous disc identification (92.7%; 95% confidence interval [CI], 91.2%-94.2%), achieving 89.3% sensitivity (95% CI, 86.8%-91.7%) and 97.1% specificity (95% CI, 96.1%-98.1%), with an area under the receiver operating characteristic curve of 0.97 (95% CI, 0.96-0.98). Using the independent online HRF database (30 images), the AI system again accomplished high accuracy, with 86.7% in both sensitivity and specificity (for ophthalmologists, 75.6% sensitivity and 77.8% specificity) and an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.76-1.00). CONCLUSIONS: This study demonstrated that a deep learning-based algorithm can identify glaucomatous discs at high accuracy level using monoscopic fundus images. Given that it is far easier to obtain monoscopic disc images than high-quality stereoscopic images, this study highlights the algorithm's potential application in large population-based disease screening or telemedicine programs.
Authors: Ravi Aggarwal; Viknesh Sounderajah; Guy Martin; Daniel S W Ting; Alan Karthikesalingam; Dominic King; Hutan Ashrafian; Ara Darzi Journal: NPJ Digit Med Date: 2021-04-07
Authors: Mark Christopher; Kenichi Nakahara; Christopher Bowd; James A Proudfoot; Akram Belghith; Michael H Goldbaum; Jasmin Rezapour; Robert N Weinreb; Massimo A Fazio; Christopher A Girkin; Jeffrey M Liebmann; Gustavo De Moraes; Hiroshi Murata; Kana Tokumo; Naoto Shibata; Yuri Fujino; Masato Matsuura; Yoshiaki Kiuchi; Masaki Tanito; Ryo Asaoka; Linda M Zangwill Journal: Transl Vis Sci Technol Date: 2020-04-28 Impact factor: 3.283
Authors: Yang Gao; Xiong Xiao; Bangcheng Han; Guilin Li; Xiaolin Ning; Defeng Wang; Weidong Cai; Ron Kikinis; Shlomo Berkovsky; Antonio Di Ieva; Liwei Zhang; Nan Ji; Sidong Liu Journal: JMIR Med Inform Date: 2020-11-17