Hanruo Liu1,2, Liu Li3, I Michael Wormstone4, Chunyan Qiao1,2, Chun Zhang5, Ping Liu6, Shuning Li1,2, Huaizhou Wang1,2, Dapeng Mou1,2, Ruiqi Pang1,2, Diya Yang1,2, Linda M Zangwill7, Sasan Moghimi7, Huiyuan Hou7, Christopher Bowd7, Lai Jiang3, Yihan Chen1,2, Man Hu8, Yongli Xu9, Hong Kang10, Xin Ji11, Robert Chang12, Clement Tham13, Carol Cheung13, Daniel Shu Wei Ting14, Tien Yin Wong14, Zulin Wang3, Robert N Weinreb7, Mai Xu3, Ningli Wang1,2. 1. Beijing Institute of Ophthalmology, Beijing Tongren Hospital, Capital Medical University, Beijing, China. 2. Beijing Ophthalmology and Visual Science Key Lab, Beijing, China. 3. School of Electronic and Information Engineering, Beihang University, Beijing, China. 4. School of Biological Sciences, University of East Anglia, Norwich, United Kingdom. 5. Department of Ophthalmology, Peking University Third Hospital, Beijing, China. 6. Ophthalmology Hospital, First Hospital of Harbin Medical University, Harbin, Heilongjiang, China. 7. Shiley Eye Institute, University of California, San Diego, La Jolla, California. 8. Department of Ophthalmology, Beijing Children's Hospital, Capital Medical University, Beijing, China. 9. Department of Mathematics, Beijing University of Chemical Technology, Beijing, China. 10. College of Computer Science,Nankai University, Tianjin, China. 11. Beijing Shanggong Medical Technology Co., Ltd, Beijing, China. 12. Department of Ophthalmology, Byers Eye Institute at Stanford University, Palo Alto, California. 13. Department of Ophthalmology and Visual Sciences, Faculty of Medicine, The Chinese University of Hong Kong, Kowloon, Hong Kong, China. 14. Singapore Eye Research Institute, Singapore National Eye Center, Singapore.
Abstract
Importance: A deep learning system (DLS) that could automatically detect glaucomatous optic neuropathy (GON) with high sensitivity and specificity could expedite screening for GON. Objective: To establish a DLS for detection of GON using retinal fundus images and glaucoma diagnosis with convoluted neural networks (GD-CNN) that has the ability to be generalized across populations. Design, Setting, and Participants: In this cross-sectional study, a DLS for the classification of GON was developed for automated classification of GON using retinal fundus images obtained from the Chinese Glaucoma Study Alliance, the Handan Eye Study, and online databases. The researchers selected 241 032 images were selected as the training data set. The images were entered into the databases on June 9, 2009, obtained on July 11, 2018, and analyses were performed on December 15, 2018. The generalization of the DLS was tested in several validation data sets, which allowed assessment of the DLS in a clinical setting without exclusions, testing against variable image quality based on fundus photographs obtained from websites, evaluation in a population-based study that reflects a natural distribution of patients with glaucoma within the cohort and an additive data set that has a diverse ethnic distribution. An online learning system was established to transfer the trained and validated DLS to generalize the results with fundus images from new sources. To better understand the DLS decision-making process, a prediction visualization test was performed that identified regions of the fundus images utilized by the DLS for diagnosis. Exposures: Use of a deep learning system. Main Outcomes and Measures: Area under the receiver operating characteristics curve (AUC), sensitivity and specificity for DLS with reference to professional graders. Results: From a total of 274 413 fundus images initially obtained from CGSA, 269 601 images passed initial image quality review and were graded for GON. A total of 241 032 images (definite GON 29 865 [12.4%], probable GON 11 046 [4.6%], unlikely GON 200 121 [83%]) from 68 013 patients were selected using random sampling to train the GD-CNN model. Validation and evaluation of the GD-CNN model was assessed using the remaining 28 569 images from CGSA. The AUC of the GD-CNN model in primary local validation data sets was 0.996 (95% CI, 0.995-0.998), with sensitivity of 96.2% and specificity of 97.7%. The most common reason for both false-negative and false-positive grading by GD-CNN (51 of 119 [46.3%] and 191 of 588 [32.3%]) and manual grading (50 of 113 [44.2%] and 183 of 538 [34.0%]) was pathologic or high myopia. Conclusions and Relevance: Application of GD-CNN to fundus images from different settings and varying image quality demonstrated a high sensitivity, specificity, and generalizability for detecting GON. These findings suggest that automated DLS could enhance current screening programs in a cost-effective and time-efficient manner.
Importance: A deep learning system (DLS) that could automatically detect glaucomatous optic neuropathy (GON) with high sensitivity and specificity could expedite screening for GON. Objective: To establish a DLS for detection of GON using retinal fundus images and glaucoma diagnosis with convoluted neural networks (GD-CNN) that has the ability to be generalized across populations. Design, Setting, and Participants: In this cross-sectional study, a DLS for the classification of GON was developed for automated classification of GON using retinal fundus images obtained from the Chinese Glaucoma Study Alliance, the Handan Eye Study, and online databases. The researchers selected 241 032 images were selected as the training data set. The images were entered into the databases on June 9, 2009, obtained on July 11, 2018, and analyses were performed on December 15, 2018. The generalization of the DLS was tested in several validation data sets, which allowed assessment of the DLS in a clinical setting without exclusions, testing against variable image quality based on fundus photographs obtained from websites, evaluation in a population-based study that reflects a natural distribution of patients with glaucoma within the cohort and an additive data set that has a diverse ethnic distribution. An online learning system was established to transfer the trained and validated DLS to generalize the results with fundus images from new sources. To better understand the DLS decision-making process, a prediction visualization test was performed that identified regions of the fundus images utilized by the DLS for diagnosis. Exposures: Use of a deep learning system. Main Outcomes and Measures: Area under the receiver operating characteristics curve (AUC), sensitivity and specificity for DLS with reference to professional graders. Results: From a total of 274 413 fundus images initially obtained from CGSA, 269 601 images passed initial image quality review and were graded for GON. A total of 241 032 images (definite GON 29 865 [12.4%], probable GON 11 046 [4.6%], unlikely GON 200 121 [83%]) from 68 013 patients were selected using random sampling to train the GD-CNN model. Validation and evaluation of the GD-CNN model was assessed using the remaining 28 569 images from CGSA. The AUC of the GD-CNN model in primary local validation data sets was 0.996 (95% CI, 0.995-0.998), with sensitivity of 96.2% and specificity of 97.7%. The most common reason for both false-negative and false-positive grading by GD-CNN (51 of 119 [46.3%] and 191 of 588 [32.3%]) and manual grading (50 of 113 [44.2%] and 183 of 538 [34.0%]) was pathologic or high myopia. Conclusions and Relevance: Application of GD-CNN to fundus images from different settings and varying image quality demonstrated a high sensitivity, specificity, and generalizability for detecting GON. These findings suggest that automated DLS could enhance current screening programs in a cost-effective and time-efficient manner.
Authors: Julia Schottenhamml; Tobias Würfl; Sophia Mardin; Stefan B Ploner; Lennart Husvogt; Bettina Hohberger; Robert Lämmer; Christian Mardin; Andreas Maier Journal: Biomed Opt Express Date: 2021-11-09 Impact factor: 3.732
Authors: Parmita Mehta; Christine A Petersen; Joanne C Wen; Michael R Banitt; Philip P Chen; Karine D Bojikian; Catherine Egan; Su-In Lee; Magdalena Balazinska; Aaron Y Lee; Ariel Rokem Journal: Am J Ophthalmol Date: 2021-05-02 Impact factor: 5.258
Authors: Nazlee Zebardast; Sayuri Sekimitsu; Jiali Wang; Tobias Elze; Puya Gharahkhani; Brian S Cole; Michael M Lin; Ayellet V Segrè; Janey L Wiggs Journal: Ophthalmology Date: 2021-03-10 Impact factor: 14.277
Authors: Christopher Bowd; Akram Belghith; Mark Christopher; Michael H Goldbaum; Massimo A Fazio; Christopher A Girkin; Jeffrey M Liebmann; Carlos Gustavo de Moraes; Robert N Weinreb; Linda M Zangwill Journal: Transl Vis Sci Technol Date: 2021-07-01 Impact factor: 3.048
Authors: Jimmy S Chen; Aaron S Coyner; Susan Ostmo; Kemal Sonmez; Sanyam Bajimaya; Eli Pradhan; Nita Valikodath; Emily D Cole; Tala Al-Khaled; R V Paul Chan; Praveer Singh; Jayashree Kalpathy-Cramer; Michael F Chiang; J Peter Campbell Journal: Ophthalmol Retina Date: 2021-02-06