Premium
Diabetic retinopathy screening using deep neural network
Author(s) -
Ramachandran Nishanthan,
Hong Sheng Chiong,
Sime Mary J,
Wilson Graham A
Publication year - 2017
Publication title -
clinical and experimental ophthalmology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.3
H-Index - 74
eISSN - 1442-9071
pISSN - 1442-6404
DOI - 10.1111/ceo.13056
Subject(s) - medicine , diabetic retinopathy , receiver operating characteristic , confidence interval , retinopathy , retinal , optometry , artificial neural network , ophthalmology , artificial intelligence , diabetes mellitus , computer science , endocrinology
Importance There is a burgeoning interest in the use of deep neural network in diabetic retinal screening. Background To determine whether a deep neural network could satisfactorily detect diabetic retinopathy that requires referral to an ophthalmologist from a local diabetic retinal screening programme and an international database. Design Retrospective audit. Participants Diabetic retinal photos from Otago database photographed during October 2016 (485 photos), and 1200 photos from Messidor international database. Methods Receiver operating characteristic curve to illustrate the ability of a deep neural network to identify referable diabetic retinopathy (moderate or worse diabetic retinopathy or exudates within one disc diameter of the fovea). Main Outcome Measures Area under the receiver operating characteristic curve, sensitivity and specificity. Results For detecting referable diabetic retinopathy, the deep neural network had an area under receiver operating characteristic curve of 0.901 (95% confidence interval 0.807–0.995), with 84.6% sensitivity and 79.7% specificity for Otago and 0.980 (95% confidence interval 0.973–0.986), with 96.0% sensitivity and 90.0% specificity for Messidor. Conclusions and Relevance This study has shown that a deep neural network can detect referable diabetic retinopathy with sensitivities and specificities close to or better than 80% from both an international and a domestic (New Zealand) database. We believe that deep neural networks can be integrated into community screening once they can successfully detect both diabetic retinopathy and diabetic macular oedema.