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.
Keywords: artificial intelligence; computer; diabetic retinopathy; neural network; screening.
© 2017 Royal Australian and New Zealand College of Ophthalmologists.