Screening for diabetic retinopathy using an automated diagnostic system based on deep learning: Diagnostic accuracy assessment
Ophthalmologica Nov 03, 2020
Rêgo S, Dutra Medeiros M, Soares F, et al. - Researchers conducted this cross-sectional study to assess the diagnostic accuracy of diagnostic system software for the automated screening of diabetic retinopathy (DR) on digital colour fundus photographs, the 2019 Convolutional Neural Network (CNN) model with Inception-V3. Two hundred ninety-five fundus images were analyzed by the CNN model and compared to a panel of ophthalmologists. The CNN model's sensitivity and specificity in diagnosing referable DR was 81% and 97%, respectively. A CNN model negative test outcome safely eliminates DR and its use may significantly lessen the burden of ophthalmologists at reading centres.
-
Exclusive Write-ups & Webinars by KOLs
-
Daily Quiz by specialty
-
Paid Market Research Surveys
-
Case discussions, News & Journals' summaries