Automatic Detection of Diabetic Retinopathy in Retinal Fundus Photographs Based on Deep Learning Algorithm

Feng Li; Zheng Liu; Hua Chen; Minshan Jiang; Xuedian Zhang; Zhizheng Wu

doi:10.1167/tvst.8.6.4

Automatic Detection of Diabetic Retinopathy in Retinal Fundus Photographs Based on Deep Learning Algorithm

Transl Vis Sci Technol. 2019 Nov 12;8(6):4. doi: 10.1167/tvst.8.6.4. eCollection 2019 Nov.

Authors

Feng Li¹, Zheng Liu¹, Hua Chen¹, Minshan Jiang¹, Xuedian Zhang¹, Zhizheng Wu²

Affiliations

¹ School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China.
² Department of Precision Mechanical Engineering, Shanghai University, Shanghai 200072, China.

Abstract

Purpose: To achieve automatic diabetic retinopathy (DR) detection in retinal fundus photographs through the use of a deep transfer learning approach using the Inception-v3 network.

Methods: A total of 19,233 eye fundus color numerical images were retrospectively obtained from 5278 adult patients presenting for DR screening. The 8816 images passed image-quality review and were graded as no apparent DR (1374 images), mild nonproliferative DR (NPDR) (2152 images), moderate NPDR (2370 images), severe NPDR (1984 images), and proliferative DR (PDR) (936 images) by eight retinal experts according to the International Clinical Diabetic Retinopathy severity scale. After image preprocessing, 7935 DR images were selected from the above categories as a training dataset, while the rest of the images were used as validation dataset. We introduced a 10-fold cross-validation strategy to assess and optimize our model. We also selected the publicly independent Messidor-2 dataset to test the performance of our model. For discrimination between no referral (no apparent DR and mild NPDR) and referral (moderate NPDR, severe NPDR, and PDR), we also computed prediction accuracy, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and κ value.

Results: The proposed approach achieved a high classification accuracy of 93.49% (95% confidence interval [CI], 93.13%-93.85%), with a 96.93% sensitivity (95% CI, 96.35%-97.51%) and a 93.45% specificity (95% CI, 93.12%-93.79%), while the AUC was up to 0.9905 (95% CI, 0.9887-0.9923) on the independent test dataset. The κ value of our best model was 0.919, while the three experts had κ values of 0.906, 0.931, and 0.914, independently.

Conclusions: This approach could automatically detect DR with excellent sensitivity, accuracy, and specificity and could aid in making a referral recommendation for further evaluation and treatment with high reliability.

Translational relevance: This approach has great value in early DR screening using retinal fundus photographs.

Keywords: Inception-v3 network; deep transfer learning; diabetic retinopathy; retinal fundus photographs.