Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy

• Published in: Translational vision science & technology Vol. 9; no. 2; p. 35
• Main Authors: Le, David, Alam, Minhaj, Yao, Cham K., Lim, Jennifer I., Hsieh, Yi-Ting, Chan, Robison V. P., Toslak, Devrim, Yao, Xincheng
• Format: Journal Article
• Language: English
• Published: United States The Association for Research in Vision and Ophthalmology 02.07.2020
• Subjects: Angiography; Artificial Intelligence; Diabetes Mellitus; Diabetic Retinopathy - diagnosis; Humans; Machine Learning; Retinal Vessels; Special Issue; Tomography, Optical Coherence; deep learning; detection; screening; diabetic retinopathy; artificial intelligence
• ISSN: 2164-2591; 2164-2591
• DOI: 10.1167/tvst.9.2.35

To test the feasibility of using deep learning for optical coherence tomography angiography (OCTA) detection of diabetic retinopathy. A deep-learning convolutional neural network (CNN) architecture, VGG16, was employed for this study. A transfer learning process was implemented to retrain the CNN for robust OCTA classification. One dataset, consisting of images of 32 healthy eyes, 75 eyes with diabetic retinopathy (DR), and 24 eyes with diabetes but no DR (NoDR), was used for training and cross-validation. A second dataset consisting of 20 NoDR and 26 DR eyes was used for external validation. To demonstrate the feasibility of using artificial intelligence (AI) screening of DR in clinical environments, the CNN was incorporated into a graphical user interface (GUI) platform. With the last nine layers retrained, the CNN architecture achieved the best performance for automated OCTA classification. The cross-validation accuracy of the retrained classifier for differentiating among healthy, NoDR, and DR eyes was 87.27%, with 83.76% sensitivity and 90.82% specificity. The AUC metrics for binary classification of healthy, NoDR, and DR eyes were 0.97, 0.98, and 0.97, respectively. The GUI platform enabled easy validation of the method for AI screening of DR in a clinical environment. With a transfer learning process for retraining, a CNN can be used for robust OCTA classification of healthy, NoDR, and DR eyes. The AI-based OCTA classification platform may provide a practical solution to reducing the burden of experienced ophthalmologists with regard to mass screening of DR patients. Deep-learning-based OCTA classification can alleviate the need for manual graders and improve DR screening efficiency.