As the prevalence of diabetes increases, millions of people need to be screened for diabetic retinopathy (DR). Remarkable advances in technology have made it possible to use artificial intelligence to screen DR from retinal images with high accuracy and reliability, resulting in reducing human labor by processing large amounts of data in a shorter time. We developed a fully automated classification algorithm to diagnose DR and identify referable status using optical coherence tomography angiography (OCTA) images with convolutional neural network (CNN) model and verified its feasibility by comparing its performance with that of conventional machine learning model. Ground truths for classifications were made based on ultra-widefield fluorescein angiography to increase the accuracy of data annotation. The proposed CNN classifier achieved an accuracy of 91–98%, a sensitivity of 86–97%, a specificity of 94–99%, and an area under the curve of 0.919–0.976. In the external validation, overall similar performances were also achieved. The results were similar regardless of the size and depth of the OCTA images, indicating that DR could be satisfactorily classified even with images comprising narrow area of the macular region and a single image slab of retina. The CNN-based classification using OCTA is expected to create a novel diagnostic workflow for DR detection and referral.

This paper aims to compare the effects of three treatment modalities for a submacular hemorrhage (SMH) secondary to exudative age-related macular degeneration (AMD). Seventy-seven patients with an SMH were divided into three groups: small-sized (optic disc diameter (ODD) ≥ 1 to < 4), medium-sized (ODD ≥ 4 within the temporal arcade) and large-sized (ODD ≥ 4, exceeding the temporal arcade). Patients received anti-vascular endothelial growth factor (anti-VEGF) monotherapy, pneumatic displacement (PD) with anti-VEGF or a vitrectomy with a subretinal tissue plasminogen activator (tPA) and gas tamponade based on the surgeon’s discretion. The functional and anatomical outcomes were evaluated. Among the 77 eyes, 45 eyes had a small-sized, 21 eyes had a medium-sized and 11 eyes had a large-sized SMH. In the small-sized group, all treatment modalities showed a gradual best-corrected visual acuity (BCVA) improvement with high hemorrhagic regression or displacement rates (over 75%). In the medium-sized group, PD and surgery were associated with better BCVA with more displacement than anti-VEGF monotherapy (67% and 83%, respectively, vs. 33%). In the large-sized group, surgery showed a better visual improvement with a higher displacement rate than PD (86% vs. 25%). Our findings demonstrated that visual improvement can be expected through appropriate treatment strategy regardless of the SMH size. In cases with a larger SMH, invasive techniques including PD or surgery were more advantageous than anti-VEGF monotherapy.

Purpose: To develop an automated diabetic retinopathy (DR) staging system using optical coherence tomography angiography (OCTA) images with a convolutional neural network (CNN) and to verify the feasibility of the system. Methods: In this retrospective cross-sectional study, a total of 918 data sets of 3 × 3 mm² OCTA images and 917 data sets of 6 × 6 mm² OCTA images were obtained from 1118 eyes. A deep CNN and four traditional machine learning models were trained with annotations made by a retinal specialist based on ultra-widefield fluorescein angiography. Separately, the same images of the test data sets were independently graded by two human experts. The results of the CNN algorithm were compared with those of traditional machine learning–based classifiers and human experts. Results: The proposed CNN achieved an accuracy of 0.728, a sensitivity of 0.675, a specificity of 0.944, an F1 score of 0.683, and a quadratic weighted κ of 0.908 for a six-level staging task, which were far superior to the results of traditional machine learning methods or human experts. The CNN algorithm showed a better performance using 6 × 6 mm² rather than 3 × 3 mm² sized OCTA images and using combined data rather than a separate OCTA layer alone. Conclusions: CNN-based classification using OCTA images can provide reliable assistance to clinicians for DR classification. Translational Relevance: This CNN algorithm can guide the clinical decision for invasive angiography or referrals to ophthalmology specialists, helping to create more efficient diagnostic workflow in primary care settings.