To develop and evaluate deep learning models that screen multiple abnormal findings in retinal fundus images. Cross-sectional study. For the development and testing of deep learning models, 309 786 readings from 103 262 images were used. Two additional external datasets (the Indian Diabetic Retinopathy Image Dataset and e-ophtha) were used for testing. A third external dataset (Messidor) was used for comparison of the models with human experts. Macula-centered retinal fundus images from the Seoul National University Bundang Hospital Retina Image Archive, obtained at the health screening center and ophthalmology outpatient clinic at Seoul National University Bundang Hospital, were assessed for 12 major findings (hemorrhage, hard exudate, cotton-wool patch, drusen, membrane, macular hole, myelinated nerve fiber, chorioretinal atrophy or scar, any vascular abnormality, retinal nerve fiber layer defect, glaucomatous disc change, and nonglaucomatous disc change) with their regional information using deep learning algorithms. Area under the receiver operating characteristic curve and sensitivity and specificity of the deep learning algorithms at the highest harmonic mean were evaluated and compared with the performance of retina specialists, and visualization of the lesions was qualitatively analyzed. Areas under the receiver operating characteristic curves for all findings were high at 96.2% to 99.9% when tested in the in-house dataset. Lesion heatmaps highlight salient regions effectively in various findings. Areas under the receiver operating characteristic curves for diabetic retinopathy-related findings tested in the Indian Diabetic Retinopathy Image Dataset and e-ophtha dataset were 94.7% to 98.0%. The model demonstrated a performance that rivaled that of human experts, especially in the detection of hemorrhage, hard exudate, membrane, macular hole, myelinated nerve fiber, and glaucomatous disc change. Our deep learning algorithms with region guidance showed reliable performance for detection of multiple findings in macula-centered retinal fundus images. These interpretable, as well as reliable, classification outputs open the possibility for clinical use as an automated screening system for retinal fundus images.

To define the incidence and demographic characteristics of rhegmatogenous retinal detachment (RRD) requiring surgery in Korea. Nationwide population-based retrospective study. Patients who underwent surgery for RRD from 2007 to 2011 were retrospectively identified using the diagnostic code for RRD and the surgical codes for retinal detachment surgeries in the national claim database. The average incidence rate of RRD during the 5-year period was estimated using the population data of the 2010 Census in Korea. A total of 24,928 surgically treated RRD cases were identified. The average incidence of surgery requiring RRD was 10.39 cases per 100,000 person-years [95% confidence interval (CI), 10.26–10.52). The incidence in men (11.32 cases per 100,000 person-years; 95% CI: 11.13–11.51) was significantly higher than that in women (9.47 cases per 100,000 person-years; 95% CI: 9.29–9.64) (p<0.001). The incidence of surgery requiring RRD showed a bimodal distribution across age groups, with one peak (28.55 cases per 100,000 person-years; 95% CI: 27.46–29.67) representing patients between 65 and 69 years of age and the second peak (approximately 8.5 per 100,000 person-years) representing patients between 20 and 29 years of age. The male-to-female ratio was approximately 1.0 for the peak-incidence age groups, whereas the ratio was higher for the other age groups. The incidence of RRD in the Korean population was similar to that reported previously, with the peak incidence being lower than that in the Caucasian population. The age-specific RRD incidence pattern in Korea followed a bimodal distribution.