Artificial Intelligence for Screening of Multiple Retinal and Optic Nerve Diseases.

Importance: The lack of experienced ophthalmologists limits the early diagnosis of retinal diseases. Artificial intelligence can be an efficient real-time way for screening retinal diseases. Objective: To develop and prospectively validate a deep learning (DL) algorithm that, based on ocular fundus images, recognizes numerous retinal diseases simultaneously in clinical practice. Design, Setting, and Participants: This multicenter, diagnostic study at 65 public medical screening centers and hospitals in 19 Chinese provinces included individuals attending annual routine medical examinations and participants of population-based and community-based studies. Exposures: Based on 120 002 ocular fundus photographs, the Retinal Artificial Intelligence Diagnosis System (RAIDS) was developed to identify 10 retinal diseases. RAIDS was validated in a prospective collected data set, and the performance between RAIDS and ophthalmologists was compared in the data sets of the population-based Beijing Eye Study and the community-based Kailuan Eye Study. Main Outcomes and Measures: The performance of each classifier included sensitivity, specificity, accuracy, F1 score, and Cohen κ score. Results: In the prospective validation data set of 208 758 images collected from 110 784 individuals (median [range] age, 42 [8-87] years; 115 443 [55.3%] female), RAIDS achieved a sensitivity of 89.8% (95% CI, 89.5%-90.1%) to detect any of 10 retinal diseases. RAIDS differentiated 10 retinal diseases with accuracies ranging from 95.3% to 99.9%, without marked differences between medical screening centers and geographical regions in China. Compared with retinal specialists, RAIDS achieved a higher sensitivity for detection of any retinal abnormality (RAIDS, 91.7% [95% CI, 90.6%-92.8%]; certified ophthalmologists, 83.7% [95% CI, 82.1%-85.1%]; junior retinal specialists, 86.4% [95% CI, 84.9%-87.7%]; and senior retinal specialists, 88.5% [95% CI, 87.1%-89.8%]). RAIDS reached a superior or similar diagnostic sensitivity compared with senior retinal specialists in the detection of 7 of 10 retinal diseases (ie, referral diabetic retinopathy, referral possible glaucoma, macular hole, epiretinal macular membrane, hypertensive retinopathy, myelinated fibers, and retinitis pigmentosa). It achieved a performance comparable with the performance by certified ophthalmologists in 2 diseases (ie, age-related macular degeneration and retinal vein occlusion). Compared with ophthalmologists, RAIDS needed 96% to 97% less time for the image assessment. Conclusions and Relevance: In this diagnostic study, the DL system was associated with accurately distinguishing 10 retinal diseases in real time. This technology may help overcome the lack of experienced ophthalmologists in underdeveloped areas.

Retrospective analysis of secondary enucleation for uveal melanoma after plaque radiotherapy.

BACKGROUND: Uveal melanoma (UM) is the most common primary intraocular malignancy in adults. Plaque brachytherapy (PRT) is widely accepted as an effective globe-conserving treatment modality for UM. However, local treatment failure and complications lead to the enucleation of irradiated eyes. We conducted this study to explore the causes and long-term prognosis for UM patients who accepted secondary enucleation after plaque radiotherapy. METHODS: This was a retrospective cohort study. Data of patients who underwent secondary enucleation for UM after plaque radiotherapy, from July 2007 to July 2019, at Beijing Tongren Hospital were analyzed. Kaplan-Meier analysis was performed to assess the probability of indications, metastasis, and metastasis-related death. Cox regression analysis was used to analyze associations of the prognostic factors. RESULTS: Eight hundred and eighty patients were clinically diagnosed with uveal melanoma and initially treated by iodine-125 plaque radiotherapy, 132 of whom underwent secondary enucleation and pathological examination in the same hospital. Fifty-two (39.4%) eyes were enucleated simply because of uncontrollable neovascular glaucoma (NVG). Forty-four (33.3%) patients suffered from tumor recurrence. Tumor non-response occurred in 18 (13.6%) cases. Ten (7.6%) eyes received enucleation entirely due to other types of glaucoma. Failure to preserve the eyes for other reasons occurred in eight (6.1%) patients. At a median follow-up of 58.1 [IQR: 40.9-90.5] months, the systemic spread was detected in 45 (34.1%) patients, and 38 of them died. On multivariate analysis, tumor largest basal diameter (HR 1.15 [95% CI: 1.01, 1.31]), tumor non-response (HR 7.22 [95% CI: 2.63, 19.82]), and recurrence (HR 3.29 [95% CI: 1.54, 7.07]) were risk factors for metastasis. Increased age (HR 1.54 [95% CI: 1.07, 2.23]), tumor non-response (HR 7.91 [95% CI: 2.79, 22.48]), and recurrence (HR 3.08 [95% CI: 1.13, 7.23]) were risk factors for metastasis-related death. CONCLUSIONS: NVG was the major reason for secondary enucleation for Chinese UM patients after PRT. Tumor non-response and recurrence were associated with a significantly higher risk of long-term metastasis and metastasis-related death.