Retinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

Key Points Question Can deep learning algorithms achieve a performance comparable with that of ophthalmologists on multidimensional identification of retinopathy of prematurity (ROP) using wide-field retinal images? Findings In this diagnostic study of 14 108 eyes of 8652 preterm infants, a deep learning–based ROP screening platform could identify retinal images using 5 classifiers, including image quality, stages of ROP, intraocular hemorrhage, preplus/plus disease, and posterior retina. The platform achieved an area under the curve of 0.983 to 0.998, and the referral system achieved an area under the curve of 0.9901 to 0.9956; the platform achieved a Cohen κ of 0.86 to 0.98 compared with 0.93 to 0.98 by the ROP experts. Meaning Results suggest that a deep learning platform could identify and classify multidimensional ROP pathological lesions in retinal images with high accuracy and could be suitable for routine ROP screening in general and children’s hospitals.

Purpose Nattokinase (NK), an active ingredient extracted from traditional food Natto, has been studied for prevention and treatment of cardiovascular diseases due to various vasoprotective effects, including fibrinolytic, antihypertensive, anti-atherosclerotic, antiplatelet, and anti-inflammatory activities. Here, we reported an antineovascular effect of NK against experimental retinal neovascularization. Methods The inhibitory effect of NK against retinal neovascularization was evaluated using an oxygen-induced retinopathy murine model. Expressions of Nrf2/HO-1 signaling and glial activation in the NK-treated retinae were measured. We also investigated cell proliferation and migration of human umbilical vein endothelial cells (HUVECs) after NK administration. Results NK treatment significantly attenuated retinal neovascularization in the OIR retinae. Consistently, NK suppressed VEGF-induced cell proliferation and migration in a concentration-dependent manner in cultured vascular endothelial cells. NK ameliorated ischemic retinopathy partially via activating Nrf2/HO-1. In addition, NK orchestrated reactive gliosis and promoted microglial activation toward a reparative phenotype in ischemic retina. Treatment of NK exhibited no cell toxicity or anti-angiogenic effects in the normal retina. Conclusions Our results revealed the anti-angiogenic effect of NK against retinal neovascularization via modulating Nrf2/HO-1, glial activation and neuroinflammation, suggesting a promising alternative treatment strategy for retinal neovascularization.