Deep-learning-based Prediction of Late Age-Related Macular Degeneration Progression.

Both genetic and environmental factors influence the etiology of age-related macular degeneration (AMD), a leading cause of blindness. AMD severity is primarily measured by fundus images and recently developed machine learning methods can successfully predict AMD progression using image data. However, none of these methods have utilized both genetic and image data for predicting AMD progression. Here we jointly used genotypes and fundus images to predict an eye as having progressed to late AMD with a modified deep convolutional neural network (CNN). In total, we used 31,262 fundus images and 52 AMD-associated genetic variants from 1,351 subjects from the Age-Related Eye Disease Study (AREDS) with disease severity phenotypes and fundus images available at baseline and follow-up visits over a period of 12 years. Our results showed that fundus images coupled with genotypes could predict late AMD progression with an averaged area under the curve (AUC) value of 0.85 (95%CI: 0.83-0.86). The results using fundus images alone showed an averaged AUC of 0.81 (95%CI: 0.80-0.83). We implemented our model in a cloud-based application for individual risk assessment.

Lutein and zeaxanthin protect photoreceptors from apoptosis induced by oxidative stress: relation with docosahexaenoic acid.

PURPOSE: Oxidative stress has been proposed as a major pathogenic factor in age-related macular degeneration (AMD), the leading cause of vision loss among elderly people of western European ancestry. Lutein (LUT) and zeaxanthin (ZEA), major components in macular pigment, are among the retinal antioxidants. Though xanthophyll intake may reduce the likelihood of having advanced AMD, direct evidence of neuroprotection is lacking. Prior work has shown that docosahexaenoic acid (DHA), the major polyunsaturated fatty acid in the retina, delays apoptosis and promotes differentiation of photoreceptors. This study was conducted to investigate whether LUT, ZEA, and beta-carotene (BC), major dietary carotenoids protect photoreceptors from oxidative stress and whether this protection is synergistic with that of DHA. METHODS: Pure rat retinal neurons in culture, supplemented with LUT, ZEA, or BC, with or without DHA, were subjected to oxidative stress induced with paraquat and hydrogen peroxide. Apoptosis, preservation of mitochondrial membrane potential, cytochrome c translocation, and opsin expression were evaluated. RESULTS: Pretreatment with DHA, LUT, ZEA, and BC reduced oxidative stress-induced apoptosis in photoreceptors, preserved mitochondrial potential, and prevented cytochrome c release from mitochondria. ZEA and LUT also enhanced photoreceptor differentiation. In control cultures, photoreceptors failed to grow their characteristic outer segments; addition of DHA, ZEA, or LUT increased opsin expression and promoted the development of outer-segment-like processes. CONCLUSIONS: These results show for the first time the direct neuroprotection of photoreceptors by xanthophylls and suggest that ZEA and LUT, along with DHA, are important environmental influences that together promote photoreceptor survival and differentiation.