Galen medical journal · 2025
Narrative Review of Artificial Intelligence in Ophthalmic Disease Detection : Artificial Intelligence in Ophthalmic Diseases Detection.
СтатьяОбзорНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Bokhary Kholoud Ahmad
Аннотация
BACKGROUND: Artificial intelligence (AI) is revolutionizing ophthalmology and optometry by utilizing high-resolution imaging modalities such as optical coherence tomography (OCT), fundus photography, and corneal topography. These modalities generate quantifiable data suitable for machine learning (ML), facilitating automated diagnosis of ocular conditions like diabetic retinopathy, glaucoma, and age-related macular degeneration (AMD), which are leading causes of visual impairment worldwide. This narrative review evaluates the role of ML in improving diagnostic accuracy and accessibility in eye care, focusing on methodological complexities, supervised and unsupervised learning approaches, and challenges in clinical integration.
MATERIALS AND METHODS: A comprehensive narrative literature review was conducted, analyzing ML applications in ophthalmology.
RESULTS: AI systems exhibit high sensitivity and specificity, often outperforming human graders in diabetic retinopathy screening and early detection of glaucoma and AMD using OCT and fundus imaging. Anterior segment diseases benefit from AI-driven corneal topography analysis. Challenges include image quality, dataset imbalances, and variability in imaging protocols, necessitating fine-tuning for diverse clinical environments. Unsupervised learning shows potential for identifying novel biomarkers but requires further validation.
CONCLUSION: AI-driven ML models significantly enhance eye disease diagnostics, improving accuracy and accessibility, particularly in resource-limited settings. However, challenges like data standardization and model generalizability must be addressed to ensure robust clinical adoption.
MATERIALS AND METHODS: A comprehensive narrative literature review was conducted, analyzing ML applications in ophthalmology.
RESULTS: AI systems exhibit high sensitivity and specificity, often outperforming human graders in diabetic retinopathy screening and early detection of glaucoma and AMD using OCT and fundus imaging. Anterior segment diseases benefit from AI-driven corneal topography analysis. Challenges include image quality, dataset imbalances, and variability in imaging protocols, necessitating fine-tuning for diverse clinical environments. Unsupervised learning shows potential for identifying novel biomarkers but requires further validation.
CONCLUSION: AI-driven ML models significantly enhance eye disease diagnostics, improving accuracy and accessibility, particularly in resource-limited settings. However, challenges like data standardization and model generalizability must be addressed to ensure robust clinical adoption.