AUTHOR=Huang Xuan , Wang Hui , She Chongyang , Feng Jing , Liu Xuhui , Hu Xiaofeng , Chen Li , Tao Yong 

TITLE=Artificial intelligence promotes the diagnosis and screening of diabetic retinopathy

JOURNAL=Frontiers in Endocrinology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/endocrinology/articles/10.3389/fendo.2022.946915

DOI=10.3389/fendo.2022.946915

ISSN=1664-2392

ABSTRACT=Deep learning is a new branch of machine learning technology under the broad term of artificial intelligence (AI), which has substantial potential for large-scale healthcare screening and may allow the determination of the most appropriate specific treatment for individual patient. Major advances in diagnostic technologies are offering unprecedented insight into the condition of the retina and beyond ocular disease in metabolism and endocrinology. Diabetic retinopathy (DR) is a leading cause of vision loss globally. Recent studies, including retrospective and pre-registered prospective clinical trials, have shown deep learning systems are accurate and effective in detecting DR from digital fundus photographs or optical coherence tomography. Thus, using AI techniques, highly accurate and efficient systems can be developed to help assist medical professionals in screening and diagnosing DR at an earlier stage and without the full resources that are only available in specialty clinics. In particular, deep learning facilitates diagnosis earlier and with higher sensitivity and specificity, which makes decisions based on minimally handcrafted features paving the way for personalized DR progression real-time monitoring and in-time ophthalmic or endocrine therapies. This review will discuss the cutting-edge AI algorithms, automated detecting systems of DR stage grading and feature segmentation, prediction of DR outcomes and therapeutics, and ophthalmic indications of other systemic diseases revealed by AI.