A deep-learning system to classify diabetic macular edema
Diabetic macular edema (DME) is a complication of diabetes. Existing international guidelines and national programmes run mostly on 2D retinal fundus photographs which have limited performance in screening DME. This study developed and validated a novel deep learning system for the fully automated classification of DME based on both 3D and 2D images. It showed excellent performance in detecting DME across diverse study populations which indicated its potential as a promising second-line screening tool for patients with diabetes mellitus. (Diabetes Care. 2021 Jul 27;dc203064. doi: 10.2337/dc20-3064. Online ahead of print.)
Anyone interested in future collaboration in this field of research is welcome to contact our key investigator Dr Carol CHEUNG from the Department of Ophthalmology and Visual Sciences, CUHK. Dr Cheung’s research focuses on using ocular imaging technology and artificial intelligence to study human circulation and nervous systems, and link with eye, brain and cardiovascular diseases, in particular, diabetic eye disease, glaucoma, Alzheimer’s disease and stroke.