Journal article
An automated grading system for detection of vision-threatening referable diabetic retinopathy on the basis of color fundus photographs
Z Li, S Keel, C Liu, Y He, W Meng, J Scheetz, PY Lee, J Shaw, D Ting, TY Wong, H Taylor, R Chang, M He
Diabetes Care | AMER DIABETES ASSOC | Published : 2018
DOI: 10.2337/dc18-0147
Abstract
OBJECTIVE The goal of this study was to describe the development and validation of an artificial intelligence-based, deep learning algorithm (DLA) for the detection of referable diabetic retinopathy (DR). RESEARCH DESIGN AND METHODS A DLA using a convolutional neural network was developed for automated detection of vision-threatening referable DR (preproliferative DR or worse, diabetic macular edema, or both). The DLA was tested by using a set of 106,244 nonstereoscopic retinal images. A panel of ophthalmologists graded DR severity in retinal photographs included in the development and internal validation data sets (n = 71,043); a reference standard grading was assigned once three graders ac..
View full abstractGrants
Awarded by National Health and Medical Research Council
Funding Acknowledgements
This study was supported in part by the Fundamental Research Funds of the State Key Laboratory of Ophthalmology, National Natural Science Foundation of China (grant no. 81420108008); the Science and Technology Planning Project of Guangdong Province (grant no. 2013B20400003); and the Bupa Health Foundation (Australia grant). J.Sh. is supported by a research fellowship from the National Health and Medical Research Council. M.H. receives support from the Research Accelerator Program at the University of Melbourne and from the CERA Foundation. The Centre for Eye Research Australia receives operational infrastructure support from the Victorian State Government, and Research to Prevent Blindness, Inc., provides support to the Stanford University Department of Ophthalmology. The sponsor or funding organizations had no role in the design or conduct of this research.