TY - JOUR
T1 - A deep learning system for detecting diabetic retinopathy across the disease spectrum
AU - Dai, Ling
AU - Wu, Liang
AU - Li, Huating
AU - Cai, Chun
AU - Wu, Qiang
AU - Kong, Hongyu
AU - Liu, Ruhan
AU - Wang, Xiangning
AU - Hou, Xuhong
AU - Liu, Yuexing
AU - Long, Xiaoxue
AU - Wen, Yang
AU - Lu, Lina
AU - Shen, Yaxin
AU - Chen, Yan
AU - Shen, Dinggang
AU - Yang, Xiaokang
AU - Zou, Haidong
AU - Sheng, Bin
AU - Jia, Weiping
N1 - Publisher Copyright:
© 2021, The Author(s).
PY - 2021/12/1
Y1 - 2021/12/1
N2 - Retinal screening contributes to early detection of diabetic retinopathy and timely treatment. To facilitate the screening process, we develop a deep learning system, named DeepDR, that can detect early-to-late stages of diabetic retinopathy. DeepDR is trained for real-time image quality assessment, lesion detection and grading using 466,247 fundus images from 121,342 patients with diabetes. Evaluation is performed on a local dataset with 200,136 fundus images from 52,004 patients and three external datasets with a total of 209,322 images. The area under the receiver operating characteristic curves for detecting microaneurysms, cotton-wool spots, hard exudates and hemorrhages are 0.901, 0.941, 0.954 and 0.967, respectively. The grading of diabetic retinopathy as mild, moderate, severe and proliferative achieves area under the curves of 0.943, 0.955, 0.960 and 0.972, respectively. In external validations, the area under the curves for grading range from 0.916 to 0.970, which further supports the system is efficient for diabetic retinopathy grading.
AB - Retinal screening contributes to early detection of diabetic retinopathy and timely treatment. To facilitate the screening process, we develop a deep learning system, named DeepDR, that can detect early-to-late stages of diabetic retinopathy. DeepDR is trained for real-time image quality assessment, lesion detection and grading using 466,247 fundus images from 121,342 patients with diabetes. Evaluation is performed on a local dataset with 200,136 fundus images from 52,004 patients and three external datasets with a total of 209,322 images. The area under the receiver operating characteristic curves for detecting microaneurysms, cotton-wool spots, hard exudates and hemorrhages are 0.901, 0.941, 0.954 and 0.967, respectively. The grading of diabetic retinopathy as mild, moderate, severe and proliferative achieves area under the curves of 0.943, 0.955, 0.960 and 0.972, respectively. In external validations, the area under the curves for grading range from 0.916 to 0.970, which further supports the system is efficient for diabetic retinopathy grading.
UR - http://www.scopus.com/inward/record.url?scp=85106991784&partnerID=8YFLogxK
U2 - 10.1038/s41467-021-23458-5
DO - 10.1038/s41467-021-23458-5
M3 - Article
C2 - 34050158
AN - SCOPUS:85106991784
SN - 2041-1723
VL - 12
JO - Nature communications
JF - Nature communications
IS - 1
M1 - 3242
ER -