A deep learning system for detecting diabetic retinopathy across the disease spectrum

doi:10.1038/s41467-021-23458-5

	A deep learning system for detecting diabetic retinopathy across the disease spectrum
	Dai, Ling 1,2,3; Wu, Liang 2; Li, Huating 2; Cai, Chun 2; Wu, Qiang 4; Kong, Hongyu 4; Liu, Ruhan 1,3; Wang, Xiangning 4; Hou, Xuhong 2; Liu, Yuexing 2; Long, Xiaoxue 2; Wen, Yang 1,3; Lu, Lina 5; Shen, Yaxin 1,3; Chen, Yan 4; Shen, Dinggang6,7 ; Yang, Xiaokang 8; Zou, Haidong 5; Sheng, Bin 1,3; Jia, Weiping 2
	2021-05-28
发表期刊	NATURE COMMUNICATIONS (IF:14.7[JCR-2023],16.1[5-Year])
ISSN	2041-1723
卷号	12 期号:1
DOI	10.1038/s41467-021-23458-5
摘要	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. As the leading cause of vision loss in working-age adults, diabetic retinopathy requires routinely retinal screening. Here the authors develop a deep learning system that can facilitate the screening by providing real-time image quality assessment, lesions detection, and grades across the disease spectrum.
URL	查看原文
收录类别	SCIE
语种	英语
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:000659145000027
出版者	NATURE RESEARCH
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/127578
专题	生物医学工程学院_PI研究组_沈定刚组
通讯作者	Zou, Haidong; Sheng, Bin; Jia, Weiping
作者单位	1.Shanghai Jiao Tong Univ, Dept Comp Sci & Engn, Shanghai 200240, Peoples R China; 2.Shanghai Jiao Tong Univ Affiliated Peoples Hosp 6, Shanghai Clin Ctr Diabet, Shanghai Diabet Inst, Dept Endocrinol & Metab, Shanghai 200233, Peoples R China; 3.Shanghai Jiao Tong Univ, Artificial Intelligence Inst, MoE Key Lab Artificial Intelligence, Shanghai 200240, Peoples R China; 4.Shanghai Jiao Tong Univ Affiliated Peoples Hosp 6, Dept Ophthalmol, Shanghai 200233, Peoples R China; 5.Shanghai Jiao Tong Univ, Shanghai Engn Ctr Precise Diag & Treatment Eye Di, Shanghai Eye Dis Prevent & Treatment Ctr, Shanghai Eye Hosp,Shanghai Gen Hosp,Dept Ophthalm, Shanghai 200040, Peoples R China; 6.Shanghai Tech Univ, Sch Biomed Engn, Shanghai, Peoples R China; 7.Shanghai United Imaging Intelligence Co Ltd, Shanghai, Peoples R China; 8.Shanghai Jiao Tong Univ, Shanghai Inst Adv Commun & Data Sci, Shanghai Key Lab Digital Media Proc & Transmiss, Shanghai 200240, Peoples R China
推荐引用方式 GB/T 7714	Dai, Ling,Wu, Liang,Li, Huating,et al. A deep learning system for detecting diabetic retinopathy across the disease spectrum[J]. NATURE COMMUNICATIONS,2021,12(1).
APA	Dai, Ling.,Wu, Liang.,Li, Huating.,Cai, Chun.,Wu, Qiang.,...&Jia, Weiping.(2021).A deep learning system for detecting diabetic retinopathy across the disease spectrum.NATURE COMMUNICATIONS,12(1).
MLA	Dai, Ling,et al."A deep learning system for detecting diabetic retinopathy across the disease spectrum".NATURE COMMUNICATIONS 12.1(2021).