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

Ling Dai, Liang Wu, Huating Li, Chun Cai, Qiang Wu, Hongyu Kong, Ruhan Liu, Xiangning Wang, Xuhong Hou, Yuexing Liu, Xiaoxue Long, Yang Wen, Lina Lu, Yaxin Shen, Yan Chen, Dinggang Shen, Xiaokang Yang, Haidong Zou (), Bin Sheng () and Weiping Jia ()
Additional contact information
Ling Dai: Shanghai Jiao Tong University
Liang Wu: Shanghai Clinical Center for Diabetes
Huating Li: Shanghai Clinical Center for Diabetes
Chun Cai: Shanghai Clinical Center for Diabetes
Qiang Wu: Shanghai Jiao Tong University Affiliated Sixth People’s Hospital
Hongyu Kong: Shanghai Jiao Tong University Affiliated Sixth People’s Hospital
Ruhan Liu: Shanghai Jiao Tong University
Xiangning Wang: Shanghai Jiao Tong University Affiliated Sixth People’s Hospital
Xuhong Hou: Shanghai Clinical Center for Diabetes
Yuexing Liu: Shanghai Clinical Center for Diabetes
Xiaoxue Long: Shanghai Clinical Center for Diabetes
Yang Wen: Shanghai Jiao Tong University
Lina Lu: Shanghai Engineering Center for Precise Diagnosis and Treatment of Eye Diseases
Yaxin Shen: Shanghai Jiao Tong University
Yan Chen: Shanghai Jiao Tong University Affiliated Sixth People’s Hospital
Dinggang Shen: Shanghai Tech University
Xiaokang Yang: Shanghai Jiao Tong University
Haidong Zou: Shanghai Engineering Center for Precise Diagnosis and Treatment of Eye Diseases
Bin Sheng: Shanghai Jiao Tong University
Weiping Jia: Shanghai Clinical Center for Diabetes

Nature Communications, 2021, vol. 12, issue 1, 1-11

Abstract: Abstract 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.

Date: 2021
References: Add references at CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
https://www.nature.com/articles/s41467-021-23458-5 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:12:y:2021:i:1:d:10.1038_s41467-021-23458-5

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-021-23458-5

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().