Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Jan 21;11(1):1897.
doi: 10.1038/s41598-021-81539-3.

Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images

Kangrok Oh #  1 , Hae Min Kang #  2 , Dawoon Leem  3 , Hyungyu Lee  3 , Kyoung Yul Seo  4 , Sangchul Yoon  5   6
Affiliations

Early detection of diabetic retinopathy based on deep learning and ultra-wide-field fundus images

Kangrok Oh et al. Sci Rep. .

Abstract

Visually impaired and blind people due to diabetic retinopathy were 2.6 million in 2015 and estimated to be 3.2 million in 2020 globally. Though the incidence of diabetic retinopathy is expected to decrease for high-income countries, detection and treatment of it in the early stages are crucial for low-income and middle-income countries. Due to the recent advancement of deep learning technologies, researchers showed that automated screening and grading of diabetic retinopathy are efficient in saving time and workforce. However, most automatic systems utilize conventional fundus photography, despite ultra-wide-field fundus photography provides up to 82% of the retinal surface. In this study, we present a diabetic retinopathy detection system based on ultra-wide-field fundus photography and deep learning. In experiments, we show that the use of early treatment diabetic retinopathy study 7-standard field image extracted from ultra-wide-field fundus photography outperforms that of the optic disc and macula centered image in a statistical sense.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
An overview of the proposed DR detection system.
Figure 2
Figure 2
The overall flow of the optic disc and macular detection process.
Figure 3
Figure 3
Sample images at each processing stages.
Figure 4
Figure 4
The ETDRS 7SF image segmentation process and sample images with noise.
Figure 5
Figure 5
The ResNet-34 model.
Figure 6
Figure 6
The ROC curves of the DR detection system using ETDRS 7SF and F1–F2 fundus images. Here, we note that the true positive rate and the false positive rate for plotting are obtained from a single running fold experiment among the entire cross-validation tests.
Figure 7
Figure 7
The DR detection performances of the system using ETDRS 7SF and F1–F2 fundus images in terms of accuracy, AUC, sensitivity, and specificity. For each metric, plots show the mean (marked with blue circle) and deviations (marked with blue bar).
Figure 8
Figure 8
Class activation maps generated from ETDRS 7SF and F1–F2 images for DR and normal class.
See this image and copyright information in PMC

References

    1. Leasher JL, et al. Global estimates on the number of people blind or visually impaired by diabetic retinopathy: A meta-analysis from 1990 to 2010. Diabetes Care. 2016;39:1643–1649. doi: 10.2337/dc15-2171. - DOI - PubMed
    1. International Diabetes Federation. Diabetes atlas. IDF Diabetes Atlas, 9th edn. (International Diabetes Federation, Brussels, 2015).
    1. Ting DSW, Cheung GCM, Wong TY. Diabetic retinopathy: Global prevalence, major risk factors, screening practices and public health challenges: A review. Clin. Exp. Ophthalmol. 2016;44:260–277. doi: 10.1111/ceo.12696. - DOI - PubMed
    1. Thomas, R., Halim, S., Gurudas, S., Sivaprasad, S. & Owens, D. Idf diabetes atlas: A review of studies utilising retinal photography on the global prevalence of diabetes related retinopathy between 2015 and 2018. Diabetes Research and Clinical Practice, p. 107840 (2019). - PubMed
    1. Early Treatment Diabetic Retinopathy Study Research Group. Grading diabetic retinopathy from stereoscopic color fundus photographs-an extension of the modified airlie house classification: Etdrs report number 10. Ophthalmology98, 786–806 (1991). - PubMed

Publication types

MeSH terms