Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey

Diabetic retinopathy (DR) is a microvascular disease that is associated with diabetes mellitus. DR can cause irreversible vision loss and low vision. DR classification, that is, early DR diagnosis and accurate DR grading, is critical for vision protection and immediate treatment. Deep learning-based...

Full description

Saved in:
Bibliographic Details
Main Authors: Shanshan Zhu, Changchun Xiong, Qingshan Zhong, Yudong Yao
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10419327/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850062958425538560
author Shanshan Zhu
Changchun Xiong
Qingshan Zhong
Yudong Yao
author_facet Shanshan Zhu
Changchun Xiong
Qingshan Zhong
Yudong Yao
author_sort Shanshan Zhu
collection DOAJ
description Diabetic retinopathy (DR) is a microvascular disease that is associated with diabetes mellitus. DR can cause irreversible vision loss and low vision. DR classification, that is, early DR diagnosis and accurate DR grading, is critical for vision protection and immediate treatment. Deep learning-based automated systems led to significant expectations for DR classification based on fundus images with several advantages. In the past several years, many outstanding studies in this area have been conducted and several review articles have been published. However, the new trends and the future directions are need to furtherly analyzed. Thus, we carefully included and read 94 related articles published from 2018 to 2023 through Web of Science, PubMed, Scopus, and IEEE Xplore. From this review, we found that transfer learning has been used as an outstanding strategy for overcoming the issue of the limited data resources to support DR analysis. CNN models of ResNet and VGGNet with layers of tens or even hundreds are the most popular frameworks used for DR classification. The APTOS 2019 and EyePACS are the most widely used datasets for DR classification. In addition, some lightweight DL architectures like SqueezeNet and MobileNet have been proposed for DR classification tasks, especially for limited data resources and computational capabilities. Although deep learning has achieved or surpassed human-level accuracy in DR classification, there is still a long way to go in real clinical workflows. Further improvements in model interpretability, trustworthiness from ophthalmologists, cost-effective and reliable DR screening systems are needed.
format Article
id doaj-art-d0465359842441f192e883163ba6dde6
institution DOAJ
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-d0465359842441f192e883163ba6dde62025-08-20T02:49:47ZengIEEEIEEE Access2169-35362024-01-0112205402055810.1109/ACCESS.2024.336194410419327Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short SurveyShanshan Zhu0https://orcid.org/0000-0001-9265-8595Changchun Xiong1Qingshan Zhong2Yudong Yao3https://orcid.org/0000-0003-3868-0593Research Institute of Medical and Biological Engineering, Ningbo University, Ningbo, ChinaFaculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, ChinaSchool of Materials Science and Chemical Engineering, Ningbo University, Ningbo, ChinaResearch Institute of Medical and Biological Engineering, Ningbo University, Ningbo, ChinaDiabetic retinopathy (DR) is a microvascular disease that is associated with diabetes mellitus. DR can cause irreversible vision loss and low vision. DR classification, that is, early DR diagnosis and accurate DR grading, is critical for vision protection and immediate treatment. Deep learning-based automated systems led to significant expectations for DR classification based on fundus images with several advantages. In the past several years, many outstanding studies in this area have been conducted and several review articles have been published. However, the new trends and the future directions are need to furtherly analyzed. Thus, we carefully included and read 94 related articles published from 2018 to 2023 through Web of Science, PubMed, Scopus, and IEEE Xplore. From this review, we found that transfer learning has been used as an outstanding strategy for overcoming the issue of the limited data resources to support DR analysis. CNN models of ResNet and VGGNet with layers of tens or even hundreds are the most popular frameworks used for DR classification. The APTOS 2019 and EyePACS are the most widely used datasets for DR classification. In addition, some lightweight DL architectures like SqueezeNet and MobileNet have been proposed for DR classification tasks, especially for limited data resources and computational capabilities. Although deep learning has achieved or surpassed human-level accuracy in DR classification, there is still a long way to go in real clinical workflows. Further improvements in model interpretability, trustworthiness from ophthalmologists, cost-effective and reliable DR screening systems are needed.https://ieeexplore.ieee.org/document/10419327/Classificationdiabetic retinopathydeep learningfundus images
spellingShingle Shanshan Zhu
Changchun Xiong
Qingshan Zhong
Yudong Yao
Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey
IEEE Access
Classification
diabetic retinopathy
deep learning
fundus images
title Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey
title_full Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey
title_fullStr Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey
title_full_unstemmed Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey
title_short Diabetic Retinopathy Classification With Deep Learning via Fundus Images: A Short Survey
title_sort diabetic retinopathy classification with deep learning via fundus images a short survey
topic Classification
diabetic retinopathy
deep learning
fundus images
url https://ieeexplore.ieee.org/document/10419327/
work_keys_str_mv AT shanshanzhu diabeticretinopathyclassificationwithdeeplearningviafundusimagesashortsurvey
AT changchunxiong diabeticretinopathyclassificationwithdeeplearningviafundusimagesashortsurvey
AT qingshanzhong diabeticretinopathyclassificationwithdeeplearningviafundusimagesashortsurvey
AT yudongyao diabeticretinopathyclassificationwithdeeplearningviafundusimagesashortsurvey