Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysis

ObjectiveTo systematically review and meta-analyze the effectiveness of deep learning algorithms applied to optical coherence tomography (OCT) and retinal images for the detection of diabetic retinopathy (DR).MethodsWe conducted a comprehensive literature search in multiple databases including PubMe...

Full description

Saved in:
Bibliographic Details
Main Authors: Zheng Bi, Jinju Li, Qiongyi Liu, Zhaohui Fang
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-03-01
Series:Frontiers in Endocrinology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fendo.2025.1485311/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849773741252280320
author Zheng Bi
Jinju Li
Qiongyi Liu
Zhaohui Fang
Zhaohui Fang
author_facet Zheng Bi
Jinju Li
Qiongyi Liu
Zhaohui Fang
Zhaohui Fang
author_sort Zheng Bi
collection DOAJ
description ObjectiveTo systematically review and meta-analyze the effectiveness of deep learning algorithms applied to optical coherence tomography (OCT) and retinal images for the detection of diabetic retinopathy (DR).MethodsWe conducted a comprehensive literature search in multiple databases including PubMed, Cochrane library, Web of Science, Embase and IEEE Xplore up to July 2024. Studies that utilized deep learning techniques for the detection of DR using OCT and retinal images were included. Data extraction and quality assessment were performed independently by two reviewers. Meta-analysis was conducted to determine pooled sensitivity, specificity, and diagnostic odds ratios.ResultsA total of 47 studies were included in the systematic review, 10 were meta-analyzed, encompassing a total of 188268 retinal images and OCT scans. The meta-analysis revealed a pooled sensitivity of 1.88 (95% CI: 1.45-2.44) and a pooled specificity of 1.33 (95% CI: 0.97-1.84) for the detection of DR using deep learning models. All of the outcome of deep learning-based optical coherence tomography ORs ≥0.785, indicating that all included studies with artificial intelligence assistance produced good boosting results.ConclusionDeep learning-based approaches show high accuracy in detecting diabetic retinopathy from OCT and retinal images, supporting their potential as reliable tools in clinical settings. Future research should focus on standardizing datasets, improving model interpretability, and validating performance across diverse populations.Systematic Review Registrationhttps://www.crd.york.ac.uk/PROSPERO/, identifier CRD42024575847.
format Article
id doaj-art-074d3ed3475f4ea5a9be493c4fd47f86
institution DOAJ
issn 1664-2392
language English
publishDate 2025-03-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Endocrinology
spelling doaj-art-074d3ed3475f4ea5a9be493c4fd47f862025-08-20T03:01:58ZengFrontiers Media S.A.Frontiers in Endocrinology1664-23922025-03-011610.3389/fendo.2025.14853111485311Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysisZheng Bi0Jinju Li1Qiongyi Liu2Zhaohui Fang3Zhaohui Fang4Department of Endocrinology, The First Affiliated Hospital of Anhui University of Traditional Chinese Medicine, Hefei, Anhui, ChinaFirst Clinical Medical College, Anhui University of Traditional Chinese Medicine, Hefei, Anhui, ChinaFirst Clinical Medical College, Anhui University of Traditional Chinese Medicine, Hefei, Anhui, ChinaDepartment of Endocrinology, The First Affiliated Hospital of Anhui University of Traditional Chinese Medicine, Hefei, Anhui, ChinaXin ‘an Medical and Chinese Medicine Modernization Research Institute, Hefei Comprehensive National Science Center, Hefei, Anhui, ChinaObjectiveTo systematically review and meta-analyze the effectiveness of deep learning algorithms applied to optical coherence tomography (OCT) and retinal images for the detection of diabetic retinopathy (DR).MethodsWe conducted a comprehensive literature search in multiple databases including PubMed, Cochrane library, Web of Science, Embase and IEEE Xplore up to July 2024. Studies that utilized deep learning techniques for the detection of DR using OCT and retinal images were included. Data extraction and quality assessment were performed independently by two reviewers. Meta-analysis was conducted to determine pooled sensitivity, specificity, and diagnostic odds ratios.ResultsA total of 47 studies were included in the systematic review, 10 were meta-analyzed, encompassing a total of 188268 retinal images and OCT scans. The meta-analysis revealed a pooled sensitivity of 1.88 (95% CI: 1.45-2.44) and a pooled specificity of 1.33 (95% CI: 0.97-1.84) for the detection of DR using deep learning models. All of the outcome of deep learning-based optical coherence tomography ORs ≥0.785, indicating that all included studies with artificial intelligence assistance produced good boosting results.ConclusionDeep learning-based approaches show high accuracy in detecting diabetic retinopathy from OCT and retinal images, supporting their potential as reliable tools in clinical settings. Future research should focus on standardizing datasets, improving model interpretability, and validating performance across diverse populations.Systematic Review Registrationhttps://www.crd.york.ac.uk/PROSPERO/, identifier CRD42024575847.https://www.frontiersin.org/articles/10.3389/fendo.2025.1485311/fullmeta analysisdeep learningdiabetic retinopathyimage detectionoptical coherence tomography
spellingShingle Zheng Bi
Jinju Li
Qiongyi Liu
Zhaohui Fang
Zhaohui Fang
Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysis
Frontiers in Endocrinology
meta analysis
deep learning
diabetic retinopathy
image detection
optical coherence tomography
title Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysis
title_full Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysis
title_fullStr Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysis
title_full_unstemmed Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysis
title_short Deep learning-based optical coherence tomography and retinal images for detection of diabetic retinopathy: a systematic and meta analysis
title_sort deep learning based optical coherence tomography and retinal images for detection of diabetic retinopathy a systematic and meta analysis
topic meta analysis
deep learning
diabetic retinopathy
image detection
optical coherence tomography
url https://www.frontiersin.org/articles/10.3389/fendo.2025.1485311/full
work_keys_str_mv AT zhengbi deeplearningbasedopticalcoherencetomographyandretinalimagesfordetectionofdiabeticretinopathyasystematicandmetaanalysis
AT jinjuli deeplearningbasedopticalcoherencetomographyandretinalimagesfordetectionofdiabeticretinopathyasystematicandmetaanalysis
AT qiongyiliu deeplearningbasedopticalcoherencetomographyandretinalimagesfordetectionofdiabeticretinopathyasystematicandmetaanalysis
AT zhaohuifang deeplearningbasedopticalcoherencetomographyandretinalimagesfordetectionofdiabeticretinopathyasystematicandmetaanalysis
AT zhaohuifang deeplearningbasedopticalcoherencetomographyandretinalimagesfordetectionofdiabeticretinopathyasystematicandmetaanalysis