{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T16:43:02Z","timestamp":1791650582650,"version":"4.3.4"},"reference-count":71,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Diabetic retinopathy (DR) is a leading cause of preventable visual impairment worldwide, and its precise severity grading is critical for optimizing clinical management. Conventional frameworks, notably the International Clinical Diabetic Retinopathy (ICDR) scale, are often hindered by substantial inter-observer variability and high dependency on specialist expertise. While deep learning (DL) has recently emerged as a transformative approach for automated stratification, a comprehensive synthesis of evidence regarding its diagnostic performance and clinical application remains lacking.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This systematic review and meta-analysis aimed to comprehensively assess the diagnostic accuracy of fundus image-based deep learning models in the grading of diabetic retinopathy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>PubMed, Embase, Web of Science, and the Cochrane Library were systematically searched for relevant studies published up to October 28, 2025. Diagnostic accuracy studies utilizing DL algorithms alongside ICDR criteria for diabetic retinopathy grading were included. Literature screening and data extraction were performed independently by two researchers, and the risk of bias was assessed using the QUADAS\u22122 tool.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 41 studies were included, encompassing various DL architectures and multiple public and private fundus image datasets. In the five-class classification task based on ICDR criteria, the pooled sensitivities of DL-based models varied significantly across severity levels: 95.19% (95% CI: 93.00%\u201397.00%) for no DR (stage 0), 72.06% (95% CI: 62.06%\u201381.09%) for mild NPDR (stage 1), 84.33% (95% CI: 78.90%\u201389.10%) for moderate NPDR (stage 2), 75.84% (95% CI: 68.42%\u201382.57%) for severe NPDR (stage 3), and 78.82% (95% CI: 71.76%\u201385.13%) for PDR (stage 4). In the simplified four-class classification task, sensitivities markedly improved across all grades: 96.85% (95% CI: 90.18%\u201399.93%) for stage 0, 92.94% (95% CI: 79.50%\u201399.72%) for stage 1, 92.75% (95% CI: 79.31%\u201399.61%) for stage 2, and 88.19% (95% CI: 68.99%\u201398.93%) for stage 3.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>DL exhibits high sensitivity and substantial potential for DR grading, particularly in screening for no DR and vision-threatening DR. Nevertheless, precisely differentiating between adjacent non-proliferative stages remains a clinical challenge. The observed heterogeneity underscores the imperative for methodological standardization, rigorous external validation, and multimodal data integration. Future research should prioritize enhancing clinical utility and generalizability to facilitate their translation into real-world clinical practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Systematic Review Registration<\/jats:title>\n                    <jats:p>\n                      <jats:ext-link>https:\/\/www.crd.york.ac.uk\/PROSPERO\/<\/jats:ext-link>\n                      , identifier CRD420261338867.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1853785","type":"journal-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:39:47Z","timestamp":1784090387000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Diagnostic accuracy and clinical performance of deep learning models for grading diabetic retinopathy: a systematic review and meta-analysis"],"prefix":"10.3389","volume":"17","author":[{"given":"Xin","family":"Yan","sequence":"first","affiliation":[{"name":"Department of Ophthalmology, The Affiliated Hospital(Clinical College) of Xiangnan University, Xiangnan University","place":["Chenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shiqi","family":"Lei","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, The Affiliated Hospital(Clinical College) of Xiangnan University, Xiangnan University","place":["Chenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifen","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, The Affiliated Hospital(Clinical College) of Xiangnan University, Xiangnan University","place":["Chenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mu","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, The Affiliated Hospital(Clinical College) of Xiangnan University, Xiangnan University","place":["Chenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Medical Affairs, The Affiliated Hospital(Clinical College) of Xiangnan University, Xiangnan University","place":["Chenzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1038\/nrdp.2016.12","article-title":"Diabetic retinopathy","volume":"2","author":"Wong","year":"2016","journal-title":"Nat Rev Dis Primers"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/S2213-8587(18)30128-1","article-title":"Incidence and progression of diabetic retinopathy: a systematic review","volume":"7","author":"Sabanayagam","year":"2019","journal-title":"Lancet Diabetes Endocrinol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3390\/ijms19061816","article-title":"Diabetic retinopathy: pathophysiology and treatments","volume":"19","author":"Wang","year":"2018","journal-title":"Int J Mol Sci"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2022.1077669","article-title":"Diabetic retinopathy: looking forward to 2030","volume":"13","author":"Tan","year":"2023","journal-title":"Front Endocrinol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmet.2024.04.013","article-title":"Diabetic retinopathy is a ceramidopathy reversible by anti-ceramide immunotherapy","volume":"36","author":"Dorweiler","year":"2024","journal-title":"Cell Metab"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.2174\/1570161117666190502103733","article-title":"Microvascular complications of type 2 diabetes mellitus","volume":"18","author":"Faselis","year":"2020","journal-title":"Curr Vasc Pharmacol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2147\/IJN.S294807","article-title":"Progress of nanotechnology in diabetic retinopathy treatment","volume":"16","author":"Liu","year":"2021","journal-title":"Int J Nanomed"},{"key":"B8","article-title":"International clinical diabetic retinopathy disease severity scale","volume":"68","author":"Haneda","year":"2010","journal-title":"Nihon Rinsho"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.34254","article-title":"Pivotal evaluation of an artificial intelligence system for autonomous detection of referrable and vision-threatening diabetic retinopathy","volume":"4","author":"Ipp","year":"2021","journal-title":"JAMA Netw Open"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2020.105320","article-title":"Deep learning algorithms for detection of diabetic retinopathy in retinal fundus photographs: a systematic review and meta-analysis","volume":"191","author":"Islam","year":"2020","journal-title":"Comput Methods Programs BioMed"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-025-10379-5","article-title":"Comparing bipartite convoluted and attention-driven methods for skin cancer detection: a review of explainable AI and transfer learning strategies","volume":"33","author":"Banerjee","year":"2026","journal-title":"Arch Comput Methods Eng"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-11574-x","article-title":"Pyramidal attention-based T network for brain tumor classification: a comprehensive analysis of transfer learning approaches for clinically reliable and reliable AI hybrid approaches","volume":"15","author":"Banerjee","year":"2025","journal-title":"Sci Rep"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-14333-0","article-title":"A novel unified Inception-U-Net hybrid gravitational optimization model (UIGO) incorporating automated medical image segmentation and feature selection for liver tumor detection","volume":"15","author":"Banerjee","year":"2025","journal-title":"Sci Rep"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-025-10411-8","article-title":"A comparative evaluation of deep learning architectures for prostate cancer segmentation: introducing TrionixNet with N-Core multi-attention mechanism","volume":"33","author":"Narayan","year":"2026","journal-title":"Arch Comput Methods Eng"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-025-10414-5","article-title":"A comprehensive study of enhanced computational approaches for breast cancer classification: comparative analysis with existing state of the art methods","volume":"33","author":"Singh","year":"2026","journal-title":"Arch Comput Methods Eng"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100512","article-title":"DeepDRiD: diabetic retinopathy-grading and image quality estimation challenge","volume":"3","author":"Liu","year":"2022","journal-title":"Patterns"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.pdpdt.2025.105278","article-title":"Inadequacies and inaccuracies in grading non proliferative diabetic retinopathy without fluorescein fundus angiography in Chinese patients","volume":"56","author":"Peng","year":"2025","journal-title":"Photodiagn Photodyn Ther"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-155-8-201110180-00009","article-title":"QUADAS-2: a revised tool for the quality assessment of diagnostic accuracy studies","volume":"155","author":"Whiting","year":"2011","journal-title":"Ann Internal Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/ima.70152","article-title":"Advancing computer-assisted diabetic retinopathy grading: a super learner ensemble technique for fundus imagery","volume":"35","author":"Mathews","year":"2025","journal-title":"Int J Imaging Syst Technol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2024.108160","article-title":"Attention-based deep learning framework for automatic fundus image processing to aid in diabetic retinopathy grading","volume":"249","author":"Romero-Ora\u00e1","year":"2024","journal-title":"Comput Methods Programs BioMed"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09001-1","article-title":"Automated detecting and severity grading of diabetic retinopathy using transfer learning and attention mechanism","volume":"35","author":"Dinpajhouh","year":"2023","journal-title":"Neural Comput Appl"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.14704\/NQ.2022.20.15.NQ88306","article-title":"Automated diabetic retinopathy detection and grading using fusion based pretrained convolutional neural networks","volume":"20","author":"Rajkumar","year":"2022","journal-title":"NeuroQuantology"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.03.016","article-title":"Automated identification and grading system of diabetic retinopathy using deep neural networks","volume":"175","author":"Zhang","year":"2019","journal-title":"Knowledge-Based Syst"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.18280\/ts.410643","article-title":"Automatic digital analysis system to grade diabetic retinopathy by integrated stacking model concept","volume":"41","author":"Manivel","year":"2024","journal-title":"Traitement du Signal"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108014","article-title":"Computer aided diagnosis of diabetic retinopathy grading using spiking neural network","volume":"101","author":"Ragab","year":"2022","journal-title":"Comput Electr Eng"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2020.012008","article-title":"A convolutional neural network classifier VGG-19 architecture for lesion detection and grading in diabetic retinopathy based on deep learning","volume":"66","author":"Sudha","year":"2020","journal-title":"Computers Materials Continua"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac9fa0","article-title":"CoT-XNet: contextual transformer with Xception network for diabetic retinopathy grading","volume":"67","author":"Zhao","year":"2022","journal-title":"Phys Med Biol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2024.1400137","article-title":"Cross-modality transfer learning with knowledge infusion for diabetic retinopathy grading","volume":"11","author":"Chen","year":"2024","journal-title":"Front Med"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics12123084","article-title":"A deep learning based approach for grading of diabetic retinopathy using large fundus image dataset","volume":"12","author":"Mehboob","year":"2022","journal-title":"Diagnostics"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-87171-9","article-title":"A deep learning based model for diabetic retinopathy grading","volume":"15","author":"Akhtar","year":"2025","journal-title":"Sci Rep"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03745-0","article-title":"Deep learning-based binocular system for automated diabetic retinopathy grading with prior clinical knowledge integration","volume":"41","author":"Ali","year":"2025","journal-title":"Visual Comput"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-022-14234-8","article-title":"Diabetic retinopathy detection and grading of retinal fundus images using coyote optimization algorithm with deep learning","volume":"82","author":"Parthiban","year":"2023","journal-title":"Multimedia Tools Appl"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3301618","article-title":"Diabetic retinopathy detection and grading: a transfer learning approach using simultaneous parameter optimization and feature-weighted ECOC ensemble","volume":"11","author":"Wong","year":"2023","journal-title":"IEEE Access"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2024.104888","article-title":"Diabetic retinopathy grading based on multi-scale residual network and cross-attention module","volume":"157","author":"Singh","year":"2025","journal-title":"Digital Signal Process"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110364","article-title":"Dual-stage dynamic hierarchical attention framework for saliency-aware explainable diabetic retinopathy grading","volume":"148","author":"Abraham","year":"2025","journal-title":"Eng Appl Artif Intell"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128116","article-title":"Enhanced multi-grade diabetic retinopathy detection and classification via ensembled deep learning model from retinal fundus images","volume":"285","author":"Hariobulesu","year":"2025","journal-title":"Expert Syst Appl"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2021.05.009","article-title":"Ensemble of multi-stage deep convolutional neural networks for automated grading of diabetic retinopathy using image patches","volume":"34","author":"Deepa","year":"2022","journal-title":"J King Saud Univ Comput Inf Sci"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabet.2010.01.002","article-title":"Evaluation of automated fundus photograph analysis algorithms for detecting microaneurysms, haemorrhages and exudates, and of a computer-assisted diagnostic system for grading diabetic retinopathy","volume":"36","author":"Dupas","year":"2010","journal-title":"Diabetes Metab"},{"key":"B39","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1007\/s13755-022-00181-z","article-title":"Features extraction using encoded local binary pattern for detection and grading diabetic retinopathy","volume":"10","author":"Berbar","year":"2022","journal-title":"Health Inf Sci Syst"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.01.034","article-title":"Grader variability and the importance of reference standards for evaluating machine learning models for diabetic retinopathy","volume":"125","author":"Krause","year":"2018","journal-title":"Ophthalmology"},{"key":"B41","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-42823-4_18","article-title":"Grading diabetic retinopathy using transfer learning-based convolutional neural networks","volume-title":"Computer Information Systems and Industrial Management","author":"Escorcia-Gutierrez","year":"2023"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1016\/j.bmt.2024.09.004","article-title":"HFF-Net: a hybrid convolutional neural network for diabetic retinopathy screening and grading","volume":"8","author":"Ashraf","year":"2024","journal-title":"BioMed Technol"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13101664","article-title":"Identifying the key components in ResNet-50 for diabetic retinopathy grading from fundus images: a systematic investigation","volume":"13","author":"Huang","year":"2023","journal-title":"Diagnostics"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.18494\/SAM4084","article-title":"Image enhancement and 27 pretrained convolutional neural network models for diabetic retinopathy grading","volume":"35","author":"Kanjanasurat","year":"2023","journal-title":"Sens Mater"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109782","article-title":"Improving diabetic retinopathy grading using feature fusion for limited data samples","volume":"120","author":"Ashwini","year":"2024","journal-title":"Comput Electr Eng"},{"key":"B46","doi-asserted-by":"publisher","first-page":"30706","DOI":"10.1038\/s41598-025-14944-7","article-title":"Integrating non-linear radon transformation for diabetic retinopathy grading","volume":"15","author":"Mohsen","year":"2025","journal-title":"Sci Rep"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.3390\/life15091473","article-title":"Interpreting deep neural networks in diabetic retinopathy grading: a comparison with human decision criteria","volume":"15","author":"Biswas","year":"2025","journal-title":"Life"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15182355","article-title":"A multi-model image enhancement and tailored U-Net architecture for robust diabetic retinopathy grading","volume":"15","author":"Singh","year":"2025","journal-title":"Diagnostics"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2025.061150","article-title":"MVLA-Net: a multi-view lesion attention network for advanced diagnosis and grading of diabetic retinopathy","volume":"83","author":"Mahmood","year":"2025","journal-title":"Computers Materials Continua"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.106750","article-title":"A new ultra-wide-field fundus dataset to diabetic retinopathy grading using hybrid preprocessing methods","volume":"157","author":"Liu","year":"2023","journal-title":"Comput Biol Med"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2022.111485","article-title":"A novel few-shot classification framework for diabetic retinopathy detection and grading","volume":"200","author":"Murugappan","year":"2022","journal-title":"Measurement"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-021-01073-4","article-title":"A novel four-step feature selection technique for diabetic retinopathy grading","volume":"44","author":"Mohan","year":"2021","journal-title":"Phys Eng Sci Med"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-023-02175-3","article-title":"Optimal hybrid feature selection technique for diabetic retinopathy grading using fundus images","volume":"48","author":"Mohan","year":"2023","journal-title":"Sadhana"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.18662\/brain\/15.2\/576","article-title":"Potential screening, grading and follow-up of diabetic retinopathy in primary care using artificial intelligence \u2013 how hard would it be to implement? An ophthalmologist's perspective","volume":"15","author":"Rusu","year":"2024","journal-title":"Brain Broad Res Artif Intell Neurosci"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104795","article-title":"Simple methods for the lesion detection and severity grading of diabetic retinopathy by image processing and transfer learning","volume":"137","author":"Sugeno","year":"2021","journal-title":"Comput Biol Med"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1445565","article-title":"SwAV-driven diagnostics: new perspectives on grading diabetic retinopathy from retinal photography","volume":"11","author":"Alam","year":"2024","journal-title":"Front Rob AI"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-021-06042-2","article-title":"Transfer learning based robust automatic detection system for diabetic retinopathy grading","volume":"33","author":"Bhardwaj","year":"2021","journal-title":"Neural Comput Appl"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ophtha.2018.11.016","article-title":"Using a deep learning algorithm and integrated gradients explanation to assist grading for diabetic retinopathy","volume":"126","author":"Sayres","year":"2019","journal-title":"Ophthalmology"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.839088","article-title":"The validation of deep learning-based grading model for diabetic retinopathy","volume":"9","author":"Zhang","year":"2022","journal-title":"Front Med"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13040774","article-title":"A regression-based approach to diabetic retinopathy diagnosis using Efficientnet","volume":"13","author":"Vijayan","year":"2023","journal-title":"Diagnostics"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.17-23677","article-title":"Automated diagnosis and grading of diabetic retinopathy using optical coherence tomography","volume":"59","author":"Sandhu","year":"2018","journal-title":"Invest Ophthalmol Visual Sci"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1038\/s41433-021-01415-2","article-title":"Automated feature-based grading and progression analysis of diabetic retinopathy","volume":"36","author":"Al-Turk","year":"2022","journal-title":"Eye"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.17216","article-title":"Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs","volume":"316","author":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/2611250","article-title":"Automated grading of diabetic retinopathy with ultra-widefield fluorescein angiography and deep learning","volume":"2021","author":"Wang","year":"2021","journal-title":"J Diabetes Res"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.1016\/j.oret.2018.10.014","article-title":"Deep learning-based algorithms in screening of diabetic retinopathy: a systematic review of diagnostic performance","volume":"3","author":"Nielsen","year":"2019","journal-title":"Ophthalmol Retina"},{"key":"B66","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-31526-9","article-title":"Detection of diabetic retinopathy using multicolor image by multimodal network incorporating information bottleneck (MNIIB)","volume":"16","author":"Song","year":"2026","journal-title":"Sci Rep"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.3390\/jcm14134810","article-title":"Comparison of validity and reliability of manual consensus grading vs. automated AI grading for diabetic retinopathy screening in Oslo, Norway: a cross-sectional pilot study","volume":"14","author":"Karabeg","year":"2025","journal-title":"J Clin Med"},{"key":"B68","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics15141831","article-title":"Intergrader agreement on qualitative and quantitative assessment of diabetic retinopathy severity using ultra-widefield imaging: INSPIRED study report 1","volume":"15","author":"Riotto","year":"2025","journal-title":"Diagnostics"},{"key":"B69","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41392-025-02448-9","article-title":"Proliferative diabetic retinopathy subtypes defined by immune defense and endothelial mitochondrial dysfunction","volume":"10","author":"McCann","year":"2025","journal-title":"Signal Transduction Targeted Ther"},{"key":"B70","doi-asserted-by":"publisher","DOI":"10.3390\/s23125726","article-title":"Using deep learning architectures for detection and classification of diabetic retinopathy","volume":"23","author":"Mohanty","year":"2023","journal-title":"Sensors"},{"key":"B71","doi-asserted-by":"publisher","DOI":"10.1007\/s11517-021-02487-8","article-title":"The adoption of deep learning interpretability techniques on diabetic retinopathy analysis: a review","volume":"60","author":"Lim","year":"2022","journal-title":"Med Biol Eng Comput"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1853785\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T04:39:56Z","timestamp":1784090396000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1853785\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":71,"alternative-id":["10.3389\/fendo.2026.1853785"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1853785","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]},"article-number":"1853785"}}