{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T05:00:14Z","timestamp":1787806814140,"version":"build-2784847793"},"reference-count":32,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T00:00:00Z","timestamp":1785110400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004242","name":"Princess Nourah Bint Abdulrahman University","doi-asserted-by":"publisher","award":["PNURSP2026R904"],"award-info":[{"award-number":["PNURSP2026R904"]}],"id":[{"id":"10.13039\/501100004242","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early identification of diabetic retinopathy (DR), which is a primary cause of vision impairment globally, is a crucial phasis for effective intervention and treatment. Traditional screening workflows rely on manual diagnosis by ophthalmologists, which remains the gold standard but can be time-consuming and subject to variability due to human factors. To support and enhance the screening process, artificial intelligence (AI)-based tools have shown promise in automating DR detection, particularly with recent advances in deep learning. However, medical images with long-range dependencies and spatial linkages can be challenging for CNN-based algorithms to handle.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This paper proposes a Vision Transformer (ViT)-based model, specifically using a Compact Convolutional Transformer (CCT), for early automated detection of DR. The model uses self-attention techniques to improve feature extraction and classification performance; combining three main stages: the CCT tokenizer, transformer encoder, and sequence pooling. The proposed approach was trained on public datasets (EyePACS and APTOS 2019) and evaluated against state-of-the-art deep learning architectures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our experimental findings demonstrate that ViT performs among the best in the current state of the art with an overall accuracy of 97% and F1-scores above 0.95 across all DR severity levels. Our system is primarily designed for the pre-screening stage of diabetic retinopathy workflows, enabling rapid and reliable identification of potential DR cases for further clinical evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>These results highlight the potential of transformer-based designs in medical picture analysis, as well as the implications for telemedicine and e-health solutions in real-time, especially in cases of low-resource settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0350854","type":"journal-article","created":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T17:30:23Z","timestamp":1785173423000},"page":"e0350854","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Artificial intelligence for early detection of diabetic retinopathy: A vision transformer-based approach"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8879-6821","authenticated-orcid":true,"given":"Asma","family":"ElAdel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Imen","family":"Filali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mourad","family":"Zaied","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,7,27]]},"reference":[{"issue":"12","key":"pone.0350854.ref001","first-page":"911","article-title":"Diabetic retinopathy: global prevalence, major risk factors, screening practices and public health challenges: a review","volume":"7","author":"DSW Ting","year":"2019","journal-title":"The Lancet Diabetes & Endocrinology"},{"issue":"22","key":"pone.0350854.ref002","doi-asserted-by":"crossref","first-page":"2402","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":"V Gulshan","year":"2016","journal-title":"JAMA"},{"key":"pone.0350854.ref003","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1016\/j.patrec.2020.02.026","article-title":"Automated detection and classification of fundus diabetic retinopathy images using synergic deep learning model","volume":"133","author":"K Shankar","year":"2020","journal-title":"Pattern Recognition Letters"},{"issue":"7553","key":"pone.0350854.ref004","article-title":"Deep learning","volume":"521","author":"Y LeCun","year":"2015","journal-title":"Nat"},{"issue":"6","key":"pone.0350854.ref005","article-title":"Review on diabetic retinopathy with deep learning methods","volume":"8","author":"S Shekar","year":"2021","journal-title":"Journal of Medical Imaging"},{"issue":"18","key":"pone.0350854.ref006","doi-asserted-by":"crossref","first-page":"67","DOI":"10.3390\/s22186780","article-title":"Deep Learning for Diabetic Retinopathy Analysis: A Review, Research Challenges, and Future Directions","volume":"22","author":"MW Nadeem","year":"2022","journal-title":"Sensors"},{"key":"pone.0350854.ref007","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"A Dosovitskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"pone.0350854.ref008","article-title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","author":"Z Liu","year":"2021","journal-title":"arXiv preprint"},{"issue":"2","key":"pone.0350854.ref009","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1007\/s10916-007-9113-9","article-title":"Computer-based detection of diabetic retinopathy stages using digital fundus images","volume":"32","author":"U Acharya","year":"2008","journal-title":"Journal of Medical Systems"},{"issue":"5","key":"pone.0350854.ref010","first-page":"770","article-title":"Adaptive non-supervised classification for diabetic retinopathy screening","volume":"14","author":"G Quellec","year":"2010","journal-title":"Medical Image Analysis"},{"key":"pone.0350854.ref011","first-page":"1","article-title":"DIARETDB1\u2014Standard diabetic retinopathy database","volume":"3","author":"T Kauppi","year":"2007","journal-title":"Medical Image Analysis"},{"key":"pone.0350854.ref012","doi-asserted-by":"crossref","unstructured":"Kumar RR, Pandian R, Jacob TP, Pravin A, Indumathi P. Detection of diabetic retinopathy using deep convolutional neural networks. In: Proceedings of the Computational Vision and Bio-Inspired Computing (ICCVBIC), Coimbatore, India, 2021. 415\u201330.","DOI":"10.1007\/978-981-33-6862-0_34"},{"key":"pone.0350854.ref013","doi-asserted-by":"crossref","unstructured":"Kurup G, Jothi JAA, Kanadath A. Diabetic retinopathy detection and classification using pretrained Inception-v3. In: Pune, India, 2021.","DOI":"10.1109\/SMARTGENCON51891.2021.9645914"},{"issue":"15","key":"pone.0350854.ref014","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics13152606","article-title":"Automatic detection and classification of diabetic retinopathy using the improved pooling function in the convolution neural network","volume":"13","author":"U Bhimavarapu","year":"2023","journal-title":"Diagnostics"},{"issue":"12","key":"pone.0350854.ref015","doi-asserted-by":"crossref","first-page":"5726","DOI":"10.3390\/s23125726","article-title":"Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy","volume":"23","author":"C Mohanty","year":"2023","journal-title":"Sensors (Basel)"},{"key":"pone.0350854.ref016","unstructured":"Lam C, Yi D, Guo M, Lindsey T. Automated detection of diabetic retinopathy using deep learning. In: AMIA Joint Summits on Translational Science, 2018. 147\u201355."},{"issue":"12","key":"pone.0350854.ref017","doi-asserted-by":"crossref","first-page":"7850","DOI":"10.1002\/mp.15312","article-title":"Vision Transformer-based recognition of diabetic retinopathy grade","volume":"48","author":"J Wu","year":"2021","journal-title":"Med Phys"},{"key":"pone.0350854.ref018","doi-asserted-by":"crossref","unstructured":"Mohan NJ, Murugan R, Goel T, Roy P. ViT-DR: Vision Transformers in Diabetic Retinopathy Grading Using Fundus Images. In: 2022 IEEE 10th Region 10 Humanitarian Technology Conference (R10-HTC), Hyderabad, India, 2022. 167\u201372.","DOI":"10.1109\/R10-HTC54060.2022.9930027"},{"key":"pone.0350854.ref019","doi-asserted-by":"crossref","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","article-title":"Transformers in medical imaging: A survey","volume":"88","author":"F Shamshad","year":"2023","journal-title":"Medical Image Analysis"},{"issue":"3","key":"pone.0350854.ref020","doi-asserted-by":"crossref","first-page":"416","DOI":"10.3803\/EnM.2023.1913","article-title":"Artificial Intelligence Applications in Diabetic Retinopathy: What We Have Now and What to Expect in the Future","volume":"39","author":"M Kong","year":"2024","journal-title":"Endocrinol Metab (Seoul)"},{"key":"pone.0350854.ref021","doi-asserted-by":"crossref","first-page":"111884","DOI":"10.1016\/j.ejrad.2024.111884","article-title":"Current status and future directions of explainable artificial intelligence in medical imaging","volume":"183","author":"SN Saw","year":"2025","journal-title":"Eur J Radiol"},{"issue":"7","key":"pone.0350854.ref022","article-title":"Performance and Limitation of Machine Learning Algorithms for Diabetic Retinopathy Screening: Meta-analysis","volume":"23","author":"J-H Wu","year":"2021","journal-title":"J Med Internet Res"},{"key":"pone.0350854.ref023","unstructured":"Kaggle. Diabetic Retinopathy Detection Challenge. 2015. https:\/\/www.kaggle.com\/c\/diabetic-retinopathy-detection"},{"key":"pone.0350854.ref024","unstructured":"Asia Pacific Tele-Ophthalmology Society. APTOS 2019 Blindness Detection Dataset. 2019. https:\/\/www.kaggle.com\/c\/aptos2019-blindness-detection"},{"issue":"3","key":"pone.0350854.ref025","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/S0734-189X(87)80186-X","article-title":"Adaptive histogram equalization and its variations","volume":"39","author":"SM Pizer","year":"1987","journal-title":"Computer Vision, Graphics, and Image Processing"},{"key":"pone.0350854.ref026","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic Minority Over-sampling Technique","volume":"16","author":"NV Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"issue":"60","key":"pone.0350854.ref027","article-title":"A survey on image data augmentation for deep learning","volume":"6","author":"C Shorten","year":"2019","journal-title":"Journal of Big Data"},{"key":"pone.0350854.ref028","article-title":"Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0350854.ref029","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. In: 2014. https:\/\/arxiv.org\/abs\/1412.6980"},{"issue":"7","key":"pone.0350854.ref030","doi-asserted-by":"crossref","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","article-title":"The use of the area under the ROC curve in the evaluation of machine learning algorithms","volume":"30","author":"AP Bradley","year":"1997","journal-title":"Pattern Recognition"},{"key":"pone.0350854.ref031","doi-asserted-by":"crossref","first-page":"786","DOI":"10.1016\/S0161-6420(13)38012-9","article-title":"Grading diabetic retinopathy from stereoscopic color fundus photographs\u2013an extension of the modified Airlie House classification","volume":"98","author":"Early Treatment Diabetic Retinopathy Study Research Group","year":"1991","journal-title":"Ophthalmology"},{"issue":"7","key":"pone.0350854.ref032","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1016\/S0161-6420(81)34978-1","article-title":"Photocoagulation treatment of proliferative diabetic retinopathy. Clinical application of diabetic retinopathy study (DRS) findings","volume":"88","author":"The Diabetic Retinopathy Study Research Group","year":"1981","journal-title":"Ophthalmology"}],"updated-by":[{"DOI":"10.1371\/journal.pone.0357114","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000}}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T17:30:29Z","timestamp":1785173429000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0350854"}},"subtitle":[],"editor":[{"given":"Anirban","family":"Bhowmick","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,7,27]]},"references-count":32,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7,27]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0350854","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,27]]}}}