{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:03:50Z","timestamp":1784127830301,"version":"3.55.0"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T00:00:00Z","timestamp":1726185600000},"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. Robot. AI"],"abstract":"<jats:p>Diabetic Retinopathy (DR) is a serious eye condition that occurs due to high blood sugar levels in patients with Diabetes Mellitus. If left untreated, DR can potentially result in blindness. Using automated neural network-based methods to grade DR shows potential for early detection. However, the uneven and non-quadrilateral forms of DR lesions provide difficulties for traditional Convolutional Neural Network (CNN)-based architectures. To address this challenge and explore a novel algorithm architecture, this work delves into the usage of contrasting cluster assignments in retinal fundus images with the Swapping Assignments between multiple Views (SwAV) algorithm for DR grading. An ablation study was made where SwAV outperformed other CNN and Transformer-based models, independently and in ensemble configurations with an accuracy of 87.00% despite having fewer parameters and layers. The proposed approach outperforms existing state-of-the-art models regarding classification metrics, complexity, and prediction time. The findings offer great potential for medical practitioners, allowing for more accurate diagnosis of DR and earlier treatments to avoid visual loss.<\/jats:p>","DOI":"10.3389\/frobt.2024.1445565","type":"journal-article","created":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T07:55:22Z","timestamp":1726214122000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SwAV-driven diagnostics: new perspectives on grading diabetic retinopathy from retinal photography"],"prefix":"10.3389","volume":"11","author":[{"given":"Md Nuho Ul","family":"Alam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erfanul Hoque","family":"Bahadur","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdul Kadar Muhammad","family":"Masum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Farzan M.","family":"Noori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Md Zia","family":"Uddin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,9,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.eswa.2018.07.053","article-title":"Exudate detection for diabetic retinopathy with circular hough transformation and convolutional neural networks","volume":"114","author":"Adem","year":"2018","journal-title":"Expert Syst. Appl."},{"key":"B2","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.compbiomed.2013.11.014","article-title":"Detection and classification of retinal lesions for grading of diabetic retinopathy","volume":"45","author":"Akram","year":"2014","journal-title":"Comput. Biol. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"567","DOI":"10.3390\/e22050567","article-title":"Machine learning based automated segmentation and hybrid feature analysis for diabetic retinopathy classification using fundus image","volume":"22","author":"Ali","year":"2020","journal-title":"Entropy"},{"key":"B4","unstructured":"Self-labelling via simultaneous clustering and representation learning\n          \n          \n            \n              Asano\n              Y. M.\n            \n            \n              Rupprecht\n              C.\n            \n            \n              Vedaldi\n              A.\n            \n          \n          \n          2019"},{"key":"B5","first-page":"1","article-title":"Diabetic retinal exudates detection using machine learning techniques","author":"Asha","year":"2015"},{"key":"B6","unstructured":"Aptos 2019 blindness detection\n          \n          \n          2019"},{"key":"B7","doi-asserted-by":"publisher","first-page":"914","DOI":"10.3390\/electronics9060914","article-title":"Blended multi-modal deep convnet features for diabetic retinopathy severity prediction","volume":"9","author":"Bodapati","year":"2020","journal-title":"Electronics"},{"key":"B8","doi-asserted-by":"publisher","first-page":"9825","DOI":"10.1007\/s12652-020-02727-z","article-title":"Composite deep neural network with gated-attention mechanism for diabetic retinopathy severity classification","volume":"12","author":"Bodapati","year":"","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"B9","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1007\/s11760-020-01816-y","article-title":"Deep convolution feature aggregation: an application to diabetic retinopathy severity level prediction","volume":"15","author":"Bodapati","year":"","journal-title":"Signal, Image Video Process."},{"key":"B10","first-page":"132","article-title":"Deep clustering for unsupervised learning of visual features","author":"Caron","year":"2018"},{"key":"B11","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"33","author":"Caron","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B12","first-page":"1","article-title":"Automated detection of diabetic retinopathy using svm","author":"Carrera","year":"2017"},{"key":"B13","doi-asserted-by":"publisher","first-page":"178552","DOI":"10.1109\/access.2020.3027794","article-title":"An approach to detecting diabetic retinopathy based on integrated shallow convolutional neural networks","volume":"8","author":"Chen","year":"2020","journal-title":"IEEE Access"},{"key":"B14","first-page":"1","article-title":"Diabetic retinopathy detection using machine learning and texture features","author":"Chetoui","year":"2018"},{"key":"B15","doi-asserted-by":"publisher","first-page":"180","DOI":"10.2337\/dc13-1507","article-title":"Barriers to eye care among people aged 40 years and older with diagnosed diabetes, 2006\u20132010","volume":"37","author":"Chou","year":"2014","journal-title":"Diabetes Care"},{"key":"B16","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.cmpb.2018.02.016","article-title":"Microaneurysm detection using fully convolutional neural networks","volume":"158","author":"Chudzik","year":"2018","journal-title":"Comput. Methods Programs Biomed."},{"key":"B17","article-title":"Sinkhorn distances: lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B18","doi-asserted-by":"publisher","first-page":"307","DOI":"10.18280\/ria.340308","article-title":"Deep convolution features in non-linear embedding space for fundus image classification","volume":"34","author":"Dondeti","year":"2020","journal-title":"Rev. d\u2019Intelligence Artif."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2540","DOI":"10.2337\/diacare.27.10.2540","article-title":"Diabetic retinopathy","volume":"27","author":"Fong","year":"2004","journal-title":"Diabetes Care"},{"key":"B20","first-page":"679","article-title":"Diabetic retinopathy detection using transfer learning and deep learning","author":"Gangwar","year":"2021"},{"key":"B21","doi-asserted-by":"publisher","first-page":"639","DOI":"10.1007\/s13246-021-01012-3","article-title":"Diabetic retinopathy classification based on multipath cnn and machine learning classifiers","volume":"44","author":"Gayathri","year":"2021","journal-title":"Phys. Eng. Sci. Med."},{"key":"B22","first-page":"2069","article-title":"Weakly-supervised localization of diabetic retinopathy lesions in retinal fundus images","author":"Gondal","year":"2017"},{"key":"B23","unstructured":"Case study: TensorFlow in medicine - retinal imaging, TensorFlow dev summit 2017\n          \n          \n          2017"},{"key":"B24","doi-asserted-by":"publisher","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":"Gulshan","year":"2016","journal-title":"JAMA"},{"key":"B25","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1001\/jamaophthalmol.2019.2004","article-title":"Performance of a deep-learning algorithm vs manual grading for detecting diabetic retinopathy in India","volume":"137","author":"Gulshan","year":"2019","journal-title":"JAMA Ophthalmol."},{"key":"B26","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"B27","volume-title":"Diabetic retinopathy identification and severity classification","author":"Honnungar","year":"2016"},{"key":"B28","first-page":"888","article-title":"Transfer learning based diabetic retinopathy detection with a novel preprocessed layer","author":"Islam","year":"2020"},{"key":"B29","article-title":"Deep learning based early detection and grading of diabetic retinopathy using retinal fundus images","author":"Islam","year":"2018"},{"key":"B30","unstructured":"Diabetic retinopathy\n          \n          \n            \n              Kanukollu\n              V. M.\n            \n            \n              Ahmad\n              S. S.\n            \n          \n          \n          2023"},{"key":"B31","doi-asserted-by":"publisher","first-page":"608","DOI":"10.1109\/tbme.2017.2707578","article-title":"Automatic detection of retinal lesions for screening of diabetic retinopathy","volume":"65","author":"Kar","year":"2017","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B32","first-page":"1","article-title":"Diabetic retinopathy classification using a modified xception architecture","author":"Kassani","year":"2019"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1679","DOI":"10.1007\/s11760-021-01904-7","article-title":"Dristi: a hybrid deep neural network for diabetic retinopathy diagnosis","volume":"15","author":"Kumar","year":"2021","journal-title":"Signal, Image Video Process."},{"key":"B34","first-page":"617","article-title":"Diabetic retinopathy using morphological operations and machine learning","author":"Lachure","year":"2015"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/8840174","article-title":"Hybrid model structure for diabetic retinopathy classification","volume":"2020","author":"Liu","year":"2020","journal-title":"J. Healthc. Eng."},{"key":"B36","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1007\/s00779-020-01519-8","article-title":"An automatic detection system of diabetic retinopathy using a hybrid inductive machine learning algorithm","volume":"27","author":"Mahmoud","year":"2023","journal-title":"Personal Ubiquitous Comput."},{"key":"B37","doi-asserted-by":"publisher","first-page":"123220","DOI":"10.1109\/access.2021.3109240","article-title":"Multitasking deep learning model for detection of five stages of diabetic retinopathy","volume":"9","author":"Majumder","year":"2021","journal-title":"IEEE Access"},{"key":"B38","first-page":"579","article-title":"Automated localization of optic disk, detection of microaneurysms and extraction of blood vessels to bypass angiography","author":"Manjiri","year":"2015"},{"key":"B39","first-page":"6707","article-title":"Self-supervised learning of pretext-invariant representations","author":"Misra","year":"2020"},{"key":"B40","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1007\/s13410-017-0561-6","article-title":"Automatic detection of retinal hemorrhages by exploiting image processing techniques for screening retinal diseases in diabetic patients","volume":"38","author":"Mumtaz","year":"2018","journal-title":"Int. J. Diabetes Dev. Ctries."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1676","DOI":"10.1056\/nejm199306103282306","article-title":"Long-term complications of diabetes mellitus","volume":"328","author":"Nathan","year":"1993","journal-title":"N. Engl. J. Med."},{"key":"B42","first-page":"173","article-title":"Diabetic retinopathy detection using ensemble machine learning","author":"Odeh","year":"2021"},{"key":"B43","doi-asserted-by":"publisher","first-page":"150530","DOI":"10.1109\/access.2019.2947484","article-title":"A deep learning ensemble approach for diabetic retinopathy detection","volume":"7","author":"Qummar","year":"2019","journal-title":"IEEE Access"},{"key":"B44","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/s40708-016-0045-3","article-title":"Automatic screening and classification of diabetic retinopathy and maculopathy using fuzzy image processing","volume":"3","author":"Rahim","year":"2016","journal-title":"Brain Inf."},{"key":"B45","first-page":"636","article-title":"Proposed retinal abnormality detection and classification approach: computer aided detection for diabetic retinopathy by machine learning approaches","author":"Raman","year":"2016"},{"key":"B46","first-page":"1","article-title":"Automatic diabetic retinopathy detection through ensemble classification techniques automated diabetic retionapthy classification","author":"Ramani","year":"2017"},{"key":"B47","first-page":"1","article-title":"An ensemble based machine learning model for diabetic retinopathy classification","author":"Reddy","year":"2020"},{"key":"B48","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.patrec.2020.04.026","article-title":"Automated detection of diabetic retinopathy using convolutional neural networks on a small dataset","volume":"135","author":"Samanta","year":"2020","journal-title":"Pattern Recognit. Lett."},{"key":"B49","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/s00138-021-01253-y","article-title":"Lesion-aware attention with neural support vector machine for retinopathy diagnosis","volume":"32","author":"Shaik","year":"2021","journal-title":"Mach. Vis. Appl."},{"key":"B50","first-page":"307","article-title":"Drdr: automatic masking of exudates and microaneurysms caused by diabetic retinopathy using mask r-cnn and transfer learning","author":"Shenavarmasouleh","year":"2021"},{"key":"B51","unstructured":"Diabetic retinopathy\n          \n          \n            \n              Shukla\n              U. V.\n            \n            \n              Tripathy\n              K.\n            \n          \n          \n          2023"},{"key":"B52","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s10916-017-0853-x","article-title":"A machine learning ensemble classifier for early prediction of diabetic retinopathy","volume":"41","author":"Sk","year":"2017","journal-title":"J. Med. Syst."},{"key":"B53","doi-asserted-by":"crossref","DOI":"10.2174\/97816810835751160101","volume-title":"Ophthalmology: current and future developments: volume 1-diagnostic atlas of retinal diseases","author":"Soriano","year":"2016"},{"key":"B54","doi-asserted-by":"publisher","first-page":"1580","DOI":"10.1016\/j.ophtha.2021.04.027","article-title":"Global prevalence of diabetic retinopathy and projection of burden through 2045: systematic review and meta-analysis","volume":"128","author":"Teo","year":"2021","journal-title":"Ophthalmology"},{"key":"B55","first-page":"17","article-title":"Image processing, textural feature extraction and transfer learning based detection of diabetic retinopathy","author":"Umapathy","year":"2019"},{"key":"B56","first-page":"3733","article-title":"Unsupervised feature learning via non-parametric instance discrimination","author":"Wu","year":"2018"},{"key":"B57","doi-asserted-by":"publisher","first-page":"6768","DOI":"10.1109\/access.2024.3351473","article-title":"A novel transformer model with multiple instance learning for diabetic retinopathy classification","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"B58","first-page":"1744","article-title":"Exudate detection for diabetic retinopathy with convolutional neural networks","author":"Yu","year":"2017"},{"key":"B59","doi-asserted-by":"publisher","first-page":"30744","DOI":"10.1109\/access.2019.2903171","article-title":"Automated diabetic retinopathy detection based on binocular siamese-like convolutional neural network","volume":"7","author":"Zeng","year":"2019","journal-title":"IEEE Access"},{"key":"B60","first-page":"1385","article-title":"Bira-net: bilinear attention net for diabetic retinopathy grading","author":"Zhao","year":"2019"},{"key":"B61","first-page":"2724","article-title":"Multi-cell multi-task convolutional neural networks for diabetic retinopathy grading","author":"Zhou","year":"2018"}],"container-title":["Frontiers in Robotics and AI"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2024.1445565\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,13]],"date-time":"2024-09-13T07:55:31Z","timestamp":1726214131000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frobt.2024.1445565\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,13]]},"references-count":61,"alternative-id":["10.3389\/frobt.2024.1445565"],"URL":"https:\/\/doi.org\/10.3389\/frobt.2024.1445565","relation":{},"ISSN":["2296-9144"],"issn-type":[{"value":"2296-9144","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,13]]},"article-number":"1445565"}}