{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T05:03:48Z","timestamp":1789967028798,"version":"4.0.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"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. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Retinal Diseases are the main reason for vision loss and blindness worldwide. Initial identification of retinal abnormalities is essential for avoiding severe retinal-related complications and improving patient results. Traditional retinal disease diagnosis mainly depends on manual checks of retinal fundus images, which are slow and highly dependent on medical expertise. Deep learning methods are used in retinal disease classification. Existing methods are primarily based on labelled image data and often do not fully utilize complementary clinical information. The proposed hybrid multi-model framework classifies retinal diseases from the available retinal fundus images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>SSLVNet combines a Self-Supervised Learning encoder, Lesion Attention, CNN, ViT, and a Simplified lesion Graph. Also, Grad- CAM provides visual elucidations of the model predictions. ODIR-5K dataset, which includes multiple ocular disease categories, is used.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The results are promising, with an Exact Accuracy of 84.44%, a Hamming accuracy of 96.92%, and a Macro F1-Score of 90.36%. An ablation study was done to understand the contribution of individual components in the proposed framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These results indicate that the proposed work can effectively support reliable and interpretable retinal disease classification in real-world healthcare applications.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2026.1937520","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T04:28:31Z","timestamp":1789964911000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SSLVNet: an explainable multi-modal hybrid framework integrating self-supervised learning and vision transformers for multi-label classification of retinal diseases"],"prefix":"10.3389","volume":"9","author":[{"given":"M.","family":"Rithiga","sequence":"first","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"R. K.","family":"Nadesh","sequence":"additional","affiliation":[{"name":"School of Computer Science Engineering and Information Systems, Vellore Institute of Technology","place":["Vellore, Tamil Nadu, India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"73950","DOI":"10.1109\/ACCESS.2024.3405570","article-title":"Enhancing early detection of diabetic retinopathy through the integration of deep learning models and explainable artificial intelligence","volume":"12","author":"Ahnaf Alavee","year":"2024","journal-title":"IEEE Access"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"102059","DOI":"10.1016\/j.inffus.2023.102059","article-title":"Fundus-DeepNet: multi-label deep learning classification system for enhanced detection of multiple ocular diseases through data fusion of fundus images","volume":"102","author":"Al-Fahdawi","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-025-09684-y","article-title":"Multi-modal fusion and vision transformers for robust early AMD prediction","volume":"16","author":"Annamalai","year":"2025","journal-title":"Evol. Syst."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"37403","DOI":"10.1109\/ACCESS.2023.3263493","article-title":"Deep transfer learning strategy to diagnose eye-related conditions and diseases: an approach based on low-quality fundus images","volume":"11","author":"Aranha","year":"2023","journal-title":"IEEE Access"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"21873","DOI":"10.1109\/JIOT.2023.3304790","article-title":"Federated learning for the healthcare metaverse: concepts, applications, challenges, and future directions","volume":"10","author":"Bashir","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging9070140","article-title":"Conv-ViT: A convolution and vision transformer-based hybrid feature extraction method for retinal disease detection","volume":"9","author":"Dutta","year":"2023","journal-title":"J. Imaging"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2020.102329","article-title":"Multi-class multi-label ophthalmological disease detection using transfer learning based convolutional neural network","volume":"66","author":"Gour","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"key":"ref8","volume-title":"Multi-label Image Classification for Ocular Disease Diagnosis Using K-fold Cross-Validation on the ODIR-5K Dataset IEEE International Symposium on Industrial Electronics","author":"Herrera-Chavez","year":"2024"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12010057","article-title":"FundusNet: a deep-learning approach for fast diagnosis of neurodegenerative and eye diseases using fundus images","volume":"12","author":"Hu","year":"2025","journal-title":"Bioengineering"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics14232679","article-title":"CAD-EYE: an automated system for multi-eye disease classification using feature fusion with deep learning models and fluorescence imaging for enhanced interpretability","volume":"14","author":"Khalid","year":"2024","journal-title":"Diagnostics"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106396","article-title":"Multi-module attention-guided deep learning framework for precise gastrointestinal disease identification in endoscopic imagery","volume":"95","author":"Khan","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"2029","DOI":"10.1007\/s11517-025-03314-0","article-title":"A novel deep learning framework for retinal disease detection leveraging contextual and local features cues from retinal images","volume":"63","author":"Khan","year":"2025","journal-title":"Med. Biol. Eng. Comput."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"70853","DOI":"10.1109\/ACCESS.2023.3294443","article-title":"Redefining retinal lesion segmentation: a quantum leap with DL-UNet enhanced auto encoder-decoder for fundus image analysis","volume":"11","author":"Kumar","year":"2023","journal-title":"IEEE Access"},{"key":"ref14","author":"Li","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"79793","DOI":"10.1109\/ACCESS.2025.3566073","article-title":"EffNet-SVM: a hybrid model for diabetic retinopathy classification using retinal fundus images","volume":"13","author":"Naveen","year":"2025","journal-title":"IEEE Access"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1109\/ACCESS.2024.3522862","article-title":"Explainable AI-based approach for age-related macular degeneration (AMD) detection via fundus imaging","volume":"13","author":"Osa-Sanchez","year":"2025","journal-title":"IEEE Access"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"106739","DOI":"10.1016\/j.cmpb.2022.106739","article-title":"BFENet: A two-stream interaction CNN method for multi-label ophthalmic diseases classification with bilateral fundus images","volume":"219","author":"Ou","year":"2022","journal-title":"Comput. Methods Prog. Biomed."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"6618","DOI":"10.1109\/ACCESS.2025.3525499","article-title":"Automatic detection of hard exudate in color retinal fundus image and diabetic maculopathy grading","volume":"13","author":"Rajesh","year":"2025","journal-title":"IEEE Access"},{"key":"ref19","article-title":"Eye disease identification using deep learning","author":"Sattigeri","year":"2022","journal-title":"Int. Res. J. Eng. Technol."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"143985","DOI":"10.1109\/ACCESS.2024.3469244","article-title":"DualEye-FeatureNet: a dual-stream feature transfer framework for multi-modal ophthalmic image classification","volume":"12","author":"Shafiq","year":"2024","journal-title":"IEEE Access"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13101706","article-title":"Automatic classification of colour fundus images for prediction eye disease types based on hybrid features","volume":"13","author":"Shamsan","year":"2023","journal-title":"Diagnostics"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"15166","DOI":"10.1038\/s41598-025-99309-w","article-title":"A hybrid deep learning framework for early detection of diabetic retinopathy using retinal fundus images","volume":"15","author":"Sushith","year":"2025","journal-title":"Sci. Rep."},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-024-00293-8","article-title":"A transfer learning enabled approach for ocular disease detection and classification","volume":"12","author":"ul Hassan","year":"2024","journal-title":"Health Inf. Sci. Syst."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"97322","DOI":"10.1109\/ACCESS.2025.3572471","article-title":"A low-cost AI-powered system for early detection of diabetic retinopathy and ocular diseases in resource limited settings","volume":"13","author":"Vohra","year":"2025","journal-title":"IEEE Access"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12050548","article-title":"Integrating artificial intelligence and precision therapeutics for advancing the diagnosis and treatment of age-related macular degeneration","volume":"12","author":"Wang","year":"2025","journal-title":"Bioengineering"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12122697","article-title":"An explainable artificial intelligence-based robustness optimization approach for age-related macular degeneration detection based on medical IOT systems","volume":"12","author":"Wang","year":"2023","journal-title":"Electronics"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"445","DOI":"10.26599\/BDMA.2023.9020024","article-title":"AI-based advanced approaches and dry eye disease detection based on multi-source evidence: cases, applications, issues, and future directions","volume":"7","author":"Wang","year":"2024","journal-title":"Big Data Min. Anal."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"19298","DOI":"10.1038\/s41598-025-04503-5","article-title":"Ensemble-based eye disease detection system utilizing fundus and vascular structures","volume":"15","author":"Yu","year":"2025","journal-title":"Sci. Rep."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1109\/JBHI.2021.3092339","article-title":"Joint optimization of CycleGAN and CNN classifier for detection and localization of retinal pathologies on color fundus photographs","volume":"26","author":"Zhang","year":"2022","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref30","doi-asserted-by":"publisher","first-page":"2988","DOI":"10.1109\/JBHI.2020.3046771","article-title":"DeepUWF: an automated ultra-wide-field fundus screening system via deep learning","volume":"25","author":"Zhang","year":"2021","journal-title":"IEEE J. Biomed. Health Inform."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1937520\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T04:28:32Z","timestamp":1789964912000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2026.1937520\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":30,"alternative-id":["10.3389\/frai.2026.1937520"],"URL":"https:\/\/doi.org\/10.3389\/frai.2026.1937520","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]},"article-number":"1937520"}}