{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T05:17:06Z","timestamp":1788239826528,"version":"build-2803163510"},"reference-count":47,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100019345","name":"King Salman Center for Disability Research","doi-asserted-by":"publisher","award":["KSCDR-ERC-2024-01"],"award-info":[{"award-number":["KSCDR-ERC-2024-01"]}],"id":[{"id":"10.13039\/501100019345","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Med."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Vision impairment caused by retinal diseases stands out as one of the significant sources of irreversible blindness, highlighting the importance of developing robust automated screening tools to detect eye diseases at an early stage. Despite the promising results of recent deep learning approaches to the automatic classification of retinal images, most existing solutions focus on image-based representations and do not consider the importance of vascular topology. To overcome the limitations, this study proposes VG-RETFound \u2013 a hybrid framework based on a retinal foundation model and graph-based vascular-topology modeling that can be used to classify multiple retinal categories and detect vision impairment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The authors use RETFound\u2014a retinal foundation model\u2014pretrained on a vast number of retinal images, as well as the Graph Attention Network (GAT), to learn vascular topology features by representing retinal vessels as graphs. The presented approach employs a cross-modal multi-head attention fusion method to integrate features from both modalities in real time. To evaluate the efficiency of VG-RETFound, experiments were conducted using the RFMiD and ODIR-5 K datasets for model training and testing across six retinal categories: Normal, Diabetic Retinopathy, Pathological Myopia, Age-related Macular Degeneration, Hypertensive Retinopathy, and Other Retinal Diseases.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The accuracy of 96.39%, F1-score of 95.84%, MCC of 94.87%, and Kappa of 94.71% were attained on an internal test dataset, while cross-dataset external validation on the BRSET dataset revealed accuracy of 94.81%, F1-score of 94.25%, MCC of 93.09%, and Kappa of 92.94%.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings demonstrate that integrating retinal foundation models with anatomically informed vessel-topology learning significantly improves classification accuracy, interpretability, and generalization, highlighting the potential of VG-RETFound as a tool for large-scale vision impairment. screening and retinal disease diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1905129","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T04:27:41Z","timestamp":1788236861000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VG-RETFound: a hybrid retinal AI framework for early vision impairment screening through vessel-graph learning and cross-modal fusion"],"prefix":"10.3389","volume":"13","author":[{"given":"Ashit Kumar","family":"Dutta","sequence":"first","affiliation":[{"name":"Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University","place":["Riyadh, Saudi Arabia"]},{"name":"King Salman Center for Disability Research","place":["Riyadh, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nasser Ali","family":"Aljarallah","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Systems, College of Applied Sciences, AlMaarefa University","place":["Riyadh, Saudi Arabia"]},{"name":"King Salman Center for Disability Research","place":["Riyadh, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdul Rahaman","family":"Wahab Sait","sequence":"additional","affiliation":[{"name":"King Salman Center for Disability Research","place":["Riyadh, Saudi Arabia"]},{"name":"Department of Documents and Archive, Center of Documents and Administrative Communication, King Faisal University","place":["Al Hofuf, Al-Ahsa, Saudi Arabia"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e144","DOI":"10.1016\/S2214-109X(20)30489-7","article-title":"Causes of blindness and vision impairment in 2020 and trends over 30 years, and prevalence of avoidable blindness in relation to VISION 2020: the right to sight: an analysis for the global burden of disease study","volume":"9","author":"Steinmetz","year":"2021","journal-title":"Lancet Glob Health"},{"key":"B2","volume-title":"Report of the 2030 Targets on Effective Coverage of eye Care","year":"2022"},{"key":"B3","doi-asserted-by":"publisher","first-page":"e1221","DOI":"10.1016\/S2214-109X(17)30393-5","article-title":"Global causes of blindness and distance vision impairment 1990\u20132020: a systematic review and meta-analysis","volume":"5","author":"Flaxman","year":"2017","journal-title":"Lancet Glob Health"},{"key":"B4","doi-asserted-by":"publisher","first-page":"101354","DOI":"10.1016\/j.eclinm.2022.101354","article-title":"The economics of vision impairment and its leading causes: a systematic review","volume":"46","author":"Marques","year":"2022","journal-title":"eClinicalMed"},{"key":"B5","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1038\/s41572-025-00646-x","article-title":"Diabetic retinal disease","volume":"11","author":"Sivaprasad","year":"2025","journal-title":"Nat Rev Dis Primers"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.14336\/AD.2024.0124","article-title":"Recent advances in our understanding of age-related macular degeneration: mitochondrial dysfunction, redox signaling, and the complement system","volume":"16","author":"Buonfiglio","year":"2024","journal-title":"Aging Dis"},{"key":"B7","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s13024-025-00800-9","article-title":"Genetic context modulates aging and degeneration in the murine retina","volume":"20","author":"Marola","year":"2025","journal-title":"Mol Neurodegener"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-64573-1_200","article-title":"Artificial intelligence and deep learning in ophthalmology","author":"Wang","year":"2022","journal-title":"Artificial Intelligence in Medicine."},{"key":"B9","doi-asserted-by":"publisher","first-page":"264","DOI":"10.22608\/APO.2018479","article-title":"Promising artificial intelligence-machine learning-deep learning algorithms in ophthalmology","volume":"8","author":"Balyen","year":"2019","journal-title":"Asia Pac J Ophthalmol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"1018","DOI":"10.3390\/jcm9041018","article-title":"Artificial intelligence in ophthalmology: a meta-analysis of deep learning models for retinal vessels segmentation","volume":"9","author":"Islam","year":"2020","journal-title":"J Clin Med"},{"key":"B11","doi-asserted-by":"publisher","first-page":"101267","DOI":"10.1109\/ACCESS.2021.3094649","article-title":"Classification of eye diseases in fundus images","volume":"9","author":"Bernab\u00e9","year":"2021","journal-title":"IEEE Access"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1706","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":"B13","first-page":"627","article-title":"Automated ocular disease screening using machine learning and deep CNN architectures: implications for US ophthalmic care","author":"Paul","year":"2026"},{"key":"B14","doi-asserted-by":"publisher","first-page":"105","DOI":"10.3390\/diagnostics14010105","article-title":"Retinal disease diagnosis using deep learning on ultra-wide-field fundus images","volume":"14","author":"Nguyen","year":"2024","journal-title":"Diagnostics"},{"key":"B15","doi-asserted-by":"publisher","first-page":"11437","DOI":"10.3390\/app132011437","article-title":"Artificial intelligence-driven eye disease classification model","volume":"13","author":"Wahab Sait","year":"2023","journal-title":"Appl Sci"},{"key":"B16","first-page":"1","article-title":"Classification of eye disease from fundus images using efficientnet","volume":"2","author":"Bulut","year":"2022","journal-title":"Artif Intell Theory Appl"},{"key":"B17","doi-asserted-by":"publisher","first-page":"88745","DOI":"10.1007\/s11042-024-18938-x","article-title":"Deep learning of fundus imagfaes and optical coherence tomography images for ocular disease detection\u2014a review","volume":"83","author":"M","year":"2024","journal-title":"Multimed Tools Appl"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1995","DOI":"10.32604\/cmc.2023.039644","article-title":"Eye-Tracking based autism Spectrum disorder diagnosis using chaotic butterfly optimization with deep learning model","volume":"76","author":"Thanarajan","year":"2023","journal-title":"Comput Mater Contin"},{"key":"B19","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1007\/s11831-023-09989-8","article-title":"Analysis of deep learning techniques for prediction of eye diseases: a systematic review","volume":"31","author":"Bali","year":"2024","journal-title":"Arch Comput Methods Eng"},{"key":"B20","doi-asserted-by":"publisher","first-page":"3861","DOI":"10.1007\/s11831-022-09720-z","article-title":"Machine learning methods for diagnosis of eye-related diseases: a systematic review study based on ophthalmic imaging modalities","volume":"29","author":"Abbas","year":"2022","journal-title":"Arch Comput Methods Eng"},{"key":"B21","doi-asserted-by":"publisher","first-page":"84","DOI":"10.3390\/jimaging9040084","article-title":"Retinal disease detection using deep learning techniques: a comprehensive review","volume":"9","author":"Muchuchuti","year":"2023","journal-title":"J Imaging"},{"key":"B22","doi-asserted-by":"publisher","first-page":"e1947","DOI":"10.7717\/peerj-cs.1947","article-title":"A systematic review on diabetic retinopathy detection and classification based on deep learning techniques using fundus images","volume":"10","author":"Bhulakshmi","year":"2024","journal-title":"PeerJ Computer Science"},{"key":"B23","doi-asserted-by":"publisher","first-page":"9171","DOI":"10.1007\/s00521-024-09564-7","article-title":"Automated retinal disease classification using hybrid transformer model (SViT) using optical coherence tomography images","volume":"36","author":"Hemalakshmi","year":"2024","journal-title":"Neural Comput Appl"},{"key":"B24","doi-asserted-by":"publisher","first-page":"110164","DOI":"10.1016\/j.compbiomed.2025.110164","article-title":"Effivit: hybrid cnn-transformer for retinal imaging","volume":"191","author":"Rajatha","year":"2025","journal-title":"Comput Biol Med"},{"key":"B25","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1038\/s41586-023-06555-x","article-title":"A foundation model for generalizable disease detection from retinal images","volume":"622","author":"Zhou","year":"2023","journal-title":"Nature"},{"key":"B26","author":"Jang","year":"2024"},{"key":"B27","doi-asserted-by":"publisher","first-page":"137881","DOI":"10.1109\/ACCESS.2023.3339574","article-title":"Enhancing ocular healthcare: deep learning-based multi-class diabetic eye disease segmentation and classification","volume":"11","author":"Vadduri","year":"2023","journal-title":"IEEE Access"},{"key":"B28","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 Fus"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1966","DOI":"10.3390\/electronics11131966","article-title":"Multiple ocular disease diagnosis using fundus images based on multi-label deep learning classification","volume":"11","author":"Ouda","year":"2022","journal-title":"Electronics (Basel)"},{"key":"B30","doi-asserted-by":"publisher","first-page":"10551","DOI":"10.1007\/s00521-023-08249-x","article-title":"EyeDeep-Net: a multi-class diagnosis of retinal diseases using deep neural network","volume":"35","author":"Sengar","year":"2023","journal-title":"Neural Comput Appl"},{"key":"B31","doi-asserted-by":"publisher","first-page":"107565","DOI":"10.1016\/j.bspc.2025.107565","article-title":"A novel eye disease segmentation and classification model using advanced deep learning network","volume":"105","author":"Venkataiah","year":"2025","journal-title":"Biomed Signal Process Control"},{"key":"B32","unstructured":"Ali\n              MS\n            \n            \n              Islam\n              MK\n            \n          \n          Faculty of Engineering and Technology Islamic University\n          A hyper-tuned vision transformer model with explainable AI for eye disease detection and classification from medical images\n          \n          2023"},{"key":"B33","doi-asserted-by":"publisher","first-page":"117546","DOI":"10.1109\/ACCESS.2023.3326528","article-title":"Vision transformer model for predicting the severity of diabetic retinopathy in fundus photography-based retina images","volume":"11","author":"Nazih","year":"2023","journal-title":"IEEE Access"},{"key":"B34","first-page":"643","article-title":"Comprehensive evaluation of federated learning based models for disease detection in healthcare","author":"Jayalakshmi","year":"2024"},{"key":"B35","first-page":"71","article-title":"Classification of eye diseases in humans using vision transformer architecture model","author":"Purba","year":"2024"},{"key":"B36","first-page":"1979","article-title":"Integrating convolutional and transformer networks for efficient retinal disease screening","author":"Sathiya","year":"2025"},{"key":"B37","doi-asserted-by":"publisher","first-page":"6368","DOI":"10.1038\/s41598-026-35357-0","article-title":"Multi-class eye disease classification using deep learning EfficientNetB0 fusion techniques","volume":"16","author":"Sah","year":"2026","journal-title":"Sci Rep"},{"key":"B38","doi-asserted-by":"publisher","first-page":"19453","DOI":"10.1109\/ACCESS.2026.3659151","article-title":"EDDNet30: a spatial attention and multi-scale fusion model for enhanced eye disease classification with explainable AI","volume":"14","author":"Nirob","year":"2026","journal-title":"IEEE Access"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-026-38063-z","article-title":"Identification of multiple ocular diseases using a hybrid quantum convolutional neural network with fundus images","volume":"16","author":"Alqassab","year":"2026","journal-title":"Sci Rep"},{"key":"B40","first-page":"1","article-title":"Eye disease detection using GCN, GAT, and GraphSAGE","author":"Inbakumar","year":"2025"},{"key":"B41","year":""},{"key":"B42","year":""},{"key":"B43","year":""},{"key":"B44","doi-asserted-by":"publisher","first-page":"3110","DOI":"10.1007\/s10278-025-01416-7","article-title":"Multi-class classification of retinal eye diseases from ophthalmoscopy images using transfer learning-based vision transformers","volume":"38","author":"Cutur","year":"2025","journal-title":"J Imaging Inform Med"},{"key":"B45","doi-asserted-by":"publisher","first-page":"110598","DOI":"10.1016\/j.exer.2025.110598","article-title":"TL-GWO: fine-tuned transfer learning with grey wolf optimizer for accurate fundus image-based eye disease classification","volume":"260","author":"G\u00fcl","year":"2025","journal-title":"Exp Eye Res"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-026-54982-3","article-title":"Integrated deep learning model for multi-label retinal disease diagnosis","volume":"16","author":"Mahmood","year":"2026","journal-title":"Sci Rep"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3797024","article-title":"Interpretable AI models for detecting and classifying multiple retinal conditions using hybrid CNN-transformer-ensemble architectures","volume":"7","author":"Singh","year":"2026","journal-title":"ACM Trans Comput Healthcare"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1905129\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T04:27:42Z","timestamp":1788236862000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1905129\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,1]]},"references-count":47,"alternative-id":["10.3389\/fmed.2026.1905129"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1905129","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,1]]},"article-number":"1905129"}}