{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T05:46:26Z","timestamp":1782279986792,"version":"3.54.5"},"reference-count":26,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T00:00:00Z","timestamp":1782259200000},"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. Physiol."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Retinal diseases are a leading cause of visual impairment worldwide, highlighting the need for accurate and scalable automated screening systems. This study introduces RHT-Net (Retinal Hybrid Transformer Network), a novel hybrid deep learning architecture designed for multi-class classification of nine retinal diseases from color fundus images by combining the strengths of convolutional neural networks and transformer encoders.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>RHT-Net integrates residual convolutional neural networks for local feature extraction with transformer encoders to capture long-range global dependencies. A real-world dataset comprising 5,318 color fundus images collected from Bengali patients was used in this study. Data augmentation techniques, including rotation, flipping, and Gaussian noise addition, expanded the dataset to 21,272 images. Images were preprocessed through resizing to 224 \u00d7 224 pixels and contrast enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE). The augmented dataset was divided into training (80%) and testing (20%) subsets for model development and evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed RHT-Net achieved a training accuracy of 97.93% with an F1-score of 96.10%. On the testing set, the model attained an accuracy of 96.12% and an F1-score of 92.28%. The overall classification performance reached an accuracy of 97.57% and an F1-score of 95.31%. Comprehensive evaluations, including class-wise performance analysis, confusion matrices, and Grad-CAM visualizations, demonstrated the model\u2019s strong predictive capability, robustness, and interpretability across the nine retinal disease classes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>The findings indicate that RHT-Net is a promising and scalable approach for early retinal disease screening. By effectively capturing both local and global image features, the model achieves high classification performance while providing interpretable predictions. These characteristics support its potential integration into telemedicine and remote diagnostic workflows. However, further external validation and deployment-oriented optimization are necessary before real-world clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fphys.2026.1837336","type":"journal-article","created":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T04:48:25Z","timestamp":1782276505000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Advanced retinal disease detection using RHT-Net: a hybrid deep learning approach with augmented fundus imaging"],"prefix":"10.3389","volume":"17","author":[{"given":"Yaoyang","family":"Cheng","sequence":"first","affiliation":[{"name":"Institute of Intelligent Media Computing, Hangzhou Dianzi University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiling","family":"Pan","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Media Computing, Hangzhou Dianzi University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guodao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Intelligent Media Computing, Hangzhou Dianzi University","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Wu","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry, Wuyi University","place":["Wuyishan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yisu","family":"Ge","sequence":"additional","affiliation":[{"name":"Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry, Wuyi University","place":["Wuyishan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology, Zhongshan Hospital, Fudan University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"30469","DOI":"10.1038\/s41598-025-16415-5","article-title":"Multi-stage framework using transformer models, feature fusion and ensemble learning for enhancing eye disease classification","volume":"15","author":"AlMohimeed","year":"2025","journal-title":"Sci. Rep."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.110164","article-title":"Effivit: Hybrid CNN-transformer for retinal imaging","volume":"191","author":"Ashoka","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103956","article-title":"MIL-ViT: A multiple-instance vision transformer for fundus image classification","volume":"97","author":"Bi","year":"2023","journal-title":"J. Visual Commun. Img Rep"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2504.08481","article-title":"A hybrid fully convolutional CNN-Transformer model for inherently interpretable disease detection from retinal fundus images","author":"Djoumessi","year":"2025"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2405.07338","article-title":"Explainable convolutional neural networks for retinal fundus classification and cutting-edge segmentation models for retinal blood vessels from fundus images","author":"Faria","year":"2024"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2507.21922","article-title":"SwinECAT: A Transformer-based fundus disease classification model with Shifted Window Attention and Efficient Channel Attention","author":"Gu","year":"2025","journal-title":"arXiv"},{"key":"B8","doi-asserted-by":"publisher","first-page":"37258","DOI":"10.1038\/s41598-025-21229-6","article-title":"Privacy preservation in diabetic disease prediction using federated learning based on efficient cross stage recurrent model","volume":"15","author":"Jayalakshmi","year":"2025","journal-title":"Sci. Rep."},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1109\/ECCE64574.2025.11013100","volume-title":"An interpretable diagnosis of retinal diseases using vision transformer and grad-CAM","author":"Jilan","year":"2025"},{"key":"B10","doi-asserted-by":"crossref","DOI":"10.1109\/ICFTS62006.2025.11031986","volume-title":"Hybrid CNN-viT model with grad-CAM for ocular disease detection","author":"Kaleel","year":"2025"},{"key":"B11","first-page":"717","article-title":"Hybridizing convolutional and transformer networks for diabetic retinopathy detection in retinal images","author":"Kavitha","year":"2025"},{"key":"B12","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":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105607","article-title":"Lesion identification in fundus images via convolutional neural network-vision transformer","volume":"88","author":"Lian","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.107352","article-title":"STMF-DRNet: A multi-branch fine-grained classification model for diabetic retinopathy using Swin-TransformerV2","volume":"103","author":"Liu","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B15","volume-title":"VGG-ST: A VGG-swin transformer-based model for ROP disease diagnosis","author":"Luo","year":"2024"},{"key":"B16","first-page":"1979","article-title":"Integrating convolutional and transformer networks for efficient retinal disease screening","author":"Sathiya","year":"2025"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2024.110979","article-title":"A dataset of color fundus images for the detection and classification of eye diseases","volume":"57","author":"Sharmin","year":"2024","journal-title":"Data Brief"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2022.106445","article-title":"Structure-oriented transformer for retinal diseases grading from OCT images","volume":"152","author":"Shen","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B19","first-page":"902","article-title":"Graph enhanced transformers for predicting drug using drug synergies and antagonistic interactions","author":"herine","year":"2025"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.21465","article-title":"Retinal fundus multi-disease image classification using hybrid CNN-Transformer-ensemble architectures","author":"Singh","year":"2025"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2025.110410","article-title":"Image-level multi-label retinal disease classification with a novel classification head","volume":"124","author":"Sivaz","year":"2025","journal-title":"Comput. Electr Eng"},{"key":"B22","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":"B23","doi-asserted-by":"publisher","first-page":"71-85","DOI":"10.1007\/978-3-031-98161-6_6","article-title":"Doctor AI: A Hybrid Model for Clinical Ocular Disease Classification","author":"Thinh","year":"2025","journal-title":"International Conference on Computational Intelligence in Engineering Science"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2023.1290803","article-title":"Multi-label classification of retinal disease via a novel vision transformer model","volume":"17","author":"Wang","year":"2024","journal-title":"Front. Neurosci."},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2023.1293019","article-title":"A hybrid neural network approach for classifying diabetic retinopathy subtypes","volume":"10","author":"Xu","year":"2024","journal-title":"Front. Med."},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiolchem.2024.108241","article-title":"A multi-class fundus disease classification system based on an adaptive scale discriminator and hybrid loss","volume":"113","author":"Zhou","year":"2024","journal-title":"Comput. Biol. Chem."}],"container-title":["Frontiers in Physiology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1837336\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T04:48:47Z","timestamp":1782276527000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphys.2026.1837336\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,24]]},"references-count":26,"alternative-id":["10.3389\/fphys.2026.1837336"],"URL":"https:\/\/doi.org\/10.3389\/fphys.2026.1837336","relation":{},"ISSN":["1664-042X"],"issn-type":[{"value":"1664-042X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,24]]},"article-number":"1837336"}}