{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:03:29Z","timestamp":1759190609541,"version":"3.44.0"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"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. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>With optical coherence tomography (OCT), doctors are able to see cross-sections of the retinal layers and diagnose retinal diseases. Computer-aided diagnosis algorithms such as convolutional neural networks (CNNs) and vision Transformers (ViTs) enhance diagnostic efficiency by automatically analyzing these OCT images. However, CNNs are less effective in extracting global features and ViTs lack the local inductive bias and typically require large amounts of training data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this paper, we presented a hybrid retinal diseases classification and diagnosis network named HyReti-Net which incorporated two branches. One branch extracted local features by leveraging the spatial hierarchy learning capabilities of ResNet-50, while the other branch was established based on Swin Transformer to consider the global information. In addition, we proposed a feature fusion module (FFM) consisting of a concatenation and residual block and the improved channel attention block to retain local and global features more effectively. The multi-level features fusion mechanism was used to further enhance the ability of global feature extraction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Evaluation and comparison were used to show the advantage of the proposed architecture. Five metrics were applied to compare the performance of existing methods. Moreover, ablation studies were carried out to evaluate their effects on the foundational model. For each public dataset, heatmaps were also generated to enhance the interpretability of OCT image classification. The results underscored the effectiveness and advantage of the proposed method which achieved the highest classification accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>In this article, a hybrid multi-scale network model integrating dual-branches and a features fusion module was proposed to diagnose retinal diseases. The performance of the proposed method produced promising classification results. On the OCT-2014, OCT-2017 and OCT-C8, experimental results indicated that HyReti-Net achieved better performance than the state-of-the-art networks. This study can provide a reference for clinical diagnosis of ophthalmologists through artificial intelligence technology.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1660920","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T05:25:22Z","timestamp":1759123522000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["HyReti-Net: hybrid retinal diseases classification and diagnosis network using optical coherence tomography"],"prefix":"10.3389","volume":"12","author":[{"given":"Jikun","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chaoliang","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxi","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenbo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaili","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liwei","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"101971","DOI":"10.1016\/j.media.2021.101971","article-title":"Applications of deep learning in fundus images: a review","volume":"69","author":"Li","year":"2021","journal-title":"Med Image Anal"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"140","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":"ref3","doi-asserted-by":"publisher","first-page":"5393","DOI":"10.3390\/s23125393","article-title":"Enhanced deep learning model for classification of retinal optical coherence tomography images","volume":"23","author":"Hassan","year":"2023","journal-title":"Sensors"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"92352","DOI":"10.1109\/ACCESS.2020.2994047","article-title":"Retinal image classification by self-supervised fuzzy clustering network","volume":"8","author":"Luo","year":"2020","journal-title":"IEEE Access"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.ophtha.2012.10.036","article-title":"Clinical classification of age-related macular degeneration","volume":"120","author":"Ferris","year":"2013","journal-title":"Ophthalmology"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1088\/0034-4885\/66\/2\/204","article-title":"Optical coherence tomography-principles and applications","volume":"66","author":"Fercher","year":"2003","journal-title":"Rep Prog Phys"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"102538","DOI":"10.1016\/j.cmpb.2021.106294","article-title":"A novel multiscale convolutional neural network based age-related macular degeneration detection using OCT images","volume":"67","author":"Thomas","year":"2021","journal-title":"Biomed Signal Proces Control"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1309","DOI":"10.3390\/diagnostics13071309","article-title":"CNV-Net: segmentation, classification and activity score measurement of choroidal neovascularization (CNV) using optical coherence tomography angiography (OCTA)","volume":"13","author":"Vali","year":"2023","journal-title":"Diagnostics"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"114","DOI":"10.1186\/s12886-020-01382-4","article-title":"Classification of optical coherence tomography images using a capsule network","volume":"20","author":"Tsuji","year":"2020","journal-title":"BMC Ophthalmol"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"4787","DOI":"10.2147\/DMSO.S288419","article-title":"Identifying diabetic macular edema and other retinal diseases by optical coherence tomography image and multiscale deep learning","volume":"13","author":"Zhang","year":"2020","journal-title":"Diabetes Metab Syndr Obes"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/s42979-022-01024-0","article-title":"Macularnet: towards fully automated attention-based deep CNN for macular disease classification","volume":"3","author":"Mishra","year":"2022","journal-title":"SN Comput Sci"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"106445","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":"ref13","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"9355","DOI":"10.48550\/arXiv.2104.13840","article-title":"Twins: revisiting the design of spatial attention in vision transformers","volume":"34","author":"Chu","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"e37532","DOI":"10.2196\/37532","article-title":"Emerging trends and research foci in artificial intelligence for retinal diseases: bibliometric and visualization study","volume":"24","author":"Zhao","year":"2022","journal-title":"J Med Internet Res"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1016\/j.ophtha.2019.11.004","article-title":"Consensus nomenclature for reporting neovascular age-related macular degeneration data: consensus on neovascular age-related macular degeneration nomenclature study group","volume":"127","author":"Spaide","year":"2020","journal-title":"Ophthalmology"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1334","DOI":"10.1001\/jamaophthalmol.2014.2854","article-title":"Prevalence of and risk factors for diabetic macular edema in the United States","volume":"132","author":"Varma","year":"2014","journal-title":"JAMA Ophthalmol"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"2653","DOI":"10.2337\/diacare.26.9.2653","article-title":"Diabetic retinopathy and diabetic macular edema: pathophysiology, screening, and novel therapies","volume":"26","author":"Ciulla","year":"2003","journal-title":"Diabetes Care"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1167\/tvst.7.6.41","article-title":"Deep learning-based automated classification of multi-categorical abnormalities from optical coherence tomography images","volume":"7","author":"Lu","year":"2018","journal-title":"Transl Vis Sci Technol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying medical diagnoses and treatable diseases by image-based deep learning","volume":"172","author":"Kermany","year":"2018","journal-title":"Cell"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1026","DOI":"10.1109\/LSP.2019.2917779","article-title":"Automatic classification of retinal optical coherence tomography images with layer guided convolutional neural network","volume":"26","author":"Huang","year":"2019","journal-title":"IEEE Signal Process Lett"},{"key":"ref22","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","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","journal-title":"arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.05704","article-title":"Escaping the big data paradigm with compact transformers","author":"Hassani","year":"2021","journal-title":"arXiv"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.48550\/arXiv.2106.04803","article-title":"Coatnet: marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv Neural Inf Proces Syst"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"3637","DOI":"10.1038\/s41598-023-30853-z","article-title":"An interpretable transformer network for the retinal disease classification using optical coherence tomography","volume":"13","author":"He","year":"2023","journal-title":"Sci Rep"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"101985","DOI":"10.1016\/j.media.2021.101985","article-title":"A survey on incorporating domain knowledge into deep learning for medical image analysis","volume":"69","author":"Xie","year":"2021","journal-title":"Med Image Anal"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"542","DOI":"10.3390\/bios12070542","article-title":"HCTNet: a hybrid ConvNet-transformer network for retinal optical coherence tomography image classification","volume":"12","author":"Ma","year":"2022","journal-title":"Biosensors"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.11854","article-title":"WaveNet-SF: a hybrid network for retinal disease detection based on wavelet transform in the spatial-frequency domain","author":"Cheng","year":"2025","journal-title":"arXiv"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1608325","DOI":"10.3389\/fcell.2025.1608325","article-title":"MSLI-net: retinal disease detection network based on multi-segment localization and multi-scale interaction","volume":"13","author":"Qi","year":"2025","journal-title":"Front Cell Dev Biol"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"e26405","DOI":"10.1016\/j.heliyon.2024.e26405","article-title":"Improved neural network with multi-task learning for Alzheimer's disease classification","volume":"10","author":"Zhang","year":"2024","journal-title":"Heliyon"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3411133","article-title":"A hierarchical full-resolution fusion network and topology-aware connectivity booster for retinal vessel segmentation","volume":"73","author":"Su","year":"2024","journal-title":"IEEE Trans Instrum Meas"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1484880","DOI":"10.3389\/fcell.2024.1484880","article-title":"Multi-resolution visual mamba with multi-directional selective mechanism for retinal disease detection","volume":"12","author":"Zuo","year":"2024","journal-title":"Front Cell Dev Biol"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.17632\/rscbjbr9sj.2","article-title":"Labeled optical coherence tomography (oct) and chest x-ray images for classification","author":"Kermany","year":"2018","journal-title":"Mendeley Data"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"3568","DOI":"10.1364\/BOE.5.003568","article-title":"Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images","volume":"5","author":"Srinivasan","year":"2014","journal-title":"Biomed Opt Express"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.survophthal.2024.11.007","article-title":"Applications of artificial intelligence to inherited retinal diseases: a systematic review","volume":"70","author":"Issa","year":"2025","journal-title":"Surv Ophthalmol"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"3332","DOI":"10.1109\/JBHI.2021.3083605","article-title":"Ophthalmic disease detection via deep learning with a novel mixture loss function","volume":"25","author":"Luo","year":"2021","journal-title":"IEEE J Biomed Health Inform"},{"key":"ref38","first-page":"618","article-title":"Grad-cam: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1660920\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T05:25:26Z","timestamp":1759123526000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1660920\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":38,"alternative-id":["10.3389\/fmed.2025.1660920"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1660920","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,29]]},"article-number":"1660920"}}