{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T23:46:58Z","timestamp":1791330418222,"version":"4.3.1"},"reference-count":70,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T00:00:00Z","timestamp":1749168000000},"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. Cell Dev. Biol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The retina plays a critical role in visual perception, yet lesions affecting it can lead to severe and irreversible visual impairment. Consequently, early diagnosis and precise identification of these retinal lesions are essential for slowing disease progression. Optical coherence tomography (OCT) stands out as a pivotal imaging modality in ophthalmology due to its exceptional performance, while the inherent complexity of retinal structures and significant noise interference present substantial challenges for both manual interpretation and AI-assisted diagnosis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose MSLI-Net, a novel framework built upon the ResNet50 backbone, which enhances the global receptive field via a multi-scale dilation fusion module (MDF) to better capture long-range dependencies. Additionally, a multi-segmented lesion localization module (LLM) is integrated within each branch of a modified feature pyramid network (FPN) to effectively extract critical features while suppressing background noise through parallel branch refinement, and a wavelet subband spatial attention module (WSSA) is designed to significantly improve the model\u2019s overall performance in noise suppression by collaboratively processing and exchanging information between the low- and high-frequency subbands extracted through wavelet decomposition.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Experimental evaluation on the OCT-C8 dataset demonstrates that MSLI-Net achieves 96.72% accuracy in retinopathy classification, underscoring its strong discriminative performance and promising potential for clinical application.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This model provides new research ideas for the early diagnosis of retinal diseases and helps drive the development of future high-precision medical imaging-assisted diagnostic systems.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fcell.2025.1608325","type":"journal-article","created":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T01:22:26Z","timestamp":1749172946000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":24,"title":["MSLI-Net: retinal disease detection network based on multi-segment localization and multi-scale interaction"],"prefix":"10.3389","volume":"13","author":[{"given":"Zhenjia","family":"Qi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jilan","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoli","family":"Long","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siyue","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangliang","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,6]]},"reference":[{"key":"B1","first-page":"854","article-title":"WCAM: wavelet convolutional attention module SoutheastCon 2024","author":"Alaba","year":"2024"},{"key":"B2","first-page":"8120661","article-title":"Classification of sd-OCT images using a deep learning approach","volume-title":"IEEE International Conference on Signal and Image Processing Applications","author":"Awais","year":"2017"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.00351","article-title":"Multi-scale feature enhancement in multi-task learning for medical image analysis","author":"Bui","year":"2024"},{"key":"B4","first-page":"98","volume-title":"Wavelets and wavelet transforms","author":"Burrus","year":"1998"},{"key":"B5","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"},{"key":"B6","doi-asserted-by":"publisher","first-page":"104810","DOI":"10.1016\/j.bspc.2023.104810","article-title":"Classification and segmentation of OCT images for age-related macular degeneration based on dual guidance networks","volume":"84","author":"Diao","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B7","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":"B8","doi-asserted-by":"publisher","first-page":"3008","DOI":"10.1109\/TMI.2020.2983721","article-title":"CPFNet: context pyramid fusion network for medical image segmentation","volume":"39","author":"Feng","year":"2020","journal-title":"IEEE Trans. Med. imaging"},{"key":"B9","first-page":"363","volume-title":"Wavelet convolutions for large receptive fields European Conference on Computer Vision","author":"Finder","year":"2024"},{"key":"B10","first-page":"17","volume-title":"Wavelets: theory and applications for manufacturingFrom fourier transform to wavelet transform: a historical perspective","author":"Gao","year":"2010"},{"key":"B11","doi-asserted-by":"publisher","first-page":"2308","DOI":"10.18240\/ijo.2024.12.20","article-title":"Development and research status of intelligent ophthalmology in China","volume":"17","author":"Gong","year":"2024","journal-title":"Int. J. Ophthalmol."},{"key":"B12","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/bs.pmbts.2015.06.001","article-title":"Introduction to the retina","volume":"134","author":"Grossniklaus","year":"2015","journal-title":"Prog. Mol. Biol. Transl. Sci."},{"key":"B13","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":"B14","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B15","doi-asserted-by":"publisher","first-page":"231","DOI":"10.3233\/fi-2019-1830","article-title":"Improvement of cerebral microbleeds detection based on discriminative feature learning","volume":"168","author":"Hong","year":"","journal-title":"Fundam. Inf."},{"key":"B16","doi-asserted-by":"publisher","first-page":"1123","DOI":"10.1007\/s00138-019-01029-5","article-title":"Detecting cerebral microbleeds with transfer learning","volume":"30","author":"Hong","year":"","journal-title":"Mach. Vis. Appl."},{"key":"B17","doi-asserted-by":"publisher","first-page":"584682","DOI":"10.3389\/fneur.2020.584682","article-title":"Brain age prediction of children using routine brain MR images via deep learning","volume":"11","author":"Hong","year":"","journal-title":"Front. Neurology"},{"key":"B18","doi-asserted-by":"publisher","first-page":"15151","DOI":"10.1007\/s11042-018-6862-z","article-title":"Classification of cerebral microbleeds based on fully-optimized convolutional neural network","volume":"79","author":"Hong","year":"","journal-title":"Multimedia Tools Appl."},{"key":"B19","doi-asserted-by":"publisher","first-page":"108729","DOI":"10.1016\/j.asoc.2022.108729","article-title":"Unsupervised domain adaptation for cross-modality liver segmentation via joint adversarial learning and self-learning","volume":"121","author":"Hong","year":"","journal-title":"Appl. Soft Comput."},{"key":"B20","doi-asserted-by":"publisher","first-page":"109155","DOI":"10.1016\/j.knosys.2022.109155","article-title":"Source-free unsupervised domain adaptation for cross-modality abdominal multi-organ segmentation","volume":"250","author":"Hong","year":"","journal-title":"Knowledge-Based Syst."},{"key":"B21","first-page":"7132","article-title":"Squeeze-and-excitation networks","author":"Hu","year":"2018","journal-title":"Proc. IEEE Conf. Comput. Vis. pattern Recognit."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1126\/science.1957169","article-title":"Optical coherence tomography","volume":"254","author":"Huang","year":"1991","journal-title":"science"},{"key":"B23","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":"B24","doi-asserted-by":"publisher","first-page":"3406890","DOI":"10.1155\/2022\/3406890","article-title":"Research progress of artificial intelligence image analysis in systemic disease\u2010related ophthalmopathy","volume":"2022","author":"Ji","year":"2022","journal-title":"Dis. Markers"},{"key":"B25","first-page":"964","article-title":"Optic-net: a novel convolutional neural network for diagnosis of retinal diseases from optical tomography images","author":"Kamran","year":"2019"},{"key":"B26","doi-asserted-by":"publisher","first-page":"189","DOI":"10.3390\/diagnostics13020189","article-title":"The classification of common macular diseases using deep learning on optical coherence tomography images with and without prior automated segmentation","volume":"13","author":"Kaothanthong","year":"2023","journal-title":"Diagnostics"},{"key":"B27","doi-asserted-by":"publisher","first-page":"104176","DOI":"10.1016\/j.bspc.2022.104176","article-title":"Convolution neural networks for optical coherence tomography (OCT) image classification","volume":"79","author":"Karthik","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"B28","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":"B29","doi-asserted-by":"publisher","first-page":"3003","DOI":"10.3390\/math12193003","article-title":"OCTNet: a modified multi-scale attention feature fusion network with InceptionV3 for retinal OCT image classification","volume":"12","author":"Khalil","year":"2024","journal-title":"Mathematics"},{"key":"B30","article-title":"Densely connected convolutional networks","author":"Kq","year":"2018"},{"key":"B31","doi-asserted-by":"publisher","first-page":"108726","DOI":"10.1016\/j.compbiomed.2024.108726","article-title":"Htc-retina: a hybrid retinal diseases classification model using transformer-convolutional neural network from optical coherence tomography images","volume":"178","author":"Laouarem","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"B32","doi-asserted-by":"publisher","first-page":"6204","DOI":"10.1364\/BOE.10.006204","article-title":"Deep learning-based automated detection of retinal diseases using optical coherence tomography images","volume":"10","author":"Li","year":"2019","journal-title":"Biomed. Opt. express"},{"key":"B33","doi-asserted-by":"publisher","first-page":"106028","DOI":"10.1016\/j.bspc.2024.106028","article-title":"Source-free unsupervised adaptive segmentation for knee joint MRI","volume":"92","author":"Li","year":"2024","journal-title":"Biomed. Signal Process. Control"},{"key":"B34","first-page":"1","article-title":"Efficient dense modules of asymmetric convolution for real-time semantic segmentation","volume-title":"Proceedings of the 1st ACM International Conference on Multimedia in Asia","author":"Lo","year":"2019"},{"key":"B35","doi-asserted-by":"publisher","first-page":"106791","DOI":"10.1016\/j.compbiomed.2023.106791","article-title":"MedViT: a robust vision transformer for generalized medical image classification","volume":"157","author":"Manzari","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"B36","first-page":"552","volume-title":"Espnet: efficient spatial pyramid of dilated convolutions for semantic segmentationProceedings of the european conference on computer vision (ECCV)","author":"Mehta","year":"2018"},{"key":"B37","article-title":"Retinal OCT image classification - C8","author":"Obuli","year":"2021"},{"key":"B38","doi-asserted-by":"publisher","first-page":"150","DOI":"10.3390\/s24010150","article-title":"Multi-scale-denoising residual convolutional network for retinal disease classification using OCT","volume":"24","author":"Peng","year":"2023","journal-title":"Sensors"},{"key":"B39","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1186\/s40662-016-0063-5","article-title":"Epidemiology of age-related macular degeneration (AMD): associations with cardiovascular disease phenotypes and lipid factors","volume":"3","author":"Pennington","year":"2016","journal-title":"Eye Vis."},{"key":"B40","doi-asserted-by":"publisher","first-page":"107161","DOI":"10.1016\/j.bspc.2024.107161","article-title":"Enhanced diagnosis of thyroid-associated eye diseases based on deep learning: a novel triplet loss design strategy","volume":"100","author":"Qian","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B41","first-page":"175","article-title":"Prevalence of Asymptomatic Eye Disease Pr\u00e9valence des maladies oculaires asymptomatiques","volume":"65","author":"Robinson","year":"2003","journal-title":"Rev. Can. D'Optom\u00e9trie"},{"key":"B42","doi-asserted-by":"publisher","first-page":"109447","DOI":"10.1016\/j.compbiomed.2024.109447","article-title":"AELGNet: attention-based enhanced local and global features network for medicinal leaf and plant classification","volume":"184","author":"Sharma","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"B43","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"B44","doi-asserted-by":"publisher","first-page":"1505530","DOI":"10.3389\/fmed.2025.1505530","article-title":"Construction of a predictive model for the efficacy of anti-VEGF therapy in macular edema patients based on OCT imaging: a retrospective study","volume":"12","author":"Song","year":"2025","journal-title":"Front. Med."},{"key":"B45","doi-asserted-by":"publisher","first-page":"107988","DOI":"10.1016\/j.engappai.2024.107988","article-title":"Real-time semantic segmentation network with an enhanced backbone based on Atrous spatial pyramid pooling module","volume":"133","author":"Song","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"B46","first-page":"1","article-title":"Classification of retinal oct images using deep learning","author":"Subramanian","year":"2022"},{"key":"B47","doi-asserted-by":"publisher","first-page":"105877","DOI":"10.1016\/j.cmpb.2020.105877","article-title":"OCTnet: a lightweight cnn for retinal disease classification from optical coherence tomography images","volume":"200","author":"Sunija","year":"2021","journal-title":"Comput. methods programs Biomed."},{"key":"B48","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"B49","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"B50","article-title":"Haar wavelet based approach for image compression and quality assessment of compressed image","author":"Talukder","year":"2010"},{"key":"B51","first-page":"6105","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1","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":"B53","doi-asserted-by":"publisher","first-page":"1309097","DOI":"10.3389\/fmed.2023.1309097","article-title":"DBPF-net: dual-branch structural feature extraction reinforcement network for ocular surface disease image classification","volume":"10","author":"Wan","year":"2024","journal-title":"Front. Med."},{"key":"B54","doi-asserted-by":"publisher","first-page":"6057","DOI":"10.1364\/BOE.10.006057","article-title":"Deep learning for quality assessment of retinal OCT images","volume":"10","author":"Wang","year":"2019","journal-title":"Biomed. Opt. express"},{"key":"B55","doi-asserted-by":"publisher","first-page":"111030","DOI":"10.1016\/j.knosys.2023.111030","article-title":"CTransCNN: combining transformer and CNN in multilabel medical image classification","volume":"281","author":"Wu","year":"2023","journal-title":"Knowledge-Based Syst."},{"key":"B56","doi-asserted-by":"publisher","first-page":"6404","DOI":"10.1109\/ICCV51070.2023.00589","article-title":"ADNet: lane shape prediction via anchor decomposition","author":"Xiao","year":"2023","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"B57","doi-asserted-by":"publisher","first-page":"821565","DOI":"10.3389\/fmed.2022.821565","article-title":"A few-shot learning-based retinal vessel segmentation method for assisting in the central serous chorioretinopathy laser surgery","volume":"9","author":"Xu","year":"","journal-title":"Front. Med."},{"key":"B58","doi-asserted-by":"publisher","first-page":"105730","DOI":"10.1016\/j.compbiomed.2022.105730","article-title":"An intelligent location method of key boundary points for assisting the diameter measurement of central serous chorioretinopathy lesion area","volume":"147","author":"Xu","year":"","journal-title":"Comput. Biol. Med."},{"key":"B59","doi-asserted-by":"publisher","first-page":"104056","DOI":"10.1016\/j.compbiomed.2020.104056","article-title":"Weakly supervised detection of central serous chorioretinopathy based on local binary patterns and discrete wavelet transform","volume":"127","author":"Xu","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"B60","doi-asserted-by":"publisher","first-page":"107544","DOI":"10.1016\/j.bspc.2025.107544","article-title":"CRAT: advanced transformer-based deep learning algorithms in OCT image classification","volume":"104","author":"Yang","year":"2025","journal-title":"Biomed. Signal Process. Control"},{"key":"B61","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015"},{"key":"B62","doi-asserted-by":"publisher","first-page":"125937","DOI":"10.1016\/j.eswa.2024.125937","article-title":"ANC-Net: a novel multi-scale active noise cancellation network for rotating machinery fault diagnosis based on discrete wavelet transform","volume":"265","author":"Yu","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"B63","doi-asserted-by":"publisher","first-page":"1730501","DOI":"10.1155\/2022\/1730501","article-title":"Hypermixed convolutional neural network for retinal vein occlusion classification","volume":"2022","author":"Zhang","year":"2022","journal-title":"Dis. Markers"},{"key":"B64","first-page":"5978","article-title":"Deep stacked hierarchical multi-patch network for image deblurring","author":"Zhang","year":"2019"},{"key":"B65","doi-asserted-by":"publisher","first-page":"1573329","DOI":"10.3389\/fmed.2025.1573329","article-title":"A scoping review of advancements in machine learning for glaucoma: current trends and future direction","volume":"12","author":"Zhang","year":"2025","journal-title":"Front. Med."},{"key":"B66","doi-asserted-by":"publisher","first-page":"1492808","DOI":"10.3389\/fmed.2024.1492808","article-title":"Effective automatic classification methods via deep learning for myopic maculopathy","volume":"11","author":"Zhang","year":"2024","journal-title":"Front. Med."},{"key":"B67","doi-asserted-by":"publisher","first-page":"915","DOI":"10.1007\/s00530-022-00889-8","article-title":"Wavelet-Attention CNN for image classification","volume":"28","author":"Zhao","year":"2022","journal-title":"Multimed. Syst."},{"key":"B68","doi-asserted-by":"publisher","first-page":"S53","DOI":"10.4103\/IJO.IJO_48_23","article-title":"Research on an artificial intelligence-based myopic maculopathy grading method using EfficientNet","volume":"72","author":"Zheng","year":"2024","journal-title":"Indian J. Ophthalmol."},{"key":"B69","doi-asserted-by":"publisher","first-page":"808402","DOI":"10.3389\/fmed.2022.808402","article-title":"Screening of common retinal diseases using six-category models based on EfficientNet","volume":"9","author":"Zhu","year":"2022","journal-title":"Front. Med."},{"key":"B70","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."}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1608325\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T01:22:29Z","timestamp":1749172949000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2025.1608325\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,6]]},"references-count":70,"alternative-id":["10.3389\/fcell.2025.1608325"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2025.1608325","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,6]]},"article-number":"1608325"}}