{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T15:32:33Z","timestamp":1765380753739,"version":"3.46.0"},"reference-count":50,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62001328"],"award-info":[{"award-number":["62001328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Open Fund of Hebei Chemical & Pharmaceutical College Intelligent Electromechanical Application Technology Collaborative Innovation Center"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,2,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Optical coherence tomography (OCT), a non-invasive imaging modality, holds significant clinical value in cardiology and ophthalmology. However, its imaging quality is often constrained by inherently limited resolution, thereby affecting diagnostic utility. For OCT-based diagnosis, enhancing perceptual quality that emphasizes human visual recognition ability and diagnostic effectiveness is crucial. Existing super-resolution methods prioritize reconstruction accuracy (e.g., PSNR optimization) but neglect perceptual quality. To address this, we propose a Multi-level Local-Global feature Fusion Generative Adversarial Network (MLGF-GAN) that systematically integrates local details, global contextual information, and multilevel features to fully exploit the recoverable information in the image. The Local Feature Extractor (LFE) employs Coordinate Attention-enhanced convolutional neural network (CNN) for lesion-focused local feature refinement, and the Global Feature Extractor (GFE) employs shifted-window Transformers to model long-range dependencies. The Multi-level Feature Fusion Structure (MFFS) hierarchically aggregates image features and adaptively processes information at different scales. The multi-scale (\u00d72, \u00d74, \u00d78) evaluations conducted on coronary and retinal OCT datasets demonstrate that the proposed model achieves highly competitive perceptual quality across all scales while maintaining reconstruction accuracy. The generated OCT super-resolution images exhibit superior texture detail restoration and spectral consistency, contributing to improved accuracy and reliability in clinical assessment. Furthermore, cross-pathology experiments further demonstrate that the proposed model possesses excellent generalization capability.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae2623","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T22:47:52Z","timestamp":1764629272000},"page":"015015","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MLGF-GAN: a multi-level local-global feature fusion GAN for OCT image super-resolution"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8326-3839","authenticated-orcid":true,"given":"Tingting","family":"Han","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jixing","family":"Han","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5016-703X","authenticated-orcid":true,"given":"Jihao","family":"Lang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenxia","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6157-144X","authenticated-orcid":true,"given":"Wei","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kuiyuan","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5110-8950","authenticated-orcid":true,"given":"Dandan","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"bpexae2623bib1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JBO.23.3.036011","type":"journal-article","article-title":"Optical coherence tomography retinal image reconstruction via nonlocal weighted sparse representation","volume":"23","author":"Abbasi","year":"2018","journal-title":"J. Biomed. Opt."},{"key":"bpexae2623bib2","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1364\/OL.507931","type":"journal-article","article-title":"Dual-convolutional neural network-enhanced strain estimation method for optical coherence elastography","volume":"49","author":"Bai","year":"2024","journal-title":"Opt. Lett."},{"key":"bpexae2623bib3","doi-asserted-by":"publisher","first-page":"6228","DOI":"10.48550\/arXiv.1711.06077","type":"other","article-title":"The perception-distortion tradeoff","author":"Blau","year":"2018"},{"key":"bpexae2623bib4","doi-asserted-by":"publisher","first-page":"1879","DOI":"10.1109\/EMBC44109.2020.9175777","type":"other","article-title":"Super-resolution technology to simultaneously improve optical & digital resolution of optical coherence tomography via deep learning","author":"Cao","year":"2020"},{"key":"bpexae2623bib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2019.101632","type":"journal-article","article-title":"Dn-gan: Denoising generative adversarial networks for speckle noise reduction in optical coherence tomography images","volume":"55","author":"Chen","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae2623bib6","doi-asserted-by":"publisher","first-page":"39946","DOI":"10.1364\/OE.439761","type":"journal-article","article-title":"Fast and accurate spectral-estimation axial super-resolution optical coherence tomography","volume":"29","author":"De Wit","year":"2021","journal-title":"Opt. Express"},{"key":"bpexae2623bib7","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/TPAMI.2015.2439281","type":"journal-article","article-title":"Image super-resolution using deep convolutional networks","volume":"38","author":"Dong","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"bpexae2623bib8","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1038\/86589","type":"journal-article","article-title":"Ultrahigh-resolution ophthalmic optical coherence tomography","volume":"7","author":"Drexler","year":"2001","journal-title":"Nat. Med."},{"key":"bpexae2623bib9","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1109\/TMI.2016.2611503","type":"journal-article","article-title":"Segmentation based sparse reconstruction of optical coherence tomography images","volume":"36","author":"Fang","year":"2016","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae2623bib10","doi-asserted-by":"publisher","first-page":"2034","DOI":"10.1109\/TMI.2013.2271904","type":"journal-article","article-title":"Fast acquisition and reconstruction of optical coherence tomography images via sparse representation","volume":"32","author":"Fang","year":"2013","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae2623bib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102280","type":"journal-article","article-title":"Super-resolution of magnetic resonance images using generative adversarial networks","volume":"108","author":"Guerreiro","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"bpexae2623bib12","doi-asserted-by":"publisher","first-page":"015008","DOI":"10.1088\/1361-6560\/ad111c","type":"journal-article","article-title":"Automatic stent struts detection in optical coherence tomography based on a multiple attention convolutional model","volume":"69","author":"Han","year":"2023","journal-title":"Physics in Medicine & Biology"},{"key":"bpexae2623bib13","doi-asserted-by":"publisher","first-page":"13713","DOI":"10.48550\/arXiv.2103.02907","type":"other","article-title":"Coordinate attention for efficient mobile network design","author":"Hou","year":"2021"},{"key":"bpexae2623bib14","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1016\/j.seppur.2025.133986","type":"journal-article","article-title":"Optical coherence tomography","volume":"254","author":"Huang","year":"1991","journal-title":"Science"},{"key":"bpexae2623bib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102374","type":"journal-article","article-title":"Deep local-to-global feature learning for medical image super-resolution","volume":"115","author":"Huang","year":"2024","journal-title":"Comput. Med. Imaging Graph."},{"key":"bpexae2623bib16","doi-asserted-by":"publisher","first-page":"12289","DOI":"10.1364\/OE.27.012289","type":"journal-article","article-title":"Simultaneous denoising and super-resolution of optical coherence tomography images based on generative adversarial network","volume":"27","author":"Huang","year":"2019","journal-title":"Opt. Express"},{"key":"bpexae2623bib17","doi-asserted-by":"publisher","DOI":"10.17632\/rscbjbr9sj.2","type":"other","article-title":"Labeled optical coherence tomography (oct) and chest x-ray images for classification","author":"Kermany","year":"2018"},{"key":"bpexae2623bib18","doi-asserted-by":"publisher","first-page":"2917","DOI":"10.1007\/s10462-023-10595-0","type":"journal-article","article-title":"A survey of the vision transformers and their cnn-transformer based variants","volume":"56","author":"Khan","year":"2023","journal-title":"Artif. Intell. Rev."},{"article-title":"Adam: a method for stochastic optimization","year":"2014","author":"Kingma","key":"bpexae2623bib19","type":"conference-proceedings"},{"key":"bpexae2623bib20","doi-asserted-by":"publisher","first-page":"4681","DOI":"10.48550\/arXiv.1609.04802","type":"other","article-title":"Photo-realistic single image super-resolution using a generative adversarial network","author":"Ledig","year":"2017"},{"key":"bpexae2623bib21","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1038\/s42003-023-04846-7","type":"journal-article","article-title":"Deep learning-based image enhancement in optical coherence tomography by exploiting interference fringe","volume":"6","author":"Lee","year":"2023","journal-title":"Communications Biology"},{"key":"bpexae2623bib22","doi-asserted-by":"publisher","first-page":"1833","DOI":"10.48550\/arXiv.2108.10257","type":"other","article-title":"Swinir: image restoration using swin transformer","author":"Liang","year":"2021"},{"key":"bpexae2623bib23","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/TMI.2021.3125061","type":"journal-article","article-title":"Comprehensive assessment of coronary calcification in intravascular oct using a spatial-temporal encoder-decoder network","volume":"41","author":"Li","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexae2623bib24","doi-asserted-by":"publisher","first-page":"2547","DOI":"10.1109\/TCSVT.2020.3027732","type":"journal-article","article-title":"Mdcn: multi-scale dense cross network for image super-resolution","volume":"31","author":"Li","year":"2020","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"bpexae2623bib25","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1007\/978-3-030-01237-3_32","type":"other","article-title":"Multi-scale residual network for image super-resolution","author":"Li","year":"2018"},{"key":"bpexae2623bib26","doi-asserted-by":"publisher","first-page":"3667","DOI":"10.1109\/TBME.2022.3175670","type":"journal-article","article-title":"Multi-scale reconstruction of undersampled spectral-spatial oct data for coronary imaging using deep learning","volume":"69","author":"Li","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexae2623bib27","doi-asserted-by":"publisher","first-page":"136","DOI":"10.48550\/arXiv.1707.02921","type":"other","article-title":"Enhanced deep residual networks for single image super-resolution","author":"Lim","year":"2017"},{"key":"bpexae2623bib28","doi-asserted-by":"publisher","first-page":"26521","DOI":"10.1364\/OE.23.026521","type":"journal-article","article-title":"Spectral estimation optical coherence tomography for axial super-resolution","volume":"23","author":"Liu","year":"2015","journal-title":"Opt. Express"},{"key":"bpexae2623bib29","doi-asserted-by":"publisher","first-page":"10012","DOI":"10.48550\/arXiv.2103.14030","type":"other","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"bpexae2623bib30","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2021.613051","type":"journal-article","article-title":"Oct hyperreflective retinal foci in diabetic retinopathy: a semi-automatic detection comparative study","volume":"12","author":"Midena","year":"2021","journal-title":"Frontiers in Immunology"},{"key":"bpexae2623bib31","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1364\/OE.24.001781","type":"journal-article","article-title":"Iterative re-weighted approach to high-resolution optical coherence tomography with narrow-band sources","volume":"24","author":"Mousavi","year":"2016","journal-title":"Opt. Express"},{"key":"bpexae2623bib32","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102247","type":"journal-article","article-title":"A2oursr: adaptive adjustment based real mri super-resolution via opinion-unaware measurements","volume":"107","author":"Qin","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"bpexae2623bib33","doi-asserted-by":"publisher","first-page":"12116","DOI":"10.48550\/arXiv.2108.08810","type":"journal-article","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"bpexae2623bib34","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1117\/1.429925","type":"journal-article","article-title":"Speckle in optical coherence tomography","volume":"4","author":"Schmitt","year":"1999","journal-title":"J. Biomed. Opt."},{"key":"bpexae2623bib35","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.48550\/arXiv.1609.05158","type":"other","article-title":"Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network","author":"Shi","year":"2016"},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"bpexae2623bib36","type":"conference-proceedings"},{"key":"bpexae2623bib37","doi-asserted-by":"publisher","first-page":"13190","DOI":"10.48550\/arXiv.2302.13800","type":"other","article-title":"Spatially-adaptive feature modulation for efficient image super-resolution","author":"Sun","year":"2023"},{"key":"bpexae2623bib38","doi-asserted-by":"publisher","first-page":"235016","DOI":"10.1088\/1361-6560\/ad0997","type":"journal-article","article-title":"Axial super-resolution optical coherence tomography via complex-valued network","volume":"68","author":"Wang","year":"2023","journal-title":"Physics in Medicine & Biology"},{"key":"bpexae2623bib39","doi-asserted-by":"publisher","first-page":"63","DOI":"10.48550\/arXiv.1809.00219","type":"other","article-title":"Esrgan: enhanced super-resolution generative adversarial networks","author":"Wang"},{"key":"bpexae2623bib40","doi-asserted-by":"publisher","first-page":"3346","DOI":"10.1093\/eurheartj\/ehv367","type":"journal-article","article-title":"Optical coherence tomography imaging during percutaneous coronary intervention impacts physician decision-making: Ilumien i study","volume":"36","author":"Wijns","year":"2015","journal-title":"Eur. Heart J."},{"key":"bpexae2623bib41","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1117\/1.1482379","type":"journal-article","article-title":"In vivo human retinal imaging by fourier domain optical coherence tomography","volume":"7","author":"Wojtkowski","year":"2002","journal-title":"J. Biomed. Opt."},{"key":"bpexae2623bib42","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1109\/TMM.2021.3065731","type":"journal-article","article-title":"Fine-grained attention and feature-sharing generative adversarial networks for single image super-resolution","volume":"24","author":"Yan","year":"2021","journal-title":"IEEE Trans. Multimedia"},{"key":"bpexae2623bib43","doi-asserted-by":"publisher","first-page":"2958","DOI":"10.1364\/BOE.521453","type":"journal-article","article-title":"Pscat: a lightweight transformer for simultaneous denoising and super-resolution of oct images","volume":"15","author":"Yao","year":"2024","journal-title":"Biomedical Optics Express"},{"key":"bpexae2623bib44","doi-asserted-by":"publisher","first-page":"2690","DOI":"10.1364\/BOE.2.002690","type":"journal-article","article-title":"Real-time high-speed volumetric imaging using compressive sampling optical coherence tomography","volume":"2","author":"Young","year":"2011","journal-title":"Biomedical Optics Express"},{"key":"bpexae2623bib45","doi-asserted-by":"publisher","first-page":"204941","DOI":"10.1109\/ACCESS.2020.3036837","type":"journal-article","article-title":"Axial super-resolution study for optical coherence tomography images via deep learning","volume":"8","author":"Yuan","year":"2020","journal-title":"IEEE Access"},{"key":"bpexae2623bib46","doi-asserted-by":"publisher","first-page":"27566","DOI":"10.1364\/OE.495530","type":"journal-article","article-title":"Self super-resolution of optical coherence tomography images based on deep learning","volume":"31","author":"Yuan","year":"2023","journal-title":"Opt. Express"},{"key":"bpexae2623bib47","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.104231","type":"journal-article","article-title":"A generative adversarial network with multi-scale convolution and dilated convolution res-network for oct retinal image despeckling","volume":"80","author":"Yu","year":"2023","journal-title":"Biomed. Signal Process. Control"},{"key":"bpexae2623bib48","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1109\/CVPR.2018.00068","type":"other","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"key":"bpexae2623bib49","doi-asserted-by":"publisher","first-page":"3096","DOI":"10.1109\/ICCV.2019.00319","type":"other","article-title":"Ranksrgan: generative adversarial networks with ranker for image super-resolution","author":"Zhang","year":"2019"},{"key":"bpexae2623bib50","doi-asserted-by":"publisher","first-page":"286","DOI":"10.48550\/arXiv.1807.02758","type":"other","article-title":"Image super-resolution using very deep residual channel attention networks","author":"Zhang","year":"2018"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T15:28:49Z","timestamp":1765380529000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae2623"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":50,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12,10]]},"published-print":{"date-parts":[[2026,2,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae2623","relation":{},"ISSN":["2057-1976"],"issn-type":[{"type":"electronic","value":"2057-1976"}],"subject":[],"published":{"date-parts":[[2025,12,10]]},"assertion":[{"value":"MLGF-GAN: a multi-level local-global feature fusion GAN for OCT image super-resolution","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-09-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-01","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-10","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}