{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T23:32:12Z","timestamp":1775086332027,"version":"3.50.1"},"reference-count":56,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T00:00:00Z","timestamp":1712188800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T00:00:00Z","timestamp":1712188800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Provincial Natural Science Foundation of Shanxi","award":["20210302124190"],"award-info":[{"award-number":["20210302124190"]}]},{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["U23A20285"],"award-info":[{"award-number":["U23A20285"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"State Key Laboratory of Dynamic Measurement Technology, North University of China","award":["2022-SYSJJ-08"],"award-info":[{"award-number":["2022-SYSJJ-08"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Computed tomography (CT) has evolved into an indispensable tool for clinical diagnosis. Reducing radiation dose crucially minimizes adverse effects but may introduce noise and artifacts in reconstructed images, affecting diagnostic processes for physicians. Scholars have tackled deep learning training instability by exploring diffusion models. Given the scarcity of clinical data, we propose the unsupervised image domain score generation model (UISG) for low-dose CT reconstruction. During training, normal-dose CT images are utilized as network inputs to train a score-based generative model that captures the prior distribution of CT images. In the iterative reconstruction, the initial CT image is obtained using a filtered back-projection algorithm. Subsequently, diffusion-based prior, high-frequency convolutional sparse coding prior, and data-consistency steps are employed to obtain the high-quality reconstructed image. Given the global characteristics of noise, the score network of the diffusion model utilizes a swin transformer structure to enhance the model\u2019s ability to capture long-range dependencies. Furthermore, convolutional sparse coding is applied exclusively to the high-frequency components of the image, to prevent over-smoothing or the loss of crucial anatomical details during the denoising process. Quantitative and qualitative results indicate that UISG outperforms competing methods in terms of denoising and generalization performance.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad370e","type":"journal-article","created":{"date-parts":[[2024,3,22]],"date-time":"2024-03-22T22:40:51Z","timestamp":1711147251000},"page":"025005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Generation model meets swin transformer for unsupervised low-dose CT reconstruction"],"prefix":"10.1088","volume":"5","author":[{"given":"Yu","family":"Li","sequence":"first","affiliation":[]},{"given":"Xueqin","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Sukai","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yingwei","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Jinxiao","family":"Pan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0684-9665","authenticated-orcid":true,"given":"Ping","family":"Chen","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,4,4]]},"reference":[{"key":"mlstad370ebib1","doi-asserted-by":"publisher","first-page":"2277","DOI":"10.1056\/NEJMra072149","article-title":"Computed tomography\u2013an increasing source of radiation exposure","volume":"357","author":"Brenner","year":"2007","journal-title":"New Engl. J. Med."},{"key":"mlstad370ebib2","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1016\/S0140-6736(12)60815-0","article-title":"Radiation exposure from CT scans in childhood and subsequent risk of leukaemia and brain tumours: a retrospective cohort study","volume":"380","author":"Pearce","year":"2012","journal-title":"Lancet"},{"key":"mlstad370ebib3","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1109\/TMI.2017.2739841","article-title":"Discriminative feature representation to improve projection data inconsistency for low dose CT imaging","volume":"36","author":"Liu","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib4","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1109\/TMI.2006.882141","article-title":"Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose x-ray computed tomography","volume":"25","author":"Wang","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib5","doi-asserted-by":"publisher","DOI":"10.1118\/1.4851635","article-title":"Adaptive nonlocal means filtering based on local noise level for CT denoising","volume":"41","author":"Li","year":"2014","journal-title":"Med. Phys."},{"key":"mlstad370ebib6","doi-asserted-by":"publisher","first-page":"7923","DOI":"10.1088\/0031-9155\/57\/23\/7923","article-title":"Adaptive-weighted total variation minimization for sparse data toward low-dose x-ray computed tomography image reconstruction","volume":"57","author":"Liu","year":"2012","journal-title":"Phys. Med. Biol."},{"key":"mlstad370ebib7","doi-asserted-by":"publisher","first-page":"5401","DOI":"10.1088\/0031-9155\/55\/18\/009","article-title":"Block matching 3D random noise filtering for absorption optical projection tomography","volume":"55","author":"Fumene Feruglio","year":"2010","journal-title":"Phys. Med. Biol."},{"key":"mlstad370ebib8","doi-asserted-by":"publisher","first-page":"5803","DOI":"10.1088\/0031-9155\/58\/16\/5803","article-title":"Improving abdomen tumor low-dose CT images using a fast dictionary learning based processing","volume":"58","author":"Chen","year":"2013","journal-title":"Phys. Med. Biol."},{"key":"mlstad370ebib9","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10851-007-0042-5","article-title":"Nonlocal prior Bayesian tomographic reconstruction","volume":"30","author":"Chen","year":"2008","journal-title":"J. Math. Imaging Vis."},{"key":"mlstad370ebib10","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/j.compmedimag.2014.05.002","article-title":"Statistical image reconstruction for low-dose CT using nonlocal means-based regularization","volume":"38","author":"Zhang","year":"2014","journal-title":"Comput. Med. Imaging Graph."},{"key":"mlstad370ebib11","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1016\/j.ejmp.2012.01.003","article-title":"Iterative reconstruction methods in x-ray CT","volume":"28","author":"Beister","year":"2012","journal-title":"Phys. Med."},{"key":"mlstad370ebib12","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1186\/s12938-016-0193-y","article-title":"Low-dose CT reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares","volume":"15","author":"Zhang","year":"2016","journal-title":"Biomed. Eng."},{"key":"mlstad370ebib13","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"mlstad370ebib14","doi-asserted-by":"publisher","first-page":"2524","DOI":"10.1109\/TMI.2017.2715284","article-title":"Low-Dose CT with a residual encoder-decoder convolutional neural network","volume":"36","author":"Chen","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib15","doi-asserted-by":"publisher","first-page":"4509","DOI":"10.1109\/TIP.2017.2713099","article-title":"Deep convolutional neural network for inverse problems in imaging","volume":"26","author":"Jin","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"mlstad370ebib16","doi-asserted-by":"publisher","first-page":"1407","DOI":"10.1109\/TMI.2018.2823338","article-title":"A sparse-view CT reconstruction method based on combination of DenseNet and deconvolution","volume":"37","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib17","doi-asserted-by":"publisher","first-page":"2536","DOI":"10.1109\/TMI.2017.2708987","article-title":"Generative adversarial networks for noise reduction in low-dose CT","volume":"36","author":"Wolterink","year":"2017","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib18","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.1117\/12.2667487","article-title":"AIACT-GAN: CT reconstruction based on dynamic attention and generative adversarial networks","volume":"vol 12566","author":"Wang","year":"2023"},{"key":"mlstad370ebib19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3128703","article-title":"DU-GAN: generative adversarial networks with dual-domain U-net based discriminators for low-dose CT denoising","volume":"71","author":"Huang","year":"2022","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"mlstad370ebib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.displa.2023.102405","article-title":"SDGAN: a novel spatial deformable generative adversarial network for low-dose CT image reconstruction","volume":"78","author":"Liu","year":"2023","journal-title":"Displays"},{"key":"mlstad370ebib21","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1109\/TMI.2018.2827462","article-title":"Low-Dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss","volume":"37","author":"Yang","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib22","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1007\/978-3-030-87231-1_6","article-title":"TransCT: dual-path transformer for low dose computed tomography","volume":"vol 12906","author":"Zhang","year":"2021"},{"key":"mlstad370ebib23","doi-asserted-by":"publisher","first-page":"416","DOI":"10.1007\/978-3-030-87589-3_43","article-title":"TED-net: convolution-free T2T vision transformer-based encoder-decoder dilation network for low-dose CT denoising","volume":"12966","author":"Wang","year":"2021","journal-title":"Machine Learning in Medical Imaging"},{"key":"mlstad370ebib24","doi-asserted-by":"publisher","first-page":"910","DOI":"10.1109\/TMI.2022.3219856","article-title":"Low-dose CT denoising via sinogram inner-structure transformer","volume":"42","author":"Yang","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib25","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acc2ab","article-title":"MDST: multi-domain sparse-view CT reconstruction based on convolution and swin transformer","volume":"68","author":"Li","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"mlstad370ebib26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107161","article-title":"CAIR: combining integrated attention with iterative optimization learning for sparse-view CT reconstruction","volume":"163","author":"Cheng","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"mlstad370ebib27","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1038\/s42256-019-0057-9","article-title":"Competitive performance of a modularized deep neural network compared to commercial algorithms for low-dose CT image reconstruction","volume":"1","author":"Shan","year":"2019","journal-title":"Nat. Mach. Intell."},{"key":"mlstad370ebib28","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1109\/TMI.2018.2805692","article-title":"LEARN: learned experts\u2019 assessment-based reconstruction network for sparse-data CT","volume":"37","author":"Chen","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib29","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1109\/TRPMS.2022.3222213","article-title":"LEARN++: recurrent dual-domain reconstruction network for compressed sensing CT","volume":"7","author":"Zhang","year":"2022","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"mlstad370ebib30","doi-asserted-by":"publisher","first-page":"6840","DOI":"10.48550\/arXiv.2006.11239","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Neural Inf. Process. Syst."},{"key":"mlstad370ebib31","doi-asserted-by":"publisher","first-page":"8162","DOI":"10.48550\/arXiv.2102.09672","article-title":"Improved denoising diffusion probabilistic models","volume":"vol 139","author":"Nichol","year":"2021"},{"key":"mlstad370ebib32","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021"},{"key":"mlstad370ebib33","doi-asserted-by":"publisher","first-page":"41259","DOI":"10.48550\/arXiv.2208.09392","article-title":"Cold diffusion: inverting arbitrary image transforms without noise","volume":"36","author":"Bansal","year":"2024","journal-title":"Adv. Neural. Inf. Process. Syst"},{"key":"mlstad370ebib34","doi-asserted-by":"publisher","first-page":"12438","DOI":"10.48550\/arXiv.2006.09011","article-title":"Improved techniques for training score-based generative models","volume":"33","author":"Song","year":"2020","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"mlstad370ebib35","article-title":"Diffusion models for medical image analysis: a comprehensive survey","author":"Kazerouni","year":"2022"},{"key":"mlstad370ebib36","article-title":"One sample diffusion model in projection domain for low-dose CT imaging","author":"Huang","year":"2022"},{"key":"mlstad370ebib37","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/CyberC55534.2022.00041","article-title":"Ultra-low Dose CT image denoising based on conditional denoising diffusion probabilistic model","author":"Li","year":"2022"},{"key":"mlstad370ebib38","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1109\/TRPMS.2022.3148373","article-title":"Iterative reconstruction for low-dose CT using deep gradient priors of generative model","volume":"6","author":"He","year":"2022","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"mlstad370ebib39","doi-asserted-by":"crossref","DOI":"10.1145\/3178876.3186150","article-title":"Variational autoencoders for collaborative filtering","author":"Liang","year":"2018"},{"key":"mlstad370ebib40","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1109\/42.993128","article-title":"Statistical image reconstruction for polyenergetic x-ray computed tomography","volume":"21","author":"Elbakri","year":"2002","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib41","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","article-title":"Compressed sensing","volume":"52","author":"Donoho","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"mlstad370ebib42","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1109\/TMI.2005.862206","article-title":"Wavelet-based reconstruction for limited-angle x-ray tomography","volume":"25","author":"Rantala","year":"2006","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib43","doi-asserted-by":"publisher","first-page":"2607","DOI":"10.1109\/TMI.2019.2906853","article-title":"Convolutional sparse coding for compressed sensing CT reconstruction","volume":"38","author":"Bao","year":"2019","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib44","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021"},{"key":"mlstad370ebib45","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.942511","article-title":"Swin transformer-based GAN for multi-modal medical image translation","volume":"12","author":"Yan","year":"2022","journal-title":"Front. Oncol."},{"key":"mlstad370ebib46","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1007\/978-3-030-87231-1_27","article-title":"3D transformer-GAN for high-quality PET reconstruction","volume":"vol 12906","author":"Luo","year":"2021"},{"key":"mlstad370ebib47","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ac9da7","article-title":"Texture transformer super-resolution for low-dose computed tomography","volume":"8","author":"Zhou","year":"2022","journal-title":"Biomed. Phys. Eng. Express"},{"key":"mlstad370ebib48","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1109\/TIP.2015.2495260","article-title":"Efficient algorithms for convolutional sparse representations","volume":"25","author":"Wohlberg","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"mlstad370ebib49","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"Boyd","year":"2011"},{"key":"mlstad370ebib50","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/TMI.2021.3088344","article-title":"MAGIC: manifold and graph integrative convolutional network for low-dose CT reconstruction","volume":"40","author":"Xia","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib51","author":"NIH-AAPM-Mayo Clinic Low Dose CT Grand Challenge","year":"2016"},{"key":"mlstad370ebib52","doi-asserted-by":"publisher","first-page":"giab039","DOI":"10.1093\/gigascience\/giab039","article-title":"A large-scale metagenomic survey dataset of the post-weaning piglet gut lumen","volume":"10","author":"Gaio","year":"2021","journal-title":"Gigascience"},{"key":"mlstad370ebib53","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstad370ebib54","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1002\/mp.13769","article-title":"Enhancement pattern mapping technique for improving contrast-to-noise ratios and detectability of hepatobiliary tumors on multiphase computed tomography","volume":"47","author":"Park","year":"2020","journal-title":"Med. Phys."},{"key":"mlstad370ebib55","doi-asserted-by":"publisher","first-page":"2295","DOI":"10.1109\/TMI.2021.3076810","article-title":"Assessing the impact of deep neural network-based image denoising on binary signal detection tasks","volume":"40","author":"Li","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstad370ebib56","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1038\/s41597-019-0235-y","article-title":"A cone-beam x-ray computed tomography data collection designed for machine learning","volume":"6","author":"Sarkissian","year":"2019","journal-title":"Sci. Data"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,4]],"date-time":"2024-04-04T09:18:11Z","timestamp":1712222291000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad370e"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,4]]},"references-count":56,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,4,4]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad370e","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,4]]},"assertion":[{"value":"Generation model meets swin transformer for unsupervised low-dose CT reconstruction","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-12-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-03-22","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-04-04","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}