{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T23:16:25Z","timestamp":1791501385595,"version":"4.3.4"},"reference-count":50,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T00:00:00Z","timestamp":1729036800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC2411502"],"award-info":[{"award-number":["2023YFC2411502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62071197"],"award-info":[{"award-number":["62071197"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82202954"],"award-info":[{"award-number":["82202954"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20373"],"award-info":[{"award-number":["U20A20373"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20480"],"award-info":[{"award-number":["U21A20480"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Denoising low\u2010dose computed tomography (CT) images is a critical task in medical image computing. Supervised deep learning\u2010based approaches have made significant advancements in this area in recent years. However, these methods typically require pairs of low\u2010dose and normal\u2010dose CT images for training, which are challenging to obtain in clinical settings. Existing unsupervised deep learning\u2010based methods often require training with a large number of low\u2010dose CT images or rely on specially designed data acquisition processes to obtain training data.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To address these limitations, we propose a novel unsupervised method that only utilizes normal\u2010dose CT images during training, enabling zero\u2010shot denoising of low\u2010dose CT images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Our method leverages the diffusion model, a powerful generative model. We begin by training a cascaded unconditional diffusion model capable of generating high\u2010quality normal\u2010dose CT images from low\u2010resolution to high\u2010resolution. The cascaded architecture makes the training of high\u2010resolution diffusion models more feasible. Subsequently, we introduce low\u2010dose CT images into the reverse process of the diffusion model as likelihood, combined with the priors provided by the diffusion model and iteratively solve multiple maximum a posteriori (MAP) problems to achieve denoising. Additionally, we propose methods to adaptively adjust the coefficients that balance the likelihood and prior in MAP estimations, allowing for adaptation to different noise levels in low\u2010dose CT images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We test our method on low\u2010dose CT datasets of different regions with varying dose levels. The results demonstrate that our method outperforms the state\u2010of\u2010the\u2010art unsupervised method and surpasses several supervised deep learning\u2010based methods. Our method achieves PSNR of 45.02 and 35.35\u00a0dB on the abdomen CT dataset and the chest CT dataset, respectively, surpassing the best unsupervised algorithm Noise2Sim in the comparative methods by 0.39 and 0.85\u00a0dB, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>We propose a novel low\u2010dose CT image denoising method based on diffusion model. Our proposed method only requires normal\u2010dose CT images as training data, greatly alleviating the data scarcity issue faced by most deep learning\u2010based methods. At the same time, as an unsupervised algorithm, our method achieves very good qualitative and quantitative results. The Codes are available in <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/DeepXuan\/Dn-Dp\">https:\/\/github.com\/DeepXuan\/Dn\u2010Dp<\/jats:ext-link>.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.17431","type":"journal-article","created":{"date-parts":[[2024,10,16]],"date-time":"2024-10-16T16:44:47Z","timestamp":1729097087000},"page":"329-345","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["Diffusion probabilistic priors for zero\u2010shot low\u2010dose CT image denoising"],"prefix":"10.1002","volume":"52","author":[{"given":"Xuan","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoqin","family":"Xie","sequence":"additional","affiliation":[{"name":"Institute of Biomedical and Health Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenbin","family":"Liu","sequence":"additional","affiliation":[{"name":"Radiation Oncology Department National Cancer Center\/National Clinical Research Center for Cancer\/Cancer Hospital &amp; Shenzhen Hospital Chinese Academy of Medical Sciences and Peking Union Medical College Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Songhui","family":"Diao","sequence":"additional","affiliation":[{"name":"Institute of Biomedical and Health Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokun","family":"Liang","sequence":"additional","affiliation":[{"name":"Institute of Biomedical and Health Engineering Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,10,16]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2012.2187213"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3232004"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/53\/17\/021"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/60\/5\/1965"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2017.2715284"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4851635"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2713099"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0057-9"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13666"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2827462"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-018-0056-0"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-019-00274-4"},{"key":"e_1_2_8_14_1","doi-asserted-by":"crossref","unstructured":"ZhangZ YuL LiangX ZhaoW XingL.TransCT: dual\u2010path transformer for low dose computed tomography. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2021.","DOI":"10.1007\/978-3-030-87231-1_6"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acc000"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2022.3216887"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15886"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra072149"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1097\/RCT.0b013e318258e891"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNS.2015.2467219"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4789628"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2961837"},{"key":"e_1_2_8_23_1","unstructured":"McColloughC ChenB HolmesD et\u00a0al.Low dose CT image and projection data [data set].The Cancer Imaging Archive;2020."},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aba939"},{"key":"e_1_2_8_25_1","doi-asserted-by":"crossref","unstructured":"WuD GongK KimK LiX LiQ.Consensus neural network for medical imaging denoising with only noisy training samples. In:International Conference on Medical Image Computing and Computer\u2010Assisted Intervention.Springer;2019:741\u2010749.","DOI":"10.1007\/978-3-030-32251-9_81"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"DuW ChenH YangH.Learning invariant representation for unsupervised image restoration. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE;2020:14483\u201014492.","DOI":"10.1109\/CVPR42600.2020.01449"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3231428"},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2529698"},{"key":"e_1_2_8_29_1","unstructured":"NiuC WangG YanP et\u00a0al.Noise entangled GAN for low\u2010dose CT simulation. arXiv preprint arXiv:2102.09615.2021."},{"key":"e_1_2_8_30_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho J","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_8_31_1","unstructured":"SongJ MengC ErmonS.Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502.2020."},{"key":"e_1_2_8_32_1","unstructured":"KarrasT AilaT LaineS LehtinenJ.Progressive growing of gans for improved quality stability and variation. arXiv preprint arXiv:1710.10196.2017."},{"key":"e_1_2_8_33_1","doi-asserted-by":"crossref","unstructured":"KarrasT LaineS AilaT.A style\u2010based generator architecture for generative adversarial networks. In:Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.IEEE;2019:4401\u20104410.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_2_8_34_1","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho J","year":"2022","journal-title":"J Mach Learn Res"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278-013-9622-7"},{"key":"e_1_2_8_36_1","first-page":"4713","article-title":"Image super\u2010resolution via iterative refinement","volume":"45","author":"Saharia C","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"e_1_2_8_37_1","unstructured":"BrockA DonahueJ SimonyanK.Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096.2018."},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14820"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16983"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4722751"},{"key":"e_1_2_8_41_1","unstructured":"WagnerF ThiesM PfaffL et\u00a0al.On the benefit of dual\u2010domain denoising in a self\u2010supervised low\u2010dose CT setting. arXiv preprint arXiv:2211.01111.2022."},{"key":"e_1_2_8_42_1","unstructured":"RonchettiM.TorchRadon: fast differentiable routines for computed tomography. arXiv preprint arXiv:2009.14788.2020."},{"key":"e_1_2_8_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2007.901238"},{"key":"e_1_2_8_44_1","unstructured":"XiaW LyuQ WangG.Low\u2010dose CT using denoising diffusion probabilistic model for20\u00d7$20\\times$speedup. arXiv preprint arXiv:2209.15136.2022."},{"key":"e_1_2_8_45_1","unstructured":"SongY ShenL XingL ErmonS.Solving inverse problems in medical imaging with score\u2010based generative models. In:International Conference on Learning Representations.2022."},{"key":"e_1_2_8_46_1","unstructured":"MaderKS.The lung image database consortium image collection (LIDC\u2010IDRI).IEEE Dataport;2021. doi:10.21227\/zce3\u2010jp96"},{"key":"e_1_2_8_47_1","first-page":"26565","article-title":"Elucidating the design space of diffusion\u2010based generative models","volume":"35","author":"Karras T","year":"2022","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_8_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3355455"},{"key":"e_1_2_8_49_1","article-title":"Unsupervised CT metal artifact reduction by plugging diffusion priors in dual domains","author":"Liu X","year":"2024","journal-title":"IEEE Trans Med Imaging"},{"key":"e_1_2_8_50_1","doi-asserted-by":"crossref","unstructured":"ZoranD WeissY.From learning models of natural image patches to whole image restoration. In:2011 International Conference on Computer Vision.IEEE;2011:479\u2010486.","DOI":"10.1109\/ICCV.2011.6126278"},{"key":"e_1_2_8_51_1","first-page":"21757","article-title":"SNIPS: solving noisy inverse problems stochastically","volume":"34","author":"Kawar B","year":"2021","journal-title":"Adv Neural Inf Process Syst"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17431","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T23:23:27Z","timestamp":1755905007000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17431"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,16]]},"references-count":50,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1002\/mp.17431"],"URL":"https:\/\/doi.org\/10.1002\/mp.17431","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,16]]},"assertion":[{"value":"2024-06-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-03","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-10-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}