{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T08:42:04Z","timestamp":1775983324604,"version":"3.50.1"},"reference-count":45,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T00:00:00Z","timestamp":1761523200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>\n                      It is easy to find computed tomography (CT) images that include metals such as implants, bone plates, and bone shafts. These metals replacing body parts, cause serious artifacts in the CT image originated by x\u2010ray beam\u2010hardening. Traditionally, CT physics\u2010based image processing techniques were empirically applied to reduce metal artifacts (MAs). Recently, with the great success of deep learning, many studies on metal artifact reduction (MAR) using convolutional neural networks (CNNs) have been introduced.\n                      <jats:bold>Purpose<\/jats:bold>\n                      Most of them commonly meet a challenge to obtain ground truth images for MAR in clinical practice. Thus, for effective MAR without ground truth images, we propose a residual MA model for unsupervised deep learning scheme in CT\u00a0images.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In the 1st stage, MAs are extracted by CT physics\u2010inspired residual model, which is enabled by the residual learning scheme. The result of the 1st stage is fed into the input for the 2nd stage, where artifacts that are not reduced enough in the 1st stage are further removed by the contrastive learning scheme. Then, the networks in the 2nd stage can easily recognize the original structures due to primary artifact reduction in the 1st stage and can properly refine the\u00a0image.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our model was validated on three datasets. The results show that the proposed model outperforms other MAR models, preserving both original body and metal structures while reducing MAs effectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>We hope that this unsupervised learning model can contribute to good achievements in the MAR field while overcoming the limitations of data\u00a0construction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.70078","type":"journal-article","created":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T13:29:34Z","timestamp":1761658174000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Residual Metal Artifact Reduction in CT Images: An Unsupervised Residual and Contrastive Learning Approach for Preserving Metal Structures"],"prefix":"10.1002","volume":"52","author":[{"given":"YongSoo","family":"Kim","sequence":"first","affiliation":[{"name":"Division of Bio\u2010Medical Science &amp; Technology, KIST School Korea National University of Science and Technology Seoul South Korea"},{"name":"Bionics Research Center, Biomedical Research Division Korea Institute of Science and Technology Seoul South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jung\u2010Woo","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Oral and Maxillofacial Surgery, School of Dentistry Kyung Hee University Seoul South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byung Chul","family":"Lee","sequence":"additional","affiliation":[{"name":"Division of Bio\u2010Medical Science &amp; Technology, KIST School Korea National University of Science and Technology Seoul South Korea"},{"name":"Bionics Research Center, Biomedical Research Division Korea Institute of Science and Technology Seoul South Korea"},{"name":"KHU\u2010KIST Department of Converging Science and Technology, Graduate School Kyung Hee University Seoul South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunseok","family":"Seo","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence Korea University Seoul South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/23.775600"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3416398"},{"key":"e_1_2_9_4_1","doi-asserted-by":"crossref","unstructured":"KalenderWA HebelR Ebersberger J. Reduction of CT artifacts caused by metallic implants..Radiology. 1987;164:576\u2010577. PMID: 3602406","DOI":"10.1148\/radiology.164.2.3602406"},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","unstructured":"MeyerE BergnerF RaupachR FlohrT Kachelrie\u00df M. Normalized metal artifact reduction (NMAR) in computed tomography. In:2009 IEEE Nuclear Science Symposium Conference Record (NSS\/MIC). IEEE; 2009:3251\u20103255.","DOI":"10.1109\/NSSMIC.2009.5401721"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3691902"},{"key":"e_1_2_9_7_1","doi-asserted-by":"crossref","unstructured":"Zhang Y. Mou X. Metal artifact reduction based on beam hardening correction and statistical iterative reconstruction for X\u2010ray computed tomography. In:NishikawaRM WhitingBR Hoeschen C. eds. Proc. SPIE 8668 Medical Imaging 2013: Physics of Medical Imaging. vol. 8668. SPIE; 2013.","DOI":"10.1117\/12.2008176"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4794474"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13199"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13534-019-00110-2"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2930302"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2025.102549"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3002090"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"ZhaoB LiJ RenQ Zhong Y. Unsupervised reused convolutional network for metal artifact reduction In:Neural Information Processing. ICONIP 2020. Communications in Computer and Information Science. Springer; 2020:589\u2010596.","DOI":"10.1007\/978-3-030-63820-7_67"},{"key":"e_1_2_9_15_1","volume-title":"Developments in X\u2010Ray Tomography XI","author":"Gjesteby L","year":"2017"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2823083"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/57\/9\/2803"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2933425"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3101363"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI45749.2020.9098633"},{"key":"e_1_2_9_21_1","doi-asserted-by":"crossref","unstructured":"LeeHY TsengHY HuangJB SinghM YangMH.Diverse image\u2010to\u2010image translation via disentangled representations. In:Proceedings of the European Conference on Computer Vision (ECCV).Springer;2018.","DOI":"10.1007\/978-3-030-01246-5_3"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"HuangX LiuMY BelongieS KautzJ.Multimodal unsupervised image\u2010to\u2010image translation. In:Computer Vision \u2010 ECCV 2018: 15th European Conference Munich Germany September 8\u201014 2018 Proceedings Part III.Springer\u2010Verlag;2018:179\u2010196.","DOI":"10.1007\/978-3-030-01219-9_11"},{"key":"e_1_2_9_23_1","doi-asserted-by":"crossref","unstructured":"ZhuJY ParkT IsolaP EfrosAA.Unpaired image\u2010to\u2010image translation using cycle\u2010consistent adversarial networks. In:2017 IEEE International Conference on Computer Vision (ICCV).IEEE;2017:2242\u20102251.","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"LinWA LiaoH PengC et\u00a0al.DuDoNet: dual domain network for CT metal artifact reduction. In:2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2019:10504\u201010513.","DOI":"10.1109\/CVPR.2019.01076"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2024.3351201"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3031549"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1117\/12.2521440"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.3390\/app12010404"},{"key":"e_1_2_9_29_1","volume-title":"Foundations of Medical Imaging","author":"Zeman HD","year":"1993"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.1983.4307626"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2014.0388"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2019.2948320"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2021.104806"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers16030570"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"ParkT EfrosAA ZhangR ZhuJ.Contrastive Learning for Unpaired Image\u2010to\u2010Image Translation.in Computer Vision \u2013 ECCV 2020.2020:319\u2010345.","DOI":"10.1007\/978-3-030-58545-7_19"},{"key":"e_1_2_9_36_1","first-page":"262","article-title":"Vertebrae Localization in Pathological Spine CT via Dense Classification from Sparse Annotations","volume":"16","author":"Glocker B","year":"2013","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.5.3.036501"},{"key":"e_1_2_9_38_1","unstructured":"PaszkeA GrossS ChintalaS et\u00a0al.Automatic differentiation in PyTorch. In:NIPS 2017 Workshop on Autodiff.2017."},{"key":"e_1_2_9_39_1","unstructured":"KingmaD BaJ.Adam: a Method for Stochastic Optimization.International Conference on Learning Representations (ICLR).2015."},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102729"},{"key":"e_1_2_9_41_1","doi-asserted-by":"crossref","unstructured":"ZhangR IsolaP EfrosAA ShechtmanE WangO.The unreasonable effectiveness of deep features as a perceptual metric. In:2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).IEEE;2018:586\u2010595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"Hor\u00e9A ZiouD.Image quality metrics: PSNR vs. SSIM. In:2010 20th International Conference on Pattern Recognition.IEEE;2010:2366\u20102369.","DOI":"10.1109\/ICPR.2010.579"},{"key":"e_1_2_9_43_1","first-page":"120","article-title":"Fast normalized cross\u2010correlation","volume":"10","author":"Lewis JP","year":"1995","journal-title":"Vis Interface"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2023.111276"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijfatigue.2009.09.009"},{"key":"e_1_2_9_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/0043-1648(94)90272-0"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70078","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.70078","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.70078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T07:45:53Z","timestamp":1775979953000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.70078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":45,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1002\/mp.70078"],"URL":"https:\/\/doi.org\/10.1002\/mp.70078","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-06-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-05","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70078"}}