{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:24:17Z","timestamp":1783405457573,"version":"3.54.6"},"reference-count":50,"publisher":"IOP Publishing","issue":"13","license":[{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T00:00:00Z","timestamp":1783382400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea governmen","award":["RS-2021-II211343"],"award-info":[{"award-number":["RS-2021-II211343"]}]},{"name":"Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea","award":["RS 2025-02307233"],"award-info":[{"award-number":["RS 2025-02307233"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,7,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective<\/jats:italic>\n                    . Metal artifact reduction (MAR) in computed tomography (CT) remains a significant challenge due to inconsistencies in x-ray attenuation, which induce severe streak artifacts and obscure non-metal anatomical structures. A prevalent approach involves segmenting background and metal components within the sinogram domain. However, because the severity of artifacts varies according to the material, size, and location of the metal objects, an optimized thresholding strategy is essential to effectively distinguish background from metal regions.\n                    <jats:italic>Approach<\/jats:italic>\n                    . In this paper, we introduce LangGraph-MAR, a novel framework that integrates adaptive threshold optimization with automated image quality assessment. Our method utilizes a node-based LangGraph architecture, where specialized functions\u2014including reconstruction, sinogram inpainting, and L1-based metal soft-thresholding\u2013are assigned to discrete nodes interconnected via edges. A fundamental component of this system is the ground-checking node, a quality assessment classifier trained on both artifact-corrupted and artifact-free images. This classifier facilitates an automated, iterative MAR process that converges to the optimal threshold value to ensure high image quality.\n                    <jats:italic>Main results<\/jats:italic>\n                    . Comparative analysis with baseline models demonstrates that LangGraph-MAR outperforms several MAR methods in CT MAR tasks, yielding SSIM relative improvements of 8.64% and 5.61% for body and head protocols against InDuDoNet+, respectively. Additional representative cases and region of interest level analyses further support the efficacy of the proposed framework, showing substantial recovery of structural information in regions affected by artifacts.\n                    <jats:italic>Significance<\/jats:italic>\n                    . The proposed framework ensures consistent performance across diverse metal implants through adaptive thresholding. Furthermore, its modular plug-and-play design improves diagnostic reliability, facilitating more effective clinical decision-making. Code: https:\/\/github.com\/KimYeongHyeon\/LangGraphMAR\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ae7ec4","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T22:52:18Z","timestamp":1781736738000},"page":"135027","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive thresholding for CT metal artifact reduction via LangGraph"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6553-5478","authenticated-orcid":true,"given":"Yeonghyeon","family":"Kim","sequence":"first","affiliation":[{"name":"Seoul National University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9860-072X","authenticated-orcid":true,"given":"Kyungsang","family":"Kim","sequence":"additional","affiliation":[{"name":"Center for Advanced Medical Computing and Analysis (CAMCA), Radiology, Massachusetts General Hospital and Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3121-7099","authenticated-orcid":true,"given":"Dongheon","family":"Lee","sequence":"additional","affiliation":[{"name":"Seoul National University College of Medicine, Seoul National University Hospital"},{"name":"Institute of Medical and Biological Engineering, Seoul National University Medical Research Center"},{"name":"Seoul National University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,7]]},"reference":[{"key":"pmbae7ec4bib1","article-title":"AAPM CT metal artifact reduction (CT-MAR) grand challenge benchmark tool","author":"AAPM CT-MAR Grand Challenge","year":"2025","type":"other"},{"key":"pmbae7ec4bib2","article-title":"Simultaneous algebraic reconstruction technique (SART): a superior implementation of the art algorithm","author":"Andersen","year":"1984","type":"other"},{"key":"pmbae7ec4bib3","doi-asserted-by":"publisher","first-page":"229","DOI":"10.2217\/iim.12.13","type":"journal-article","article-title":"CT artifacts: causes and reduction techniques","volume":"4","author":"Boas","year":"2012","journal-title":"Imaging Med."},{"key":"pmbae7ec4bib4","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.5194\/gmd-7-1247-2014","type":"journal-article","article-title":"Root mean square error (RMSE) or mean absolute error (MAE)?\u2014arguments against avoiding RMSE in the literature","volume":"7","author":"Chai","year":"2014","journal-title":"Geosci. Model Dev."},{"key":"pmbae7ec4bib5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20071-7_2","type":"other","article-title":"Simple baselines for image restoration","author":"Chen","year":"2022"},{"key":"pmbae7ec4bib6","doi-asserted-by":"publisher","first-page":"457","DOI":"10.3233\/XST-2011-030700307","type":"journal-article","article-title":"Sparsity driven metal part reconstruction for artifact removal in dental CT","volume":"19","author":"Choi","year":"2011","journal-title":"J. X-ray Sci. Technol."},{"key":"pmbae7ec4bib7","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1109\/23.775600","type":"journal-article","article-title":"Metal streak artifacts in x-ray computed tomography: a simulation study","volume":"46","author":"De Man","year":"1999","journal-title":"IEEE Trans. Nucl. Sci."},{"key":"pmbae7ec4bib8","doi-asserted-by":"publisher","first-page":"R49","DOI":"10.1088\/1361-6560\/aa5293","type":"journal-article","article-title":"Metal artifacts in computed tomography for radiation therapy planning: Dosimetric effects and impact of metal artifact reduction","volume":"62","author":"Giantsoudi","year":"2017","journal-title":"Phys. Med. Biol."},{"key":"pmbae7ec4bib9","doi-asserted-by":"publisher","first-page":"5826","DOI":"10.1109\/ACCESS.2016.2608621","type":"journal-article","article-title":"Metal artifact reduction in CT: where are we after four decades?","volume":"4","author":"Gjesteby","year":"2016","journal-title":"IEEE Access"},{"key":"pmbae7ec4bib10","article-title":"UCLH stroke EIT dataset\u2013radiology data (CT)","author":"Goren","year":"2017","type":"other"},{"key":"pmbae7ec4bib11","doi-asserted-by":"publisher","DOI":"10.1002\/mp.70050","type":"journal-article","article-title":"AAPM CT metal artifact reduction grand challenge","volume":"52","author":"Haneda","year":"2025","journal-title":"Med. Phys."},{"key":"pmbae7ec4bib12","doi-asserted-by":"publisher","DOI":"10.1002\/mp.70050","type":"dataset","article-title":"AAPM CT-MAR grand challenge","author":"Haneda","year":"2025","unstructured":"Haneda E et al 2025 AAPM CT-MAR grand challenge AAPM Grand Challenge 10.1002\/mp.70050"},{"key":"pmbae7ec4bib13","article-title":"Deep residual learning for image recognition","author":"He","year":"2015","type":"preprint"},{"key":"pmbae7ec4bib14","first-page":"pp 2366","type":"conference-proceedings","article-title":"Image quality metrics: PSNR vs. SSIM","author":"Hore","year":"2010"},{"key":"pmbae7ec4bib15","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s12880-021-00554-y","type":"journal-article","article-title":"Comparison of different CT metal artifact reduction strategies for standard titanium and carbon-fiber reinforced polymer implants in sheep cadavers","volume":"21","author":"Huber","year":"2021","journal-title":"BMC Med. Imaging"},{"key":"pmbae7ec4bib16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.103147","type":"journal-article","article-title":"A comprehensive review of past and present image inpainting methods","volume":"203","author":"Jam","year":"2021","journal-title":"Comput. Vis. Image Underst."},{"key":"pmbae7ec4bib17","author":"Kak","year":"2001","type":"book"},{"key":"pmbae7ec4bib18","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s41747-025-00587-w","type":"journal-article","article-title":"Assessment of metal artifacts from titanium wrist prostheses: photon-counting versus energy-integrating detector CT","volume":"9","author":"K\u00e4mmerling","year":"2025","journal-title":"Eur. Radiol. Exp."},{"key":"pmbae7ec4bib19","article-title":"Metal artifact reduction using l1 and non-local penalties with iterative sinogram correction","author":"Kim","year":"2014","type":"other"},{"key":"pmbae7ec4bib20","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.phro.2022.11.007","type":"journal-article","article-title":"The impact of a metal artefact reduction algorithm on treatment planning for patients undergoing radiotherapy of the pelvis","volume":"24","author":"King","year":"2022","journal-title":"Phys. Imaging Rad. Oncol."},{"key":"pmbae7ec4bib21","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.221257","type":"journal-article","article-title":"Deep learning image reconstruction for CT: technical principles and clinical prospects","volume":"306","author":"Koetzier","year":"2023","journal-title":"Radiology"},{"key":"pmbae7ec4bib22","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17859","type":"journal-article","article-title":"X-ray CT metal artifact reduction using neural attenuation field prior","volume":"52","author":"Lee","year":"2025","journal-title":"Med. Phys."},{"key":"pmbae7ec4bib23","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1109\/TMI.2019.2933425","type":"journal-article","article-title":"ADN: artifact disentanglement network for unsupervised metal artifact reduction","volume":"39","author":"Liao","year":"2020","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae7ec4bib24","doi-asserted-by":"publisher","first-page":"3533","DOI":"10.1109\/TMI.2024.3351201","type":"journal-article","article-title":"Unsupervised CT metal artifact reduction by plugging diffusion priors in dual domains","volume":"43","author":"Liu","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae7ec4bib25","doi-asserted-by":"publisher","first-page":"4149","DOI":"10.1109\/TIP.2022.3181496","type":"journal-article","article-title":"Image quality assessment using contrastive learning","volume":"31","author":"Madhusudana","year":"2022","journal-title":"IEEE Trans. Image Process."},{"key":"pmbae7ec4bib26","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1109\/99.660313","type":"journal-article","article-title":"OpenMP: an industry-standard API for shared-memory programming","volume":"5","author":"Menon","year":"1998","journal-title":"Comput. Sci. Eng."},{"key":"pmbae7ec4bib27","doi-asserted-by":"publisher","first-page":"5482","DOI":"10.1118\/1.3484090","type":"journal-article","article-title":"Normalized metal artifact reduction (NMAR) in computed tomography","volume":"37","author":"Meyer","year":"2010","journal-title":"Med. Phys."},{"key":"pmbae7ec4bib28","doi-asserted-by":"publisher","first-page":"357","DOI":"10.3233\/XST-130384","type":"journal-article","article-title":"Metal artifact reduction in CT by identifying missing data hidden in metals","volume":"21","author":"Park","year":"2013","journal-title":"J. X-ray Sci. Technol."},{"key":"pmbae7ec4bib29","doi-asserted-by":"publisher","DOI":"10.1002\/mp.70020","type":"journal-article","article-title":"A hybrid training database and evaluation benchmark for assessing metal artifact reduction methods for x-ray CT imaging","volume":"52","author":"Peters","year":"2025","journal-title":"Med. Phys."},{"key":"pmbae7ec4bib30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-24574-4_28","type":"other","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"pmbae7ec4bib31","article-title":"iMAR: iterative metal artifact reduction algorithm","author":"Siemens Healthineers (n.d.)","type":"other"},{"key":"pmbae7ec4bib32","doi-asserted-by":"crossref","DOI":"10.1117\/12.2006810","type":"book","article-title":"Influence of metal segmentation on the quality of metal artifact reduction methods","author":"Stille","year":"2013"},{"key":"pmbae7ec4bib33","article-title":"EfficientNet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2020","type":"preprint"},{"key":"pmbae7ec4bib34","doi-asserted-by":"publisher","DOI":"10.1118\/1.4901553","type":"journal-article","article-title":"Moving metal artifact reduction in cone-beam CT scans with implanted cylindrical gold markers","volume":"41","author":"Toftegaard","year":"2014","journal-title":"Med. Phys."},{"key":"pmbae7ec4bib35","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1148\/rg.2019180022","type":"journal-article","article-title":"Recognizing and minimizing artifacts at CT, MRI, US and molecular imaging","volume":"39","author":"Triche","year":"2019","journal-title":"RadioGraphics"},{"key":"pmbae7ec4bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102729","type":"journal-article","article-title":"InDuDoNet+: a deep unfolding dual domain network for metal artifact reduction in CT images","volume":"85","author":"Wang","year":"2023","journal-title":"Med. Image Anal."},{"key":"pmbae7ec4bib37","doi-asserted-by":"publisher","first-page":"2408","DOI":"10.1109\/TMI.2025.3534316","type":"journal-article","article-title":"Adaptive weighting based metal artifact reduction in CT images","volume":"44","author":"Wang","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae7ec4bib38","doi-asserted-by":"publisher","first-page":"5369","DOI":"10.1109\/JBHI.2023.3312292","type":"journal-article","article-title":"SemiMAR: semi-supervised learning for CT metal artifact reduction","volume":"27","author":"Wang","year":"2023","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"pmbae7ec4bib39","article-title":"Uformer: a general U-shaped transformer for image restoration","author":"Wang","year":"2021","type":"preprint"},{"key":"pmbae7ec4bib40","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.ejrad.2018.08.010","type":"journal-article","article-title":"Metal artifact reduction techniques in musculoskeletal CT-imaging","volume":"107","author":"Wellenberg","year":"2018","journal-title":"Eur. J. Radiol."},{"key":"pmbae7ec4bib41","doi-asserted-by":"publisher","first-page":"79","DOI":"10.3354\/cr030079","type":"journal-article","article-title":"Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance","volume":"30","author":"Willmott","year":"2005","journal-title":"Clim. Res."},{"key":"pmbae7ec4bib42","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac9174","type":"journal-article","article-title":"XCIST\u2014an open access x-ray\/CT simulation toolkit","volume":"67","author":"Wu","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmbae7ec4bib43","doi-asserted-by":"publisher","first-page":"6424","DOI":"10.1002\/mp.15931","type":"journal-article","article-title":"Inpainting the metal artifact region in MRI images by using generative adversarial networks with gated convolution","volume":"49","author":"Xie","year":"2022","journal-title":"Med. Phys."},{"key":"pmbae7ec4bib44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1117\/1.JMI.5.3.036501","type":"journal-article","article-title":"DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning","volume":"5","author":"Yan","year":"2018","journal-title":"J. Med. Imaging"},{"key":"pmbae7ec4bib45","doi-asserted-by":"publisher","first-page":"138441","DOI":"10.1109\/ACCESS.2024.3461782","type":"journal-article","article-title":"Review of deep learning-based image inpainting techniques","volume":"12","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"pmbae7ec4bib46","article-title":"Unlocking the potential of early epochs: uncertainty-aware ct metal artifact reduction","author":"Yang","year":"2024","type":"preprint"},{"key":"pmbae7ec4bib47","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1109\/TMI.2020.3025064","type":"journal-article","article-title":"Deep sinogram completion with image prior for metal artifact reduction in CT images","volume":"40","author":"Yu","year":"2021","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbae7ec4bib48","first-page":"pp 5718","type":"conference-proceedings","article-title":"Restormer: efficient transformer for high-resolution image restoration","author":"Zamir","year":"2022"},{"key":"pmbae7ec4bib49","doi-asserted-by":"publisher","first-page":"3142","DOI":"10.1109\/TIP.2017.2662206","type":"journal-article","article-title":"Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising","volume":"26","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"pmbae7ec4bib50","doi-asserted-by":"publisher","first-page":"2378","DOI":"10.1109\/TIP.2011.2109730","type":"journal-article","article-title":"FSIM: a feature similarity index for image quality assessment","volume":"20","author":"Zhang","year":"2011","journal-title":"IEEE Trans. Image Process."}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T06:02:32Z","timestamp":1783404152000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7ec4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,7]]},"references-count":50,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7,7]]},"published-print":{"date-parts":[[2026,7,14]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae7ec4","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,7]]},"assertion":[{"value":"Adaptive thresholding for CT metal artifact reduction via LangGraph","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-02-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-07","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}