{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:01:16Z","timestamp":1792785676096,"version":"4.5.0"},"reference-count":27,"publisher":"IOP Publishing","issue":"19","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"KWF Kankerbestrijding","id":[{"id":"https:\/\/ror.org\/0368jnd28","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Ministerie van Volksgezondheid, Welzijn en Sport"},{"name":"Elekta Instruments"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,10,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    4D cone-beam computed tomography (4DCBCT) is a technique used to address respiratory motion in radiotherapy but is limited by significant view-aliasing artifacts. Recently, deep learning methods have been proposed to reduce view-aliasing. This study investigates the robustness and performance of these methods when variations in patient breathing period affect the noise pattern in the scans used as training data, which potentially affects the ability of the models to reduce view-aliasing.\n                    <jats:italic>Approach.<\/jats:italic>\n                    We evaluated both a supervised and a self-supervised scalable deep learning method. Using a dataset of 328 patients, scans were partitioned into cohorts according to breathing period, and independent training with cross-cohort validation was performed to assess robustness. We also evaluated the impact of a modern UNet-based architecture and data augmentation.\n                    <jats:italic>Main results.<\/jats:italic>\n                    Training and testing on matched breathing-period cohorts did not consistently improve performance, indicating that both methods are robust to clinically observed variation in average breathing period. Instead, increasing the overall dataset size led to the most noticeable improvements. For the cohort with long breathing periods, the supervised model trained on the combined dataset achieved a\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mrow>\n                            <mml:mo>\u2248<\/mml:mo>\n                          <\/mml:mrow>\n                          <mml:mn>0.5<\/mml:mn>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    PSNR improvement over the cohort-specific model and a PSG improvement of\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mrow>\n                          <mml:mrow>\n                            <mml:mo>\u2248<\/mml:mo>\n                          <\/mml:mrow>\n                          <mml:mn>0.7<\/mml:mn>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    .\n                    <jats:italic>Significance.<\/jats:italic>\n                    These findings support the reliability of deep learning-based 4DCBCT denoising across the observed range of average breathing periods. They suggest that large, diverse datasets should be prioritized over breathing-cohort-specific optimization. Finally, PSG provides a quantitative indicator that is sensitive to view-aliasing and may support future development of more robust 4DCBCT enhancement techniques.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/aea8c6","type":"journal-article","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T22:56:14Z","timestamp":1789599374000},"page":"195001","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Robustness of deep learning-based denoising 4DCBCT methods"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3221-0788","authenticated-orcid":true,"given":"Samuele","family":"Papa","sequence":"first","affiliation":[{"name":"The Netherlands Cancer Institute"},{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8947-1332","authenticated-orcid":false,"given":"Efstratios","family":"Gavves","sequence":"additional","affiliation":[{"name":"University of Amsterdam"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5155-5274","authenticated-orcid":true,"given":"Jan-Jakob","family":"Sonke","sequence":"additional","affiliation":[{"name":"The Netherlands Cancer Institute"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"pmbaea8c6bib1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4820537","type":"journal-article","article-title":"Artifact-resistant motion estimation with a patient-specific artifact model for motion-compensated cone-beam CT","volume":"40","author":"Brehm","year":"2013","journal-title":"Med. Phys."},{"key":"pmbaea8c6bib2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2025.108637","type":"journal-article","article-title":"MBST-Driven 4D-CBCT reconstruction: leveraging swin transformer and masking for robust performance","volume":"262","author":"Cao","year":"2025","journal-title":"Comput. Methods Programs Biomed."},{"key":"pmbaea8c6bib3","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s13014-024-02411-y","type":"journal-article","article-title":"A 4D-CBCT correction network based on contrastive learning for dose calculation in lung cancer","volume":"19","author":"Cao","year":"2024","journal-title":"Radiat. Oncol."},{"key":"pmbaea8c6bib4","doi-asserted-by":"publisher","first-page":"1094","DOI":"10.1109\/TRPMS.2024.3490715","type":"journal-article","article-title":"RSTAR4D: rotational streak artifact reduction in 4D CBCT using separable 4D convolutions","volume":"9","author":"Deng","year":"2025","journal-title":"IEEE Trans. Radiat. Plasma Med. Sci."},{"key":"pmbaea8c6bib5","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1016\/j.ijrobp.2007.07.2352","type":"journal-article","article-title":"Image-guided radiotherapy via daily online cone-beam CT substantially reduces margin requirements for stereotactic lung radiotherapy","volume":"70","author":"Grills","year":"2008","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"pmbaea8c6bib6","volume":"vol 2","author":"Hastie","year":"2009","type":"book"},{"key":"pmbaea8c6bib7","first-page":"pp 6840","type":"conference-proceedings","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"pmbaea8c6bib8","doi-asserted-by":"publisher","first-page":"1311","DOI":"10.1118\/1.599009","type":"journal-article","article-title":"Cone-beam computed tomography with a flat-panel imager: initial performance characterization","volume":"27","author":"Jaffray","year":"2000","journal-title":"Med. Phys."},{"key":"pmbaea8c6bib9","author":"Kak","year":"2001","type":"book"},{"key":"pmbaea8c6bib10","doi-asserted-by":"publisher","first-page":"3874","DOI":"10.1118\/1.2349696","type":"journal-article","article-title":"The management of respiratory motion in radiation oncology report of AAPM task group 76","volume":"33","author":"Keall","year":"2006","journal-title":"Med. Phys."},{"key":"pmbaea8c6bib11","first-page":"pp 1","type":"conference-proceedings","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2015"},{"key":"pmbaea8c6bib12","doi-asserted-by":"publisher","first-page":"4649","DOI":"10.1118\/1.2977736","type":"journal-article","article-title":"Streaking artifacts reduction in four-dimensional cone-beam computed tomography","volume":"35","author":"Leng","year":"2008","journal-title":"Med. Phys."},{"key":"pmbaea8c6bib13","doi-asserted-by":"publisher","first-page":"5619","DOI":"10.1002\/mp.14441","type":"journal-article","article-title":"Self-contained deep learning-based boosting of 4D cone-beam CT reconstruction","volume":"47","author":"Madesta","year":"2020","journal-title":"Med. Phys."},{"key":"pmbaea8c6bib14","doi-asserted-by":"publisher","first-page":"271.E1","DOI":"10.1016\/j.radonc.2005.03.026","type":"journal-article","article-title":"Cone-beam-CT guided radiation therapy: a model for on-line application","volume":"75","author":"Oldham","year":"2005","journal-title":"Radiother. Oncol."},{"key":"pmbaea8c6bib15","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-43999-5_46","type":"other","article-title":"Noise2Aliasing: unsupervised deep learning for view aliasing and noise reduction in 4DCBCT","author":"Papa","year":"2023"},{"key":"pmbaea8c6bib16","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1073\/pnas.1715832114","type":"journal-article","article-title":"A mixed-scale dense convolutional neural network for image analysis","volume":"115","author":"Pelt","year":"2018","journal-title":"Proc. Natl Acad. Sci."},{"key":"pmbaea8c6bib17","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1016\/j.radonc.2011.08.018","type":"journal-article","article-title":"Comparative study of respiratory motion correction techniques in cone-beam computed tomography","volume":"100","author":"Rit","year":"2011","journal-title":"Radiother. Oncol."},{"key":"pmbaea8c6bib18","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/489\/1\/012079","type":"journal-article","article-title":"The reconstruction toolkit (RTK), an open-source cone-beam ct reconstruction toolkit based on the insight toolkit (ITK)","volume":"489","author":"Rit","year":"2014","journal-title":"J. Phys.: Conf. Ser."},{"key":"pmbaea8c6bib19","doi-asserted-by":"publisher","first-page":"2283","DOI":"10.1118\/1.3115691","type":"journal-article","article-title":"On-the-fly motion-compensated cone-beam CT using an a priori model of the respiratory motion","volume":"36","author":"Rit","year":"2009","journal-title":"Med. Phys."},{"key":"pmbaea8c6bib20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13014-016-0677-8","type":"journal-article","article-title":"Evaluation of gantry speed on image quality and imaging dose for 4D cone-beam CT acquisition","volume":"11","author":"Santoso","year":"2016","journal-title":"Radiat. Oncol."},{"key":"pmbaea8c6bib21","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.ejmp.2017.11.020","type":"journal-article","article-title":"Image quality of four-dimensional cone-beam computed tomography obtained at various gantry rotation speeds for liver stereotactic body radiation therapy with fiducial markers","volume":"45","author":"Shimohigashi","year":"2018","journal-title":"Phys. Medica"},{"key":"pmbaea8c6bib22","doi-asserted-by":"publisher","first-page":"1176","DOI":"10.1118\/1.1869074","type":"journal-article","article-title":"Respiratory correlated cone beam CT","volume":"32","author":"Sonke","year":"2005","journal-title":"Med. Phys."},{"key":"pmbaea8c6bib23","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1120\/jacmp.v17i6.6459","type":"journal-article","article-title":"Difference in performance between 3D and 4D CBCT for lung imaging: a dose and image quality analysis","volume":"17","author":"Thengumpallil","year":"2016","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbaea8c6bib24","doi-asserted-by":"publisher","DOI":"10.1016\/j.tmater.2026.100082","type":"journal-article","article-title":"Characterization of medical devices and pharmaceutical formulations with 3D x-ray imaging and deep learning","volume":"10","author":"Villarraga-G\u00f3mez","year":"2026","journal-title":"Tomogr. Mater. Struct."},{"key":"pmbaea8c6bib25","doi-asserted-by":"publisher","first-page":"1177","DOI":"10.3109\/0284186X.2010.498435","type":"journal-article","article-title":"Inter- and intrafractional localisation errors in cone-beam CT guided stereotactic radiation therapy of tumours in the liver and lung","volume":"49","author":"Worm","year":"2010","journal-title":"Acta Oncol."},{"key":"pmbaea8c6bib26","doi-asserted-by":"publisher","first-page":"1495","DOI":"10.1109\/TMI.2022.3231461","type":"journal-article","article-title":"Four-dimensional cone beam CT imaging using a single routine scan via deep learning","volume":"42","author":"Yang","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbaea8c6bib27","doi-asserted-by":"publisher","first-page":"3054","DOI":"10.1109\/TMI.2021.3081824","type":"journal-article","article-title":"CycN-Net: a convolutional neural network specialized for 4D CBCT images refinement","volume":"40","author":"Zhi","year":"2021","journal-title":"IEEE Trans. Med. Imaging"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T05:02:32Z","timestamp":1790571752000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea8c6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":27,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,9,28]]},"published-print":{"date-parts":[[2026,10,14]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/aea8c6","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"Robustness of deep learning-based denoising 4DCBCT methods","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 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2026-05-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-16","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-28","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}