{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:01:14Z","timestamp":1792785674024,"version":"4.5.0"},"reference-count":35,"publisher":"IOP Publishing","issue":"17","license":[{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T00:00:00Z","timestamp":1788825600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Foundation for Research, Technology and Development"},{"name":"Christian Doppler Research Association","id":[{"id":"https:\/\/ror.org\/00mv8h305","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Austrian Federal Ministry of Economy, Energy and Tourism"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    Supervised synthetic computed tomography (sCT) generation from cone-beam computed tomography (CBCT) requires spatially registered training pairs, yet perfect registration between separately acquired scans is unattainable. This registration bias propagates into trained models and corrupts intensity-based evaluation, so higher benchmark scores may reward reproduction of registration artifacts over anatomical fidelity. We propose physics-based CBCT simulation for geometrically aligned training pairs by construction, with bias-robust geometric metrics.\n                    <jats:italic>Approach.<\/jats:italic>\n                    A framework simulated pelvic CBCT from fan-beam CT, modeling respiratory motion, x-ray scatter, and noise to yield aligned simulated-CBCT\/CT pairs. On a clinical gynecological dataset (deformable registration) and the SynthRAD 2023 pelvic dataset (rigid registration), sCT models trained on simulated data were compared against models trained on real pairs, a finetuned variant, and CycleGAN and RegGAN baselines. Evaluation combined intensity metrics (Mean absolute error, peak signal-to-noise ratio, structural similarity index measure) with geometric alignment metrics (normalized mutual information, NMI; correlation coefficient, CC) against input CBCT. Downstream segmentation of bladder, rectum and bowel bag was assessed in two modes: an sCT cascade applying a CT-trained model to sCT outputs, and direct segmentation by a model trained on simulated CBCT, plus a physics ablation and five-observer quality assessment.\n                    <jats:italic>Main results.<\/jats:italic>\n                    Simulation-trained models achieved higher geometric alignment than real-trained models (cross-dataset NMI 0.31 vs 0.22) despite lower intensity scores. Intensity metrics correlated inversely with observer ratings under deformable registration, whereas NMI consistently predicted clinical preference (clinical\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:mi>\u03c1<\/mml:mi>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    = 0.29, SynthRAD\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:mi>\u03c1<\/mml:mi>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    = 0.31). Observers preferred simulation-trained outputs in 87% of cases. In the sCT cascade, simulation-trained models improved segmentation (DSC 0.91\/0.86\/0.54 vs 0.84\/0.77\/0.04), while direct simulation-trained CBCT segmentation reached 0.92\/0.87\/0.83, exceeding a phantom-based baseline on the bowel bag.\n                    <jats:italic>Significance.<\/jats:italic>\n                    Physics-based simulation eliminates registration bias at its source, and downstream segmentation provides a task-based measure of sCT conversion quality that intensity metrics miss. Geometric fidelity, not intensity agreement with biased ground truth, aligns with the spatial-accuracy requirements of adaptive radiotherapy.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/aea04b","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T22:54:13Z","timestamp":1787957653000},"page":"175028","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Eliminating registration bias in synthetic CT generation using a physics-based simulation framework for pelvic anatomy"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0099-2276","authenticated-orcid":true,"given":"Lukas","family":"Zimmermann","sequence":"first","affiliation":[{"name":"Medical University of Vienna"},{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6640-3876","authenticated-orcid":true,"given":"Michael","family":"Rauter","sequence":"additional","affiliation":[{"name":"Competence Center for Preclinical Imaging & Biomedical Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9946-1939","authenticated-orcid":true,"given":"Martin","family":"Buschmann","sequence":"additional","affiliation":[{"name":"Medical University of Vienna"},{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tatevik","family":"Mrva-Ghukasyan","sequence":"additional","affiliation":[{"name":"Medical University of Vienna"},{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Iustin","family":"Pirsan","sequence":"additional","affiliation":[{"name":"Medical University of Vienna"},{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maximilian","family":"Schmid","sequence":"additional","affiliation":[{"name":"Medical University of Vienna"},{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dietmar","family":"Georg","sequence":"additional","affiliation":[{"name":"Medical University of Vienna"},{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4031-1711","authenticated-orcid":true,"given":"Barbara","family":"Kn\u00e4usl","sequence":"additional","affiliation":[{"name":"Medical University of Vienna"},{"name":"Medical University of Vienna"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,9,8]]},"reference":[{"key":"pmbaea04bbib1","doi-asserted-by":"publisher","first-page":"4664","DOI":"10.1002\/mp.16529","type":"journal-article","article-title":"SynthRAD2023 Grand Challenge dataset: Generating synthetic CT for radiotherapy","volume":"50","author":"Adrian","year":"2023","journal-title":"Med. Phys."},{"key":"pmbaea04bbib2","doi-asserted-by":"publisher","first-page":"802","DOI":"10.1109\/JBHI.2015.2453437","type":"journal-article","article-title":"Adaptive mathematical model of tumor response to radiotherapy based on CBCT data","volume":"20","author":"Belfatto","year":"2016","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"pmbaea04bbib3","article-title":"Why registration quality matters: enhancing sCT synthesis with IMPACT-based","author":"Boussot","year":"2025a","type":"preprint"},{"key":"pmbaea04bbib4","article-title":"IMPACT: a generic semantic loss for multimodal medical image registration","author":"Boussot","year":"2025b","type":"preprint"},{"key":"pmbaea04bbib5","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104269","type":"journal-article","article-title":"Domain adversarial networks and intensity-based data augmentation for male pelvic organ segmentation in cone beam CT","volume":"131","author":"Brion","year":"2021","journal-title":"Comput. Biol. Med."},{"key":"pmbaea04bbib6","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-92094-6","type":"journal-article","article-title":"CBCT-to-CT synthesis using a hybrid U-Net diffusion model based on transformers and information bottleneck theory","volume":"15","author":"Can","year":"2025","journal-title":"Sci. Rep."},{"key":"pmbaea04bbib7","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.988800","type":"journal-article","article-title":"A more effective CT synthesizer using transformers for cone-beam CT-guided adaptive radiotherapy","volume":"12","author":"Chen","year":"2022","journal-title":"Front. Oncol."},{"key":"pmbaea04bbib8","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.semradonc.2019.02.002","type":"journal-article","article-title":"Deformable registration for dose accumulation","volume":"29","author":"Chetty","year":"2019","journal-title":"Semin. Radiat. Oncol."},{"key":"pmbaea04bbib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.103046","type":"journal-article","article-title":"Deep learning based synthesis of MRI, CT and PET: review and analysis","volume":"92","author":"Dayarathna","year":"2024","journal-title":"Med. Image Anal."},{"key":"pmbaea04bbib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2025.100744","type":"journal-article","article-title":"Physics-based data augmentation for improved training of cone-beam computed tomography auto-segmentation of the female pelvis","volume":"34","author":"Hond","year":"2025","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"pmbaea04bbib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103276","type":"journal-article","article-title":"Generating synthetic computed tomography for radiotherapy: SynthRAD2023 challenge report","volume":"97","author":"Huijben","year":"2024","journal-title":"Med. Image Anal."},{"key":"pmbaea04bbib12","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","type":"journal-article","article-title":"nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"pmbaea04bbib13","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1109\/TMI.2009.2035616","type":"journal-article","article-title":"elastix: a toolbox for intensity based medical image registration","volume":"29","author":"Klein","year":"2010","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbaea04bbib14","first-page":"pp 1","type":"conference-proceedings","article-title":"Breaking the Dilemma of medical image-to-image translation","volume":"vol 34","author":"Kong","year":"2021"},{"key":"pmbaea04bbib15","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.3390\/cancers16061206","type":"journal-article","article-title":"Adaptive radiotherapy: next-generation radiotherapy","volume":"16","author":"Lemus","year":"2024","journal-title":"Cancers"},{"key":"pmbaea04bbib16","doi-asserted-by":"publisher","first-page":"8302","DOI":"10.1002\/mp.17338","type":"journal-article","article-title":"A unified generation-registration framework for improved MR-based CT synthesis in proton therapy","volume":"51","author":"Li","year":"2024","journal-title":"Med. Phys."},{"key":"pmbaea04bbib17","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ab22f9","type":"journal-article","article-title":"Generating synthesized computed tomography (CT) from cone-beam computed tomography (CBCT) using CycleGAN for adaptive radiation therapy","volume":"64","author":"Liang","year":"2019","journal-title":"Phys. Med. Biol."},{"key":"pmbaea04bbib18","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1186\/s13014-023-02340-2","type":"journal-article","article-title":"Review of cone beam computed tomography based online adaptive radiotherapy: current trend and future direction","volume":"18","author":"Liu","year":"2023","journal-title":"Radiat. Oncol."},{"key":"pmbaea04bbib19","doi-asserted-by":"publisher","first-page":"2472","DOI":"10.1002\/mp.14121","type":"journal-article","article-title":"CBCT-based synthetic CT generation using deep-attention cycleGAN for pancreatic adaptive radiotherapy","volume":"47","author":"Liu","year":"2020","journal-title":"Med. Phys."},{"key":"pmbaea04bbib20","article-title":"Spectral normalization for generative adversarial networks","author":"Miyato","year":"2018","type":"conference-proceedings"},{"key":"pmbaea04bbib21","article-title":"Cone-Beam CT image quality enhancement using a latent diffusion model trained with simulated CBCT artifacts","author":"Murahashi","year":"2026","type":"preprint"},{"key":"pmbaea04bbib22","doi-asserted-by":"publisher","first-page":"24TR01","DOI":"10.1088\/1361-6560\/ad0d8a","type":"journal-article","article-title":"Review and recommendations on deformable image registration uncertainties for radiotherapy applications","volume":"68","author":"Nenoff","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"pmbaea04bbib23","first-page":"pp 646","type":"book","article-title":"SinoSynth: A Physics-Based Domain Randomization Approach for Generalizable CBCT Image Enhancement","author":"Pang","year":"2024"},{"key":"pmbaea04bbib24","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1007\/s00066-024-02277-9","type":"journal-article","article-title":"Artificial intelligence for treatment delivery: image-guided radiotherapy","volume":"201","author":"Rabe","year":"2025","journal-title":"Strahlenther. Onkol."},{"key":"pmbaea04bbib25","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":"pmbaea04bbib26","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1109\/TMI.2011.2163944","type":"journal-article","article-title":"Image similarity and tissue overlaps as surrogates for image registration accuracy: widely used but unreliable","volume":"31","author":"Rohlfing","year":"2012","journal-title":"IEEE Trans. Med. Imaging"},{"key":"pmbaea04bbib27","doi-asserted-by":"publisher","first-page":"6019","DOI":"10.1002\/mp.15840","type":"journal-article","article-title":"Deep learning methods for enhancing cone-beam CT image quality toward adaptive radiation therapy: a systematic review","volume":"49","author":"Rusanov","year":"2022","journal-title":"Med. Phys."},{"key":"pmbaea04bbib28","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1259\/dmfr\/30642039","type":"journal-article","article-title":"Artefacts in CBCT: a review","volume":"40","author":"Schulze","year":"2011","journal-title":"Dentomaxillofacial Radiol."},{"key":"pmbaea04bbib29","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.3390\/cancers15072017","type":"journal-article","article-title":"CBCT-to-CT translation using registration-based generative adversarial networks in patients with head and neck cancer","volume":"15","author":"Suwanraksa","year":"2023","journal-title":"Cancers"},{"key":"pmbaea04bbib30","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17981","type":"journal-article","article-title":"SynthRAD2025 Grand Challenge dataset: Generating synthetic CTs for radiotherapy from head to abdomen","volume":"52","author":"Thummerer","year":"2025","journal-title":"Med. Phys."},{"key":"pmbaea04bbib31","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1007\/s11548-019-02011-2","type":"journal-article","article-title":"Enabling machine learning in x-ray-based procedures via realistic simulation of image formation","volume":"14","author":"Unberath","year":"2019","journal-title":"Int. J. Comput. Assist. Radiol. Surg. (IJCARS)"},{"key":"pmbaea04bbib32","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-00937-3_12","type":"book","article-title":"DeepDRR\u2013A Catalyst for Machine Learning in Fluoroscopy-guided Procedures","author":"Unberath","year":"2018"},{"key":"pmbaea04bbib33","doi-asserted-by":"publisher","first-page":"- 2024","DOI":"10.3389\/fonc.2024.1440944","type":"journal-article","article-title":"A joint learning framework for multisite CBCT-to-CT translation using a hybrid CNN-transformer synthesizer and a registration network","volume":"14","author":"Ying","year":"2024a","journal-title":"Front. Oncol."},{"key":"pmbaea04bbib34","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-61492-7","type":"journal-article","article-title":"Synthetic CT generation based on CBCT using improved vision transformer CycleGAN","volume":"14","author":"Yuxin","year":"2024","journal-title":"Sci. Rep."},{"key":"pmbaea04bbib35","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.244","type":"conference-proceedings","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T09:15:36Z","timestamp":1790154936000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/aea04b"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,8]]},"references-count":35,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,9,8]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/aea04b","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,8]]},"assertion":[{"value":"Eliminating registration bias in synthetic CT generation using a physics-based simulation framework for pelvic anatomy","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":"2026-04-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-08-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-09-08","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}