{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T06:19:09Z","timestamp":1783664349053,"version":"3.55.0"},"reference-count":36,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"Harvard Joint Center for Radiation Therapy"},{"name":"Consejo Nacional de Humanidades, Ciencias y Tecnolog\uc833"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Purpose.<\/jats:italic>\n                    Accurate modeling of intraluminal gas in synthetic computed tomography (sCT) is often compromised by the stochastic nature of bowel and rectal gas, which complicates magnetic resonance imaging (MRI)\/CT deformable image registration (DIR) and necessitates time-consuming manual corrections. Here, we propose a novel, DIR-free, two-stage deep learning framework designed to improve the definition of intraluminal gas in sCT. By circumventing registration-based errors, this method aims to streamline MRI-only simulation and enhance the dosimetric reliability of sCT images in MRI-based radiotherapy.\n                    <jats:italic>Methods.<\/jats:italic>\n                    sCT generation was implemented using a two-stage generative adversarial network (GAN) framework. In the first stage, a CycleGAN or pix2pix model converted MRI inputs into segmented map images (SMI); in the second stage, a conditional GAN (pix2pix) transformed the SMI into the final sCT. Ground-truth intraluminal gas cavities were defined in the following order: gastrointestinal contours were generated via CNN-based autosegmentation, manually verified, and subjected to a 20% intensity threshold. The framework was trained and validated using a publicly available 60-patient dataset. Performance was evaluated using the Dice-S\u00f8rensen coefficient for gas definition and mean absolute error (MAE) for global and tissue-specific Hounsfield unit (HU) accuracy, comparing the two-stage framework against a direct single-stage MRI-to-sCT model. To evaluate dosimetric accuracy, prostate volumetric modulated arc therapy plans (36.25 Gy in 5 fractions) were optimized on five reference bulk-density sCT datasets and recalculated on both one-stage and two-stage sCT using a clinical treatment planning system.\n                    <jats:italic>Results.<\/jats:italic>\n                    The gas cavity Dice-S\u00f8rensen coefficient for the two-stage method and the single-stage method were 0.63 \u00b1 0.11 and 0.04 \u00b1 0.03 for pix2pix, while for CycleGAN, they were 0.67 \u00b1 0.07 and 0.57 \u00b1 0.11, respectively. The global MAE for the standard single-stage method and the two-stage method for pix2pix were 86 \u00b1 20 HU and 94 \u00b1 20 HU, while for CycleGAN, they were 105 \u00b1 21 HU and 103 \u00b1 22 HU, respectively. Dosimetric analysis demonstrated excellent agreement for the planning target volume (PTV D95%), with mean differences of 0.04 \u00b1 0.08 cGy and \u22120.89 \u00b1 1.98 cGy for the one-stage and two-stage models, respectively. Both models exhibited negligible deviations across all assessed organ-at-risk volumetric metrics, including D0.1cc, D1cc, and D15cc.\n                    <jats:italic>Conclusions.<\/jats:italic>\n                    The proposed two-stage framework significantly enhances the anatomical accuracy of intraluminal gas in sCT images, achieving a nearly threefold improvement in gas cavity definition over standard direct-conversion models. This method maintains high fidelity for bone and soft tissue while addressing a critical bottleneck in MRI-only simulation. Future studies will focus on the prospective evaluation of this framework to quantify its impact on dosimetric accuracy and treatment efficiency in online adaptive radiotherapy workflows.\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae6d02","type":"journal-article","created":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T22:48:07Z","timestamp":1778712487000},"page":"045017","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning-based intraluminal gas modeling for anatomically accurate synthetic CT in MRI-based radiation therapy"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3501-2975","authenticated-orcid":true,"given":"Braian Adair Maldonado","family":"Luna","sequence":"first","affiliation":[{"name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6751-6884","authenticated-orcid":false,"given":"Gerardo Uriel P\u00e9rez","family":"Rojas","sequence":"additional","affiliation":[{"name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8699-011X","authenticated-orcid":false,"given":"Ren\u00e9 Eduardo Rodr\u00edguez","family":"P\u00e9rez","sequence":"additional","affiliation":[{"name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2124-1084","authenticated-orcid":true,"given":"Benito De Celis","family":"Alonso","sequence":"additional","affiliation":[{"name":"Benem\u00e9rita Universidad Aut\u00f3noma de Puebla"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3408-9587","authenticated-orcid":true,"given":"Kamal","family":"Singhrao","sequence":"additional","affiliation":[{"name":"Mass General Brigham Cancer Institute"},{"name":"Harvard Medical School"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"bpexae6d02bib1","doi-asserted-by":"publisher","first-page":"R323","DOI":"10.1088\/0031-9155\/60\/22\/R323","type":"journal-article","article-title":"Radiotherapy planning using MRI","volume":"60","author":"Schmidt","year":"2015","journal-title":"Phys. Med. Biol."},{"key":"bpexae6d02bib2","doi-asserted-by":"publisher","first-page":"05TR01","DOI":"10.1088\/1361-6560\/aaaca4","type":"journal-article","article-title":"MRI-only treatment planning: benefits and challenges","volume":"63","author":"Owrangi","year":"2018","journal-title":"Phys. Med. Biol."},{"key":"bpexae6d02bib3","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac279e","type":"journal-article","article-title":"Abdominal synthetic CT reconstruction with intensity projection prior for MRI-only adaptive radiotherapy","volume":"66","author":"Olberg","year":"2021","journal-title":"Phys. Med. Biol."},{"key":"bpexae6d02bib4","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1478148","type":"journal-article","article-title":"Abdominal synthetic CT generation for MR-only radiotherapy using structure-conserving loss and transformer-based cycle-GAN","volume":"14","author":"Lee","year":"2025","journal-title":"Front. Oncol."},{"key":"bpexae6d02bib5","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1186\/s13014-015-0549-7","type":"journal-article","article-title":"Dosimetric evaluation of synthetic CT relative to bulk density assignment-based magnetic resonance-only approaches for prostate radiotherapy","volume":"10","author":"Kim","year":"2015","journal-title":"Radiat. Oncol."},{"key":"bpexae6d02bib6","doi-asserted-by":"publisher","first-page":"3788","DOI":"10.1002\/mp.13672","type":"journal-article","article-title":"Deep learning approaches using 2D and 3D convolutional neural networks for generating male pelvic synthetic computed tomography from magnetic resonance imaging","volume":"46","author":"Fu","year":"2019","journal-title":"Med. Phys."},{"key":"bpexae6d02bib7","doi-asserted-by":"publisher","first-page":"e1256","DOI":"10.1259\/bjr\/26802977","type":"journal-article","article-title":"The influence of MRI scan position on image registration accuracy, target delineation and calculated dose in prostatic radiotherapy","volume":"85","author":"Hanvey","year":"2012","journal-title":"Br. J. Radiol."},{"key":"bpexae6d02bib8","doi-asserted-by":"publisher","first-page":"364","DOI":"10.3390\/jcm11020364","type":"journal-article","article-title":"Dosimetric effects of air cavities for MRI-guided online adaptive radiation therapy (MRgART) of prostate bed after radical prostatectomy","volume":"11","author":"Pham","year":"2022","journal-title":"J. Clin. Med."},{"key":"bpexae6d02bib9","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s13014-016-0747-y","type":"journal-article","article-title":"A review of substitute CT generation for MRI-only radiation therapy","volume":"12","author":"Edmund","year":"2017","journal-title":"Radiat. Oncol."},{"key":"bpexae6d02bib10","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20180948","type":"journal-article","article-title":"Comparison of prostate delineation on multimodality imaging for MR-guided radiotherapy","volume":"92","author":"Pathmanathan","year":"2019","journal-title":"Br. J. Radiol."},{"key":"bpexae6d02bib11","doi-asserted-by":"publisher","DOI":"10.1002\/mp.18038","type":"journal-article","article-title":"A comprehensive comparative study of generative adversarial network architectures for synthetic computed tomography generation in the abdomen","volume":"52","author":"Lapaeva","year":"2025","journal-title":"Med. Phys."},{"key":"bpexae6d02bib12","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1002\/mp.16857","type":"journal-article","article-title":"End-to-end validation of fiducial tracking accuracy in robotic radiosurgery using MRI-only simulation imaging","volume":"51","author":"Singhrao","year":"2024","journal-title":"Med. Phys."},{"key":"bpexae6d02bib13","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14411","type":"journal-article","article-title":"Linac- and CyberKnife-based MRI-only treatment planning of prostate SBRT using an optimized synthetic CT calibration curve","volume":"25","author":"Scholey","year":"2024","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"bpexae6d02bib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2023.100511","type":"journal-article","article-title":"Computed tomography synthesis from magnetic resonance imaging using cycle generative adversarial networks with multicenter learning","volume":"28","author":"Texier","year":"2023","journal-title":"Phys. Imaging Radiat. Oncol."},{"key":"bpexae6d02bib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2023.110052","type":"journal-article","article-title":"Deep learning MRI-only synthetic-CT generation for pelvis, brain and head and neck cancers","volume":"191","author":"Bird","year":"2024","journal-title":"Radiother. Oncol."},{"key":"bpexae6d02bib16","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.radonc.2020.11.027","type":"journal-article","article-title":"Multicentre, deep learning, synthetic-CT generation for ano-rectal MR-only radiotherapy treatment planning","volume":"156","author":"Bird","year":"2021","journal-title":"Radiother. Oncol."},{"key":"bpexae6d02bib17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87231-1_46","type":"conference-proceedings","article-title":"SA-GAN: structure-aware GAN for organ-preserving synthetic CT generation","volume":"vol 12906","author":"Emami","year":"2021"},{"key":"bpexae6d02bib18","doi-asserted-by":"publisher","DOI":"10.1088\/2057-1976\/ab6e1f","type":"journal-article","article-title":"Generation of abdominal synthetic CTs from 0.35T MR images using generative adversarial networks for MR-only liver radiotherapy","volume":"6","author":"Fu","year":"2020","journal-title":"Biomed. Phys. Eng. Express"},{"key":"bpexae6d02bib19","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1002\/acm2.12903","type":"journal-article","article-title":"Impact of varying air cavity on planning dosimetry for rectum patients treated on a 1.5 T hybrid MR-linac system","volume":"21","author":"Godoy Scripes","year":"2020","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"bpexae6d02bib20","doi-asserted-by":"publisher","first-page":"05NT01","DOI":"10.1088\/1361-6560\/adb5eb","type":"journal-article","article-title":"Automated hallucination detection for synthetic CT images used in MR-only radiotherapy workflows","volume":"70","author":"Parchur","year":"2025","journal-title":"Phys. Med. Biol."},{"key":"bpexae6d02bib21","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":"Thummerer","year":"2023","journal-title":"Med. Phys."},{"key":"bpexae6d02bib22","doi-asserted-by":"publisher","first-page":"1787","DOI":"10.4103\/1673-5374.238623","type":"journal-article","article-title":"Semi-automated segmentation of magnetic resonance images for thigh skeletal muscle and fat using threshold technique after spinal cord injury","volume":"13","author":"Ghatas","year":"2018","journal-title":"Neural Regen. Res."},{"key":"bpexae6d02bib23","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","type":"journal-article","article-title":"3D slicer as an image computing platform for the quantitative imaging network","volume":"30","author":"Fedorov","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"bpexae6d02bib24","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/s13139-012-0175-3","type":"journal-article","article-title":"Optimal CT number range for adipose tissue when determining lean body mass in whole-body F-18 FDG PET\/CT studies","volume":"46","author":"Kim","year":"2012","journal-title":"Nucl. Med. Mol. Imaging"},{"key":"bpexae6d02bib25","doi-asserted-by":"publisher","first-page":"6063","DOI":"10.3390\/jcm13206063","type":"journal-article","article-title":"CT-based evaluation of volumetric posterior pelvic bone density with implications for the percutaneous screw fixation of the sacroiliac joint","volume":"13","author":"Ku\u0142akowski","year":"2024","journal-title":"J. Clin. Med."},{"key":"bpexae6d02bib26","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240777","type":"journal-article","article-title":"Segmenting whole-body MRI and CT for multiorgan anatomic structure delineation","volume":"7","author":"H\u00e4ntze","year":"2025","journal-title":"Radiol. Artif. Intell."},{"key":"bpexae6d02bib27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102509","type":"journal-article","article-title":"\u2534-loss: a symmetric loss function for magnetic resonance imaging reconstruction and image registration with deep learning","volume":"80","author":"Terpstra","year":"2022","journal-title":"Med. Image Anal."},{"key":"bpexae6d02bib28","doi-asserted-by":"publisher","first-page":"2242","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"},{"key":"bpexae6d02bib29","doi-asserted-by":"publisher","first-page":"5967","DOI":"10.1109\/CVPR.2017.632","type":"conference-proceedings","article-title":"Image-to-image translation with conditional adversarial networks","author":"Isola","year":"2017"},{"key":"bpexae6d02bib30","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1111\/j.1754-9485.2012.02375.x","type":"journal-article","article-title":"CT-based estimation of intracavitary gas volumes using threshold-based segmentation: in vitro study to determine the optimal threshold range","volume":"56","author":"McWilliams","year":"2012","journal-title":"J. Med. Imaging Radiat. Oncol."},{"key":"bpexae6d02bib31","doi-asserted-by":"publisher","first-page":"4537","DOI":"10.1007\/s00330-022-08568-y","type":"journal-article","article-title":"Synthetic CT for the planning of MR-HIFU treatment of bone metastases in pelvic and femoral bones: a feasibility study","volume":"32","author":"Lena","year":"2022","journal-title":"Eur. Radiol."},{"key":"bpexae6d02bib32","article-title":"Corrections RTOG 0938: a randomized phase II trial of hypofractionated radiotherapy for favorable risk prostate cancer","author":"Radiation Therapy Oncology Group (RTOG)","year":"2016","type":"web-resource"},{"key":"bpexae6d02bib33","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.11.1.015002","type":"journal-article","article-title":"Deep learning performance on MRI prostate gland segmentation: evaluation of two commercially available algorithms compared with an expert radiologist","volume":"11","author":"Thimansson","year":"2024","journal-title":"J. Med. Imaging (Bellingham)"},{"key":"bpexae6d02bib34","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.70010","type":"journal-article","article-title":"Evaluation and failure analysis of four commercial deep learning-based autosegmentation software for abdominal organs at risk","volume":"26","author":"(MIM Software, Inc)","year":"2025","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"bpexae6d02bib35","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2022.969463","type":"journal-article","article-title":"Synthetic CT generation for MRI-guided adaptive radiotherapy in prostate cancer","volume":"12","author":"Hsu","year":"2022","journal-title":"Front. Oncol."},{"key":"bpexae6d02bib36","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2023.110064","type":"journal-article","article-title":"Stereotactic MR-guided on-table adaptive radiation therapy (SMART) for borderline resectable and locally advanced pancreatic cancer: a multi-center, open-label phase 2 study","volume":"191","author":"Chuong","year":"2024","journal-title":"Radiother. Oncol."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T06:08:55Z","timestamp":1783663735000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae6d02"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":36,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,7,10]]},"published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae6d02","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"assertion":[{"value":"Deep learning-based intraluminal gas modeling for anatomically accurate synthetic CT in MRI-based radiation therapy","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2026-01-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-05-13","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-10","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}