{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T12:01:43Z","timestamp":1787313703362,"version":"build-2736575974"},"reference-count":57,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T00:00:00Z","timestamp":1735862400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003710","name":"Korea Health Industry Development Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003710","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Recent deep-learning based synthetic computed tomography (sCT) generation using magnetic resonance (MR) images have shown promising results. However, generating sCT for the abdominal region poses challenges due to the patient motion, including respiration and peristalsis. To address these challenges, this study investigated an unsupervised learning approach using a transformer-based cycle-GAN with structure-preserving loss for abdominal cancer patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>A total of 120 T2 MR images scanned by 1.5 T Unity MR-Linac and their corresponding CT images for abdominal cancer patient were collected. Patient data were aligned using rigid registration. The study employed a cycle-GAN architecture, incorporating the modified Swin-UNETR as a generator. Modality-independent neighborhood descriptor (MIND) loss was used for geometric consistency. Image quality was compared between sCT and planning CT, using metrics including mean absolute error (MAE), peak signal-to-noise ratio (PSNR), structure similarity index measure (SSIM) and Kullback-Leibler (KL) divergence. Dosimetric evaluation was evaluated between sCT and planning CT, using gamma analysis and relative dose volume histogram differences for each organ-at-risks, utilizing treatment plan. A comparison study was conducted between original, Swin-UNETR-only, MIND-only, and proposed cycle-GAN.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The MAE, PSNR, SSIM and KL divergence of original cycle-GAN and proposed method were 86.1 HU, 26.48 dB, 0.828, 0.448 and 79.52 HU, 27.05 dB, 0.845, 0.230, respectively. The MAE and PSNR were statistically significant. The global gamma passing rates of the proposed method at 1%\/1 mm, 2%\/2 mm, and 3%\/3 mm were 86.1 \u00b1 5.9%, 97.1 \u00b1 2.7%, and 98.9 \u00b1 1.0%, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed method significantly improves image metric of sCT for the abdomen patients than original cycle-GAN. Local gamma analysis was slightly higher for proposed method. This study showed the improvement of sCT using transformer and structure preserving loss even with the complex anatomy of the abdomen.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2024.1478148","type":"journal-article","created":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T01:47:08Z","timestamp":1735868828000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Abdominal synthetic CT generation for MR-only radiotherapy using structure-conserving loss and transformer-based cycle-GAN"],"prefix":"10.3389","volume":"14","author":[{"given":"Chanwoong","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young Hun","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiwon","family":"Sung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun Won","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeona","family":"Cho","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jihun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaehee","family":"Chun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin Sung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"R323","DOI":"10.1088\/0031-9155\/60\/22\/R323","article-title":"Radiotherapy planning using mri","volume":"60","author":"Schmidt","year":"2015","journal-title":"Phys Med Biol"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13014-019-1308-y","article-title":"Mr-guidance in clinical reality: current treatment challenges and future perspectives","volume":"14","author":"Corradini","year":"2019","journal-title":"Radiat Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1007\/s11547-018-0951-y","article-title":"Delta radiomics for rectal cancer response prediction with hybrid 0.35 T magnetic resonance-guided radiotherapy (Mrgrt): A hypothesis-generating study for an innovative personalized medicine approach","volume":"124","author":"Boldrini","year":"2019","journal-title":"La radiol Med"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2018.08.010","article-title":"Magnetic resonance image-guided radiotherapy (Mrigrt): A 4.5-year clinical experience","volume":"30","author":"Henke","year":"2018","journal-title":"Clin Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2003.10.009","article-title":"Evaluation of a multimodality image (Ct, mri and pet) coregistration procedure on phantom and head and neck cancer patients: accuracy, reproducibility and consistency","volume":"69","author":"Daisne","year":"2003","journal-title":"Radiother Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1259\/bjr\/11855927","article-title":"An evaluation of four ct\u2013mri co-registration techniques for radiotherapy treatment planning of prone rectal cancer patients","volume":"85","author":"Dean","year":"2012","journal-title":"Br J Radiol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13014-016-0747-y","article-title":"A review of substitute ct generation for mri-only radiation therapy","volume":"12","author":"Edmund","year":"2017","journal-title":"Radiat Oncol"},{"key":"B8","doi-asserted-by":"publisher","first-page":"145015","DOI":"10.1088\/1361-6560\/ab25bc","article-title":"Mri-based treatment planning for proton radiotherapy: dosimetric validation of a deep learning-based liver synthetic ct generation method","volume":"64","author":"Liu","year":"2019","journal-title":"Phys Med Biol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1748-717X-4-54","article-title":"Systematisation of spatial uncertainties for comparison between a mr and a ct-based radiotherapy workflow for prostate treatments","volume":"4","author":"Nyholm","year":"2009","journal-title":"Radiat Oncol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1118\/1.1851920","article-title":"Use and uncertainties of mutual information for computed tomography\/magnetic resonance (Ct\/mr) registration post permanent implant of the prostate","volume":"32","author":"Roberson","year":"2005","journal-title":"Med Phys"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.10.017","article-title":"Results of a multi-institutional benchmark test for cranial ct\/mr image registration","volume":"77","author":"Ulin","year":"2010","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B12","article-title":"Errors and Margins in Radiotherapy","volume-title":"Seminars in radiation oncology","author":"Van Herk","year":""},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2005.12.042","article-title":"Abdominal organ motion measured using 4d ct","volume":"65","author":"Brandner","year":"2006","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14306","article-title":"B(0) field homogeneity recommendations, specifications, and measurement units for mri in radiation therapy","volume":"47","author":"Gach","year":"2020","journal-title":"Med Phys"},{"key":"B15","doi-asserted-by":"publisher","first-page":"05TR1","DOI":"10.1088\/1361-6560\/aaaca4","article-title":"Mri-only treatment planning: benefits and challenges","volume":"63","author":"Owrangi","year":"2018","journal-title":"Phys Med Biol"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.09.056","article-title":"Deep learning-enabled mri-only photon and proton therapy treatment planning for paediatric abdominal tumours","volume":"153","author":"Florkow","year":"2020","journal-title":"Radiother Oncol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1002\/mp.v48.11","article-title":"Deep learning based synthetic-ct generation in radiotherapy and pet: A review","volume":"48","author":"Spadea","year":"2021","journal-title":"Med Phys"},{"key":"B18","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.ijrobp.2017.08.043","article-title":"Systematic review of synthetic computed tomography generation methodologies for use in magnetic resonance imaging\u2013only radiation therapy","volume":"100","author":"Johnstone","year":"2018","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.10.002","article-title":"Pseudo-ct generation for mri-only radiation therapy treatment planning: comparison among patch-based, atlas-based, and bulk density methods","volume":"103","author":"Largent","year":"2019","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2461533","article-title":"Estimating ct image from mri data using structured random forest and auto-context model","volume":"35","author":"Huynh","year":"2015","journal-title":"IEEE Trans Med Imaging"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12155","article-title":"Mr-based synthetic ct generation using a deep convolutional neural network method","volume":"44","author":"Han","year":"2017","journal-title":"Med Phys"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13617","article-title":"Mri-only based synthetic ct generation using dense cycle consistent generative adversarial networks","volume":"46","author":"Lei","year":"2019","journal-title":"Med Phys"},{"key":"B23","doi-asserted-by":"publisher","first-page":"185001","DOI":"10.1088\/1361-6560\/aada6d","article-title":"Dose evaluation of fast synthetic-ct generation using a generative adversarial network for general pelvis mr-only radiotherapy","volume":"63","author":"Maspero","year":"2018","journal-title":"Phys Med Biol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1002\/mp.2018.45.issue-8","article-title":"Generating synthetic cts from magnetic resonance images using generative adversarial networks","volume":"45","author":"Emami","year":"2018","journal-title":"Med Phys"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1002\/mp.2018.45.issue-12","article-title":"U-net-generated synthetic ct images for magnetic resonance imaging-only prostate intensity-modulated radiation therapy treatment planning","volume":"45","author":"Chen","year":"2018","journal-title":"Med Phys"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1002\/mp.2018.45.issue-11","article-title":"Comparative study of algorithms for synthetic ct generation from mri: consequences for mri-guided radiation planning in the pelvic region","volume":"45","author":"Arabi","year":"2018","journal-title":"Med Phys"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09592-0","article-title":"A deep learning based review on abdominal images","volume":"80","author":"Rehman","year":"2021","journal-title":"Multimed Tools Appl"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.10.018","article-title":"A deep learning approach to generate synthetic ct in low field mr-guided adaptive radiotherapy for abdominal and pelvic cases","volume":"153","author":"Cusumano","year":"2020","journal-title":"Radiother Oncol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13838","article-title":"Evaluation of mri-only based online adaptive radiotherapy of abdominal region on mr-linac","volume":"24","author":"Nousiainen","year":"2023","journal-title":"J Appl Clin Med Phys"},{"key":"B30","doi-asserted-by":"publisher","first-page":"204001","DOI":"10.1088\/1361-6560\/ac279e","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":"B31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1706.03762","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929","article-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:201011929"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2022.3167808","article-title":"Resvit: residual vision transformers for multimodal medical image synthesis","volume":"41","author":"Dalmaz","year":"2022","journal-title":"IEEE Trans Med Imaging"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.467683","article-title":"Tcgan: A transformer-enhanced gan for pet synthetic ct","volume":"13","author":"Li","year":"2022","journal-title":"Biomed Optics Express"},{"key":"B35","doi-asserted-by":"publisher","first-page":"102150","DOI":"10.1016\/j.compmedimag.2022.102150","article-title":"Ct synthesis from mr in the pelvic area using residual transformer conditional gan","volume":"103","author":"Zhao","year":"2023","journal-title":"Computer Med Imaging Graphics"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2012.05.008","article-title":"Mind: modality independent neighbourhood descriptor for multi-modal deformable registration","volume":"16","author":"Heinrich","year":"2012","journal-title":"Med image Anal"},{"key":"B37","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-08999-2_22","article-title":"Swin Unetr: Swin Transformers for Semantic Segmentation of Brain Tumors in Mri Images","volume-title":"Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 7th International Workshop, BrainLes 2021, Held in Conjunction with MICCAI 2021, Virtual Event, September 27, 2021, Revised Selected Papers, Part I","author":"Hatamizadeh","year":""},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1109\/WACV51458.2022.00181","article-title":"Unetr: transformers for 3d medical image segmentation","author":"Hatamizadeh","year":"2022"},{"key":"B39","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2017.244","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.42","article-title":"Unsupervised mr-to-ct synthesis using structure-constrained cyclegan","volume":"39","author":"Yang","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"key":"B41","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1214\/aoms\/1177729694","article-title":"On information and sufficiency","volume":"22","author":"Kullback","year":"1951","journal-title":"Ann Math Stat"},{"key":"B42","doi-asserted-by":"crossref","first-page":"196","DOI":"10.1007\/978-1-4612-4380-9_16","article-title":"Individual Comparisons by Ranking Methods","volume-title":"Breakthroughs in Statistics: Methodology and Distribution","author":"Wilcoxon","year":"1992"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1118\/1.598248","article-title":"A technique for the quantitative evaluation of dose distributions","volume":"25","author":"Low","year":"1998","journal-title":"Med Phys"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07215","article-title":"On convergence and stability of gans","author":"Kodali","year":"2017","journal-title":"arXiv preprint arXiv:170507215"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021","journal-title":"Proc IEEE\/CVF Int Conf Comput Vision"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14619","article-title":"Cross-modality deep learning: contouring of mri data from annotated ct data only","volume":"48","author":"Kieselmann","year":"2021","journal-title":"Med Phys"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.2018.19.issue-2","article-title":"Validation of a deformable mri to ct registration algorithm employing same day planning mri for surrogate analysis","volume":"19","author":"Padgett","year":"2018","journal-title":"J Appl Clin Med Phys"},{"key":"B48","doi-asserted-by":"publisher","first-page":"015033","DOI":"10.1088\/2057-1976\/ab6e1f","article-title":"Generation of abdominal synthetic cts from 0.35 T mr images using generative adversarial networks for mr-only liver radiotherapy","volume":"6","author":"Fu","year":"2020","journal-title":"Biomed Phys Eng Express"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/j.meddos.2014.05.002","article-title":"A study on correlation between 2d and 3d gamma evaluation metrics in patient-specific quality assurance for vmat","volume":"39","author":"Rajasekaran","year":"2014","journal-title":"Med Dosimetry"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1118\/1.3238104","article-title":"Imrt commissioning: multiple institution planning and dosimetry comparisons, a report from aapm task group 119","volume":"36","author":"Ezzell","year":"2009","journal-title":"Med Phys"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12810","article-title":"Tolerance limits and methodologies for imrt measurement-based verification qa: recommendations of aapm task group no. 218","volume":"45","author":"Miften","year":"2018","journal-title":"Med Phys"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-022-01113-7","article-title":"Commissioning measurements on an elekta unity mr-linac","volume":"45","author":"Powers","year":"2022","journal-title":"Phys Eng Sci Med"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2006.01.039","article-title":"Magnetic resonance imaging of freely moving objects: prospective real-time motion correction using an external optical motion tracking system","volume":"31","author":"Zaitsev","year":"2006","journal-title":"Neuroimage"},{"key":"B54","doi-asserted-by":"publisher","first-page":"1547","DOI":"10.1088\/0031-9155\/52\/6\/001","article-title":"4d mr imaging of respiratory organ motion and its variability","volume":"52","author":"von Siebenthal","year":"2007","journal-title":"Phys Med Biol"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.2214\/AJR.07.3657","article-title":"Mri artifact reduction and quality improvement in the upper abdomen with propeller and prospective acquisition correction (Pace) technique","volume":"191","author":"Hirokawa","year":"2008","journal-title":"Am J roentgenol"},{"key":"B56","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.media.2016.06.005","article-title":"Autoadaptive motion modelling for mr-based respiratory motion estimation","volume":"35","author":"Baumgartner","year":"2017","journal-title":"Med image Anal"},{"key":"B57","doi-asserted-by":"publisher","first-page":"103276","DOI":"10.1016\/j.media.2024.103276","article-title":"Generating synthetic computed tomography for radiotherapy: synthrad2023 challenge report","volume":"97","author":"Huijben","year":"2024","journal-title":"Med image Anal"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2024.1478148\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T01:47:14Z","timestamp":1735868834000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2024.1478148\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,3]]},"references-count":57,"alternative-id":["10.3389\/fonc.2024.1478148"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2024.1478148","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,3]]},"article-number":"1478148"}}