{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T04:34:08Z","timestamp":1775277248368,"version":"3.50.1"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T00:00:00Z","timestamp":1701129600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>For radiotherapy based solely on magnetic resonance imaging (MRI), generating synthetic computed tomography scans (sCT) from MRI is essential for dose calculation. The use of deep learning (DL) methods to generate sCT from MRI has shown encouraging results if the MRI images used for training the deep learning network and the MRI images for sCT generation come from the same MRI device. The objective of this study was to create and evaluate a generic DL model capable of generating sCTs from various MRI devices for prostate radiotherapy<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>In total, 90 patients from three centers (30 CT-MR prostate pairs\/center) underwent treatment using volumetric modulated arc therapy for prostate cancer (PCa) (60 Gy in 20 fractions). T2 MRI images were acquired in addition to computed tomography (CT) images for treatment planning. The DL model was a 2D supervised conditional generative adversarial network (Pix2Pix). Patient images underwent preprocessing steps, including nonrigid registration. Seven different supervised models were trained, incorporating patients from one, two, or three centers. Each model was trained on 24 CT-MR prostate pairs. A generic model was trained using patients from all three centers. To compare sCT and CT, the mean absolute error in Hounsfield units was calculated for the entire pelvis, prostate, bladder, rectum, and bones. For dose analysis, mean dose differences of <jats:italic>D<\/jats:italic><jats:sub>99%<\/jats:sub> for CTV, <jats:italic>V<\/jats:italic><jats:sub>95%<\/jats:sub> for PTV, D<jats:sub>max<\/jats:sub> for rectum and bladder, and 3D gamma analysis (local, 1%\/1 mm) were calculated from CT and sCT. Furthermore, Wilcoxon tests were performed to compare the image and dose results obtained with the generic model to those with the other trained models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Considering the image results for the entire pelvis, when the data used for the test comes from the same center as the data used for training, the results were not significantly different from the generic model. Absolute dose differences were less than 1 Gy for the CTV <jats:italic>D<\/jats:italic><jats:sub>99%<\/jats:sub> for every trained model and center. The gamma analysis results showed nonsignificant differences between the generic and monocentric models.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The accuracy of sCT, in terms of image and dose, is equivalent to whether MRI images are generated using the generic model or the monocentric model. The generic model, using only eight MRI-CT pairs per center, offers robust sCT generation, facilitating PCa MRI-only radiotherapy for routine clinical use.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fonc.2023.1279750","type":"journal-article","created":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T08:32:21Z","timestamp":1701160341000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["A deep learning model to generate synthetic CT for prostate MR-only radiotherapy dose planning: a multicenter study"],"prefix":"10.3389","volume":"13","author":[{"given":"Safaa","family":"Tahri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Blanche","family":"Texier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jean-Claude","family":"Nunes","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"C\u00e9dric","family":"Hemon","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pauline","family":"Lekieffre","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emma","family":"Collot","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hilda","family":"Chourak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jennifer","family":"Le Guevelou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Greer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"Dowling","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Oscar","family":"Acosta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Bessieres","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Louis","family":"Marage","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adrien","family":"Boue-Rafle","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renaud","family":"De Crevoisier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Caroline","family":"Lafond","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ana\u00efs","family":"Barateau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,11,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1118\/1.2161407","article-title":"Assessing the effect of electron density in photon dose calculations: Effect of electron density in photon dose calculations","volume":"33","author":"Seco","year":"2006","journal-title":"Med Phys"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11175136","article-title":"Emergence of MR-linac in radiation oncology: successes and challenges of riding on the MRgRT bandwagon","volume":"11","author":"Das","year":"2022","journal-title":"J Clin Med"},{"key":"B3","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.radonc.2017.12.022","article-title":"Standard whole prostate gland radiotherapy with and without lesion boost in prostate cancer: Toxicity in the FLAME randomized controlled trial","volume":"127","author":"Monninkhof","year":"2018","journal-title":"Radiother Oncol"},{"key":"B4","doi-asserted-by":"publisher","first-page":"05TR01","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":"B5","doi-asserted-by":"publisher","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":"B6","doi-asserted-by":"publisher","first-page":"28","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":"B7","doi-asserted-by":"publisher","first-page":"6537\u201366","DOI":"10.1002\/mp.15150","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":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.07.027","article-title":"Deep learning methods to generate synthetic CT from MRI in radiotherapy: A literature review","volume":"89","author":"Boulanger","year":"2021","journal-title":"Phys Med"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2022.10.003","article-title":"A high-performance method of deep learning for prostate MR-only radiotherapy planning using an optimized Pix2Pix architecture","volume":"103","author":"Tahri","year":"2022","journal-title":"Phys Med"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.08.049","article-title":"Comparison of deep learning-based and patch-based methods for pseudo-CT generation in MRI-based prostate dose planning","volume":"105","author":"Largent","year":"2019","journal-title":"Int J Radiat Oncol"},{"key":"B11","doi-asserted-by":"publisher","first-page":"105004","DOI":"10.1088\/1361-6560\/ab857b","article-title":"Investigating conditional GAN performance with different generator architectures, an ensemble model, and different MR scanners for MR-sCT conversion","volume":"65","author":"Fetty","year":"2020","journal-title":"Phys Med Biol"},{"key":"B12","doi-asserted-by":"publisher","first-page":"075002","DOI":"10.1088\/1361-6560\/ab7633","article-title":"MR to CT synthesis with multicenter data in the pelvic area using a conditional generative adversarial network","volume":"65","author":"Brou Boni","year":"2020","journal-title":"Phys Med Biol"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14866","article-title":"Improving generalization in MR-to-CT synthesis in radiotherapy by using an augmented cycle generative adversarial network with unpaired data","volume":"48","author":"Brou Boni","year":"2021","journal-title":"Med Phys"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.11.027","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":"B15","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12748","article-title":"MR and CT data with multiobserver delineations of organs in the pelvic area-Part of the Gold Atlas project","volume":"45","author":"Nyholm","year":"2018","journal-title":"Med Phys"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2010.03.049","article-title":"70 Gy versus 80 Gy in localized prostate cancer: 5-year results of GETUG 06 randomized trial","volume":"80","author":"Beckendorf","year":"2011","journal-title":"Int J Radiat Oncol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2010.2046908","article-title":"N4ITK: improved N3 bias correction","volume":"29","author":"Tustison","year":"2010","journal-title":"IEEE Trans Med Imaging"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2015.08.045","article-title":"Automatic substitute computed tomography generation and contouring for magnetic resonance imaging (MRI)-alone external beam radiation therapy from standard MRI sequences","volume":"93","author":"Dowling","year":"2015","journal-title":"Int J Radiat Oncol"},{"key":"B19","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":"B20","author":"Isola","year":""},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.05.006","article-title":"Dosimetry-driven quality measure of brain pseudo computed tomography generated from deep learning for MRI-only radiation therapy treatment planning","volume":"108","author":"Alvarez Andres","year":"2020","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B22","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":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2022.06.011","article-title":"Quality assurance for AI-based applications in radiation therapy","volume":"32","author":"Claessens","year":"2022","journal-title":"Semin Radiat Oncol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2023.1279750\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,28]],"date-time":"2023-11-28T08:32:24Z","timestamp":1701160344000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2023.1279750\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,28]]},"references-count":23,"alternative-id":["10.3389\/fonc.2023.1279750"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2023.1279750","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,28]]},"article-number":"1279750"}}