{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T20:31:20Z","timestamp":1792528280846,"version":"4.5.0"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T00:00:00Z","timestamp":1771545600000},"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>\n                    <jats:title>Purpose\/objectives<\/jats:title>\n                    <jats:p>This study proposes and clinically evaluates synthetic CT (sCT) images generated from multi-center CBCT scans using artificial intelligence, with the aim of fully leveraging CBCT for adaptive radiotherapy in patients with pelvic, head-and-neck, lung, and breast cancer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>In collaboration with TheraPanacea (Paris, France), AI-based sCT models were developed for multiple anatomical sites using a cycleGAN architecture. The study included 51 patients from two European institutions diagnosed with head-and-neck, lung, pelvic or breast cancer and treated with CBCT-based position verification. CBCT scans were acquired using two linear accelerator systems (Varian and Elekta). Image accuracy was assessed using MAE, SSIM, and PSNR. For dosimetric evaluation, planning CTs (pCTs) were non-rigidly registered to CBCTs. Treatment plans were created on the pCT using a clinical TPS to meet standard clinical criteria, then recalculated on both the warped CT (wCT) and sCT. Dose distributions were compared using global gamma passing rates and dose-volume metrics.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The proposed model substantially improved image quality compared with CBCT. MAE decreased from 122.95 \u00b1 50.07 to 23.65 \u00b1 10.09, while SSIM increased from 0.78 \u00b1 0.12 to 0.97 \u00b1 0.03 and PSNR from 35.01 \u00b1 7.24 to 44.35 \u00b1 7.07. Dose-metric comparisons showed strong agreement between the pCT and wCT, with median relative differences within 0.5% for both targets and organs at risk. Median gamma passing rates for 2%\/2 mm and 3%\/3 mm criteria (10% threshold) reached 100% across all anatomical sites. No performance differences were observed between Elekta- and Varian-sCTs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This multi-center study demonstrates the feasibility of generating clinically acceptable AI-based sCTs from CBCT for multiple anatomical sites, yielding consistent image quality improvements and reliable dosimetric accuracy.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1756153","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T05:21:52Z","timestamp":1771564912000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Self-learning GAN based synthetic CT generation: unlocking CBCT-based adaptive radiotherapy"],"prefix":"10.3389","volume":"16","author":[{"given":"Jessica","family":"Prunaretty","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, Institut du Cancer de Montpellier","place":["Montpellier, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Colombo","sequence":"additional","affiliation":[{"name":"Clinical affairs, TheraPanacea","place":["Paris, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sami","family":"Romdhani","sequence":"additional","affiliation":[{"name":"AI Engineering, TheraPanacea","place":["Paris, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivier","family":"Teboul","sequence":"additional","affiliation":[{"name":"AI Engineering, TheraPanacea","place":["Paris, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Azria","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Institut du Cancer de Montpellier","place":["Montpellier, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Paragyios","sequence":"additional","affiliation":[{"name":"AI Engineering, TheraPanacea","place":["Paris, France"]},{"name":"Chief Executive Officer (CEO), TheraPanacea","place":["Paris, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pascal","family":"Fenoglietto","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Institut du Cancer de Montpellier","place":["Montpellier, France"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,20]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.semradonc.2009.11.001","article-title":"Adaptive radiotherapy: merging principle into clinical practice","volume":"20","author":"Yan","year":"2010","journal-title":"Semin Radiat Oncol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.10.021","article-title":"Adaptive radiation therapy (ART) strategies and technical considerations: A state of the ART review from NRG oncology","volume":"109","author":"Glide-Hurst","year":"2021","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B3","article-title":"World\u2019s first application of MR-guidance for radiotherapy","volume":"112","author":"Olsen","year":"2015","journal-title":"Mo Med"},{"key":"B4","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/j.ijrobp.2015.10.015","article-title":"Online magnetic resonance image guided adaptive radiation therapy: first clinical applications","volume":"94","author":"Acharya","year":"2016","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B5","article-title":"Archambault: Making on-line adaptive radiotherapy","author":"Archambault","year":"2020"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s00066-011-2236-4","article-title":"kV cone-beam CT-based IGRT: a clinical review","volume":"187","author":"Boda-Heggemann","year":"2011","journal-title":"Strahlenther Onkol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1259\/dmfr\/30642039","article-title":"Artefacts in CBCT: a review","volume":"40","author":"Schulze","year":"2011","journal-title":"Dentomaxillofac Radiol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2020.06.017","article-title":"A review of dose calculation approaches with cone beam CT in photon and proton therapy","volume":"76","author":"Giacometti","year":"2020","journal-title":"Phys Med"},{"key":"B9","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.canrad.2017.07.050","article-title":"Calcul de dose de radioth\u00e9rapie \u00e0 partir de tomographies coniques: \u00e9tat de l\u2019art","volume":"22","author":"Barateau","year":"2018","journal-title":"Cancer\/Radioth\u00e9rapie"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.01.055","article-title":"First clinical investigation of cone beam computed tomography and deformable registration for adaptive proton therapy for lung cancer","volume":"95","author":"Veiga","year":"2016","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC.2015.7319567","article-title":"Roles of Deformable Image Registration in adaptive RT: From contour propagation to dose monitoring","volume":"2015","author":"Simon","year":"2015","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"B12","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1118\/1.4903292","article-title":"Validation of a deformable image registration technique for cone beam CT-based dose verification","volume":"42","author":"Moteabbed","year":"2015","journal-title":"Med Phys"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1118\/1.3557468","article-title":"Correction for patient table-induced scattered radiation in cone-beam computed tomography (CBCT)","volume":"38","author":"Sun","year":"2011","journal-title":"Med Phys"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1118\/1.3497272","article-title":"Combining scatter reduction and correction to improve image quality in cone-beam computed tomography (CBCT)","volume":"37","author":"Jin","year":"2010","journal-title":"Med Phys"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.4236\/ijmpcero.2017.64032","article-title":"Method for converting cone-beam CT values into hounsfield units for radiation treatment planning","volume":"6","author":"Abe","year":"2017","journal-title":"Int J Med Physics Clin Eng Radiat Oncol"},{"key":"B16","doi-asserted-by":"publisher","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 Physics"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15840","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 Physics"},{"key":"B18","doi-asserted-by":"publisher","first-page":"100521","DOI":"10.1016\/j.phro.2023.100521","article-title":"Current and future developments of synthetic computed tomography generation for radiotherapy","volume":"28","author":"van Elmpt","year":"2023","journal-title":"Phys Imaging Radiat Oncol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fradi.2024.1385742","article-title":"A systematic literature review: deep learning techniques for synthetic medical image generation and their applications in radiotherapy","volume":"4","author":"Sherwani","year":"2024","journal-title":"Front Radiol"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.2548","article-title":"Cone beam computed tomography image quality improvement using a deep convolutional neural network","volume":"10","author":"Kida","year":"2018","journal-title":"Cureus"},{"key":"B21","doi-asserted-by":"publisher","first-page":"15330338211062416","DOI":"10.1177\/15330338211062415","article-title":"(CBCT) based synthetic CT generation using deep learning methods for dose calculation of nasopharyngeal carcinoma radiotherapy","volume":"20","author":"Xue","year":"2021","journal-title":"Technol Cancer Res Treat"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16777","article-title":"Comparison and evaluation of different deep learning models of synthetic CT generation from CBCT for nasopharynx cancer adaptive proton therapy","volume":"50","author":"Pang","year":"2023","journal-title":"Med Phys"},{"key":"B23","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.phro.2020.04.002","article-title":"A single neural network for cone-beam computed tomography-based radiotherapy of head-and-neck, lung and breast cancer","volume":"14","author":"Maspero","year":"2020","journal-title":"Phys Imaging Radiat Oncol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"5479","DOI":"10.3390\/cancers15225479","article-title":"CBCT-to-CT synthesis for cervical cancer adaptive radiotherapy via U-net-based model hierarchically trained with hybrid dataset","volume":"15","author":"Liu","year":"2023","journal-title":"Cancers"},{"key":"B25","doi-asserted-by":"publisher","first-page":"100511","DOI":"10.1016\/j.phro.2023.100511","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":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1245054","article-title":"A multi-centric evaluation of self-learning GAN based pseudo-CT generation software for low field pelvic magnetic resonance imaging","volume":"13","author":"Prunaretty","year":"2023","journal-title":"Front Oncol"},{"key":"B27","volume-title":"TIGRE: a MATLAB-GPU toolbox for CBCT image reconstruction","author":"Biguri","year":"2016"},{"key":"B28","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s13014-025-02590-2","article-title":"Synthetic CT generation from CBCT and MRI using StarGAN in the Pelvic Region","volume":"20","author":"Wongtrakool","year":"2025","journal-title":"Radiat Oncol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"100416","DOI":"10.1016\/j.phro.2023.100416","article-title":"Anatomical evaluation of deep-learning synthetic computed tomography images generated from male pelvis cone-beam computed tomography","volume":"25","author":"de Hond","year":"2023","journal-title":"Phys Imaging Radiat Oncol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13737","article-title":"Assessment of CBCT\u2013based synthetic CT generation accuracy for adaptive radiotherapy planning","volume":"23","author":"O\u2019Hara","year":"2022","journal-title":"J Appl Clin Med Phys"},{"key":"B31","doi-asserted-by":"publisher","first-page":"107393","DOI":"10.1016\/j.cmpb.2023.107393","article-title":"New technique and application of truncated CBCT processing in adaptive radiotherapy for breast cancer","volume":"231","author":"Xie","year":"2023","journal-title":"Comput Methods Programs Biomedicine"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17328","article-title":"CBCT-based synthetic CT image generation using a diffusion model for CBCT-guided lung radiotherapy","volume":"51","author":"Chen","year":"2024","journal-title":"Med Phys"},{"key":"B33","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"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16529","article-title":"SynthRAD2023 Grand Challenge dataset: Generating synthetic CT for radiotherapy","volume":"50","author":"Thummerer","year":"2023","journal-title":"Med Phys"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1002\/mp.17981","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":"B36","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1186\/s13014-020-01524-4","article-title":"Medical physics challenges in clinical MR-guided radiotherapy","volume":"15","author":"Kurz","year":"2020","journal-title":"Radiat Oncol"},{"key":"B37","doi-asserted-by":"publisher","first-page":"110345","DOI":"10.1016\/j.radonc.2024.110345","article-title":"A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy","volume":"197","author":"Hurkmans","year":"2024","journal-title":"Radiotherapy Oncol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1756153\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T05:21:54Z","timestamp":1771564914000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1756153\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,20]]},"references-count":37,"alternative-id":["10.3389\/fonc.2026.1756153"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1756153","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,20]]},"article-number":"1756153"}}