{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,20]],"date-time":"2025-09-20T04:43:49Z","timestamp":1758343429426,"version":"3.44.0"},"reference-count":40,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T00:00:00Z","timestamp":1758240000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Adaptive radiotherapy (ART) enhances prostate cancer treatment by accounting for daily anatomical variations, but clinical implementation remains limited due to the need for accurate and efficient auto segmentation; manual corrections after automated contouring often hinder workflow efficiency. To address this, we propose a patient-specific network (PSN) approach for clinical target volume (CTV) segmentation using cone-beam computed tomography (CBCT). This retrospective study included 26 prostate cancer patients treated with CBCT-guided online ART using the Ethos therapy system, comprising 119 retrospectively exported fractions. The PSN framework uses a two-stage strategy: initial pre-training followed by patient-specific fine-tuning via PSN<jats:sub>adaptive<\/jats:sub> or PSN<jats:sub>sequence<\/jats:sub>, implemented with the Swin UNETR architecture. This approach is distinct from static personalization methods as it continuously adapts to daily anatomical changes. Segmentation performance was compared against deformable registration and generalized deep learning models using the Dice similarity coefficient (DSC), 95<jats:sup>th<\/jats:sup> percentile Hausdorff distance (HD), and mean surface distance (MSD). PSN significantly improved segmentation performance, with PSN<jats:sub>adaptive<\/jats:sub> achieving a DSC of 0.978\u2009\u00b1\u20090.005, HD of 1.681\u2009\u00b1\u20090.743\u2009mm, and MSD of 0.510\u2009\u00b1\u20090.035\u2009mm by the fifth fraction, with accuracy improving across sequential fractions. Visual assessments confirmed high agreement with physician contours, especially in anatomically complex regions. These findings support the PSN framework as a clinically feasible and accurate solution for patient-specific segmentation in prostate ART, potentially reducing the need for manual editing, streamlining workflow efficiency, and enhancing the precision of adaptive treatment delivery.<\/jats:p>","DOI":"10.1371\/journal.pone.0332603","type":"journal-article","created":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:53:50Z","timestamp":1758318830000},"page":"e0332603","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving segmentation precision in prostate cancer adaptive radiation therapy with a patient-specific network"],"prefix":"10.1371","volume":"20","author":[{"given":"Joonil","family":"Hwang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Byung-Hee","family":"Kang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Younghee","family":"Park","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dong Hyeok","family":"Choi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jin Sung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seungryong","family":"Cho","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8945-4054","authenticated-orcid":true,"given":"Eungman","family":"Lee","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,9,19]]},"reference":[{"issue":"15","key":"pone.0332603.ref001","doi-asserted-by":"crossref","first-page":"1413","DOI":"10.1056\/NEJMoa2403365","article-title":"Phase 3 trial of stereotactic body radiotherapy in localized prostate cancer","volume":"391","author":"N van As","year":"2024","journal-title":"N Engl J Med"},{"key":"pone.0332603.ref002","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1016\/j.radonc.2021.12.013","article-title":"Online adaptive radiotherapy potentially reduces toxicity for high-risk prostate cancer treatment","volume":"167","author":"RL Christiansen","year":"2022","journal-title":"Radiother Oncol"},{"issue":"1","key":"pone.0332603.ref003","doi-asserted-by":"crossref","DOI":"10.1002\/acm2.13479","article-title":"Varian ethos online adaptive radiotherapy for prostate cancer: early results of contouring accuracy, treatment plan quality, and treatment time","volume":"23","author":"M Byrne","year":"2022","journal-title":"J Appl Clin Med Phys"},{"issue":"4","key":"pone.0332603.ref004","doi-asserted-by":"crossref","first-page":"1084","DOI":"10.1016\/j.ijrobp.2007.11.054","article-title":"Observations on real-time prostate gland motion using electromagnetic tracking","volume":"71","author":"KM Langen","year":"2008","journal-title":"Int J Radiat Oncol Biol Phys"},{"issue":"2","key":"pone.0332603.ref005","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1016\/j.ijrobp.2003.10.017","article-title":"Prostate gland motion assessed with cine-magnetic resonance imaging (cine-MRI)","volume":"62","author":"MJ Ghilezan","year":"2005","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"pone.0332603.ref006","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.radonc.2022.02.002","article-title":"Seminal vesicle inter- and intra-fraction motion during radiotherapy for prostate cancer: A review","volume":"169","author":"VJ Brand","year":"2022","journal-title":"Radiother Oncol"},{"issue":"8","key":"pone.0332603.ref007","doi-asserted-by":"crossref","first-page":"3415","DOI":"10.1002\/mp.14196","article-title":"Pelvic multi-organ segmentation on cone-beam CT for prostate adaptive radiotherapy","volume":"47","author":"Y Fu","year":"2020","journal-title":"Med Phys"},{"issue":"19","key":"pone.0332603.ref008","doi-asserted-by":"crossref","first-page":"3044","DOI":"10.1002\/cncr.34836","article-title":"Acute toxicity comparison of magnetic resonance\u2010guided adaptive versus fiducial or computed tomography\u2010guided non\u2010adaptive prostate stereotactic body radiotherapy: a systematic review and meta\u2010analysis","volume":"129","author":"JE Leeman","year":"2023","journal-title":"Cancer"},{"key":"pone.0332603.ref009","doi-asserted-by":"crossref","first-page":"1274082","DOI":"10.3389\/fonc.2023.1274082","article-title":"Feasibility study of adaptive radiotherapy with Ethos for breast cancer","volume":"13","author":"A Galand","year":"2023","journal-title":"Front Oncol"},{"key":"pone.0332603.ref010","doi-asserted-by":"crossref","first-page":"1399978","DOI":"10.3389\/fonc.2024.1399978","article-title":"Evaluation of Ethos intelligent optimization engine for left locally advanced breast cancer","volume":"14","author":"J Prunaretty","year":"2024","journal-title":"Front Oncol"},{"issue":"5","key":"pone.0332603.ref011","doi-asserted-by":"crossref","first-page":"101470","DOI":"10.1016\/j.adro.2024.101470","article-title":"Review of deep learning based autosegmentation for clinical target volume: current status and future directions","volume":"9","author":"T Matoska","year":"2024","journal-title":"Adv Radiat Oncol"},{"key":"pone.0332603.ref012","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.radonc.2021.02.040","article-title":"Clinical implementation of deep learning contour autosegmentation for prostate radiotherapy","volume":"159","author":"E Cha","year":"2021","journal-title":"Radiother Oncol"},{"issue":"3","key":"pone.0332603.ref013","doi-asserted-by":"crossref","first-page":"1573","DOI":"10.1002\/mp.16056","article-title":"Patient-specific transfer learning for auto-segmentation in adaptive 0.35 T MRgRT of prostate cancer: a bi-centric evaluation","volume":"50","author":"M Kawula","year":"2023","journal-title":"Med Phys"},{"issue":"4","key":"pone.0332603.ref014","doi-asserted-by":"crossref","first-page":"2570","DOI":"10.1002\/mp.15525","article-title":"Evaluating the clinical acceptability of deep learning contours of prostate and organs-at-risk in an automated prostate treatment planning process","volume":"49","author":"J Duan","year":"2022","journal-title":"Med Phys"},{"key":"pone.0332603.ref015","doi-asserted-by":"crossref","first-page":"102101","DOI":"10.1016\/j.media.2021.102101","article-title":"A deep learning-based framework for segmenting invisible clinical target volumes with estimated uncertainties for post-operative prostate cancer radiotherapy","volume":"72","author":"A Balagopal","year":"2021","journal-title":"Med Image Anal"},{"issue":"1","key":"pone.0332603.ref016","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.radonc.2018.01.014","article-title":"ESTRO ACROP consensus guideline on CT- and MRI-based target volume delineation for primary radiation therapy of localized prostate cancer","volume":"127","author":"C Salembier","year":"2018","journal-title":"Radiother Oncol"},{"issue":"3","key":"pone.0332603.ref017","doi-asserted-by":"crossref","first-page":"160","DOI":"10.1002\/pro6.1129","article-title":"Guidelines for radiotherapy of prostate cancer (2020 edition)","volume":"5","author":"G Li","year":"2021","journal-title":"Precision Radiat Oncol"},{"issue":"4","key":"pone.0332603.ref018","doi-asserted-by":"crossref","first-page":"990","DOI":"10.1016\/j.ijrobp.2008.12.042","article-title":"Assessing the effect of a contouring protocol on postprostatectomy radiotherapy clinical target volumes and interphysician variation","volume":"75","author":"DM Mitchell","year":"2009","journal-title":"Int J Radiat Oncol Biol Phys"},{"issue":"1","key":"pone.0332603.ref019","doi-asserted-by":"crossref","first-page":"11","DOI":"10.3857\/roj.2017.00080","article-title":"Interobserver variation in target volume for salvage radiotherapy in recurrent prostate cancer patients after radical prostatectomy using CT versus combined CT and MRI: a multicenter study (KROG 13-11)","volume":"36","author":"E Lee","year":"2018","journal-title":"Radiat Oncol J"},{"key":"pone.0332603.ref020","article-title":"Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images","volume-title":"International MICCAI Brainlesion Workshop","author":"A Hatamizadeh","year":"2021"},{"key":"pone.0332603.ref021","article-title":"Monai: An open-source framework for deep learning in healthcare","author":"MJ Cardoso","year":"2022","journal-title":"arXiv preprint arXiv:221102701"},{"key":"pone.0332603.ref022","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.02007","article-title":"Self-supervised pre-training of swin transformers for 3d medical image analysis","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Y Tang","year":"2022"},{"key":"pone.0332603.ref023","article-title":"Swin transformer v2: Scaling up capacity and resolution.","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Z Liu","year":"2022"},{"key":"pone.0332603.ref024","volume-title":"Prescribing, recording and reporting Intensity Modulated Photon Beam Therapy (IMRT)(ICRU report 83)","year":"2010"},{"key":"pone.0332603.ref025","first-page":"1","article-title":"CBCT-based online adaptive radiotherapy of the prostate bed: first clinical experience and comparison to nonadaptive conventional IGRT","author":"J Fischer","year":"2024","journal-title":"Strahlentherapie und Onkologie"},{"key":"pone.0332603.ref026","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1186\/s12880-015-0068-x","article-title":"Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool","volume":"15","author":"AA Taha","year":"2015","journal-title":"BMC Med Imaging"},{"issue":"4","key":"pone.0332603.ref027","doi-asserted-by":"crossref","first-page":"412","DOI":"10.3390\/bioengineering10040412","article-title":"U-Net architecture for prostate segmentation: the impact of loss function on system performance","volume":"10","author":"M Montazerolghaem","year":"2023","journal-title":"Bioengineering (Basel)"},{"issue":"1","key":"pone.0332603.ref028","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1016\/j.meddos.2024.09.002","article-title":"Evaluation of the accuracy of automated segmentation based on deep learning for prostate cancer patients","volume":"50","author":"H Miura","year":"2025","journal-title":"Med Dosim"},{"issue":"7","key":"pone.0332603.ref029","doi-asserted-by":"crossref","first-page":"3194","DOI":"10.1002\/mp.13577","article-title":"Ultrasound prostate segmentation based on multidirectional deeply supervised V-Net","volume":"46","author":"Y Lei","year":"2019","journal-title":"Med Phys"},{"key":"pone.0332603.ref030","article-title":"Automated design of deep learning methods for biomedical image segmentation","author":"F Isensee","year":"2019","journal-title":"arXiv preprint arXiv:190408128"},{"key":"pone.0332603.ref031","doi-asserted-by":"crossref","DOI":"10.1117\/12.3046359","article-title":"Dynamic U-Net: adaptively calibrate features for abdominal multiorgan segmentation","volume-title":"Medical Imaging 2025: Computer-Aided Diagnosis","author":"J Yang","year":"2025"},{"key":"pone.0332603.ref032","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1016\/j.radonc.2022.11.004","article-title":"Patient-specific daily updated deep learning auto-segmentation for MRI-guided adaptive radiotherapy","volume":"177","author":"Z Li","year":"2022","journal-title":"Radiother Oncol"},{"issue":"8","key":"pone.0332603.ref033","doi-asserted-by":"crossref","first-page":"4971","DOI":"10.1002\/mp.15793","article-title":"Personalized auto-segmentation for magnetic resonance imaging-guided adaptive radiotherapy of prostate cancer","volume":"49","author":"X Chen","year":"2022","journal-title":"Med Phys"},{"issue":"7","key":"pone.0332603.ref034","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0308181","article-title":"Deep-learning-based segmentation using individual patient data on prostate cancer radiation therapy","volume":"19","author":"S Jeong","year":"2024","journal-title":"PLoS One"},{"key":"pone.0332603.ref035","doi-asserted-by":"crossref","first-page":"1507806","DOI":"10.3389\/fonc.2024.1507806","article-title":"Clinical feasibility of Ethos auto-segmentation for adaptive whole-breast cancer treatment","volume":"14","author":"J Prunaretty","year":"2024","journal-title":"Front Oncol"},{"issue":"3","key":"pone.0332603.ref036","doi-asserted-by":"crossref","first-page":"1154","DOI":"10.3390\/app10031154","article-title":"Cross-domain data augmentation for deep-learning-based male pelvic organ segmentation in cone beam CT","volume":"10","author":"J L\u00e9ger","year":"2020","journal-title":"Appl Sci"},{"key":"pone.0332603.ref037","first-page":"100796","article-title":"Clinical evaluation of a deep learning CBCT auto-segmentation software for prostate adaptive radiation therapy","volume":"47","author":"L Radici","year":"2024","journal-title":"Clin Transl Radiat Oncol"},{"issue":"7","key":"pone.0332603.ref038","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0305654","article-title":"Biobjective gradient descent for feature selection on high dimension, low sample size data","volume":"19","author":"T Issa","year":"2024","journal-title":"PLoS One"},{"key":"pone.0332603.ref039","doi-asserted-by":"crossref","first-page":"1172135","DOI":"10.3389\/fonc.2023.1172135","article-title":"Feasibility study of adaptive radiotherapy for esophageal cancer using artificial intelligence autosegmentation based on MR-Linac","volume":"13","author":"H Wang","year":"2023","journal-title":"Front Oncol"},{"issue":"1","key":"pone.0332603.ref040","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1038\/s41746-025-01624-z","article-title":"Multicentre evaluation of deep learning CT autosegmentation of the head and neck region for radiotherapy","volume":"8","author":"EPP Pang","year":"2025","journal-title":"NPJ Digit Med"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0332603","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,19]],"date-time":"2025-09-19T21:53:57Z","timestamp":1758318837000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0332603"}},"subtitle":[],"editor":[{"given":"Minsoo","family":"Chun","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,9,19]]},"references-count":40,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2025,9,19]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0332603","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,19]]}}}