{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T09:50:13Z","timestamp":1791971413923,"version":"4.3.4"},"reference-count":27,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"tdm","delay-in-days":13,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T00:00:00Z","timestamp":1791936000000},"content-version":"vor","delay-in-days":13,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"NIH Office of the Director","award":["1S10OD025200-01A1"],"award-info":[{"award-number":["1S10OD025200-01A1"]}]},{"name":"National Cancer Institute","award":["R01-CA258821"],"award-info":[{"award-number":["R01-CA258821"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,10,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Online adaptive radiotherapy requires fast and accurate delineation of targets and organs at risk on cone-beam computed tomography (CBCT). Although deep learning (DL)-based CBCT auto-segmentation methods have been proposed, their clinical generalizability remains insufficiently validated. This study aimed to externally evaluate a pretrained DL model for lung tumor and esophagus segmentation on CBCT. Originally trained using C-arm linac CBCT images, the model was directly applied to an independent cohort of 12 lung cancer patients, each with 5 CBCT images acquired at a separate institution on an O-ring linac. Rigid propagation of planning CT contours served as a minimal baseline to determine whether the model matched or outperformed conventional rigid registration for gross tumor volume (GTV) and esophagus segmentation using geometric and dosimetric measures. Compared with rigid contour propagation, the model significantly improved GTV segmentation accuracy, with mean Dice similarity coefficient (DSC) increasing from 0.66 to 0.76. Significant differences in GTV D98% were observed between the model-generated contours and the reference contours (50.69 vs 53.58 Gy). The model showed a statistically non-significant decrease in performance compared with previously reported results on its original testing dataset (mean DSC = 0.84), which shared the same distribution as the training dataset. For esophagus segmentation, evaluation of 26 scans from 6 patients showed that the model achieved geometric accuracy within peri-target contour rings comparable to rigid propagation, with mean DSC of 0.72 and 0.70, respectively. Similar esophagus V32Gy values were observed between the model-generated and reference contours (0.06 vs 0.06 cc). Significantly reduced accuracy was observed compared with previously reported results, with mean DSC decreasing from 0.79 to 0.72. These findings highlight that DL-based CBCT auto-segmentation may suffer performance degradation under domain shifts across patient populations, clinical workflows, and imaging systems, emphasizing the necessity of external evaluation beyond the original development environment.<\/jats:p>","DOI":"10.1088\/2057-1976\/aeaf5c","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T22:47:53Z","timestamp":1790981273000},"page":"055049","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["External evaluation of a deep learning-based algorithm for automated lung tumor and esophagus segmentation on CBCT"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1861-0387","authenticated-orcid":true,"given":"Zhehao","family":"Zhang","sequence":"first","affiliation":[{"name":"WashU Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8932-2097","authenticated-orcid":true,"given":"Dean","family":"Hobbis","sequence":"additional","affiliation":[{"name":"WashU Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9642-3515","authenticated-orcid":true,"given":"Jue","family":"Jiang","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aneesh","family":"Rangnekar","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0348-2810","authenticated-orcid":true,"given":"Chloe","family":"Choi","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Waters","sequence":"additional","affiliation":[{"name":"WashU Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4054-5529","authenticated-orcid":true,"given":"Harini","family":"Veeraraghavan","sequence":"additional","affiliation":[{"name":"Memorial Sloan Kettering Cancer Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4109-8177","authenticated-orcid":true,"given":"Geoffrey","family":"Hugo","sequence":"additional","affiliation":[{"name":"WashU Medicine"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,10,14]]},"reference":[{"key":"bpexaeaf5cbib1","first-page":"77","type":"journal-article","article-title":"Making on-line adaptive radiotherapy possible using artificial intelligence and machine learning for efficient daily re-planning","volume":"8","author":"Archambault","year":"2020","journal-title":"Med. Phys. Int. J."},{"key":"bpexaeaf5cbib2","doi-asserted-by":"publisher","first-page":"1701","DOI":"10.1002\/mp.15421","type":"journal-article","article-title":"Improving predictive CTV segmentation on CT and CBCT for cervical cancer by diffeomorphic registration of a prior","volume":"49","author":"Beekman","year":"2022","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib3","doi-asserted-by":"publisher","first-page":"1316","DOI":"10.1200\/JCO.18.00622","type":"journal-article","article-title":"Safety and efficacy of a five-fraction stereotactic body radiotherapy schedule for centrally located non\u2013small-cell lung cancer: NRG oncology\/RTOG 0813 trial","volume":"37","author":"Bezjak","year":"2019","journal-title":"J. Clin. Oncol."},{"key":"bpexaeaf5cbib4","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.3389\/fonc.2019.01192","type":"journal-article","article-title":"Deep learning improved clinical target volume contouring quality and efficiency for postoperative radiation therapy in non-small cell lung cancer","volume":"9","author":"Bi","year":"2019","journal-title":"Front. Oncol."},{"key":"bpexaeaf5cbib5","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1200\/OP.22.00475","type":"journal-article","article-title":"Stereotactic body radiotherapy for the management of early-stage non\u2013small-cell lung cancer: a clinical overview","volume":"19","author":"Buchberger","year":"2023","journal-title":"JCO Oncol. Pract."},{"key":"bpexaeaf5cbib6","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1002\/mp.13396","type":"journal-article","article-title":"Characterization of a prototype rapid kilovoltage x\u2010ray image guidance system designed for a ring shape radiation therapy unit","volume":"46","author":"Cai","year":"2019","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib7","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","type":"journal-article","article-title":"TRIPOD+ AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"bpexaeaf5cbib8","doi-asserted-by":"publisher","first-page":"5130","DOI":"10.1002\/mp.15083","type":"journal-article","article-title":"Multitask 3DCBCT\u2010to\u2010CT translation and organs\u2010at\u2010risk segmentation using physics\u2010based data augmentation","volume":"48","author":"Dahiya","year":"2021","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib9","doi-asserted-by":"publisher","first-page":"1173","DOI":"10.1109\/TBME.2021.3117407","type":"journal-article","article-title":"Domain adaptation for medical image analysis: a survey","volume":"69","author":"Guan","year":"2021","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"bpexaeaf5cbib10","doi-asserted-by":"publisher","first-page":"3084","DOI":"10.1002\/mp.14906","type":"journal-article","article-title":"Deep\u2010learning\u2010based image registration and automatic segmentation of organs\u2010at\u2010risk in cone\u2010beam CT scans from high\u2010dose radiation treatment of pancreatic cancer","volume":"48","author":"Han","year":"2021","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib11","doi-asserted-by":"publisher","first-page":"e278S","DOI":"10.1378\/chest.12-2359","type":"journal-article","article-title":"Treatment of stage I and II non-small cell lung cancer: diagnosis and management of lung cancer: American College of Chest Physicians evidence-based clinical practice guidelines","volume":"143","author":"Howington","year":"2013","journal-title":"Chest"},{"key":"bpexaeaf5cbib12","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1109\/TMI.2022.3154934","type":"journal-article","article-title":"One shot PACS: patient specific anatomic context and shape prior aware recurrent registration-segmentation of longitudinal thoracic cone beam CTs","volume":"41","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"bpexaeaf5cbib13","doi-asserted-by":"publisher","first-page":"2741","DOI":"10.1002\/mp.16846","type":"journal-article","article-title":"A quality assurance framework for routine monitoring of deep learning cardiac substructure computed tomography segmentation models in radiotherapy","volume":"51","author":"Jin","year":"2024","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib14","doi-asserted-by":"publisher","first-page":"5635","DOI":"10.1118\/1.4962933","type":"journal-article","article-title":"Investigating deformable image registration and scatter correction for CBCT\u2010based dose calculation in adaptive IMPT","volume":"43","author":"Kurz","year":"2016","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib15","doi-asserted-by":"publisher","first-page":"1154","DOI":"10.3390\/app10031154","type":"journal-article","article-title":"Cross-domain data augmentation for deep-learning-based male pelvic organ segmentation in cone beam CT","volume":"10","author":"L\u00e9ger","year":"2020","journal-title":"Appl. Sci."},{"key":"bpexaeaf5cbib16","doi-asserted-by":"publisher","first-page":"1947","DOI":"10.1002\/mp.15960","type":"journal-article","article-title":"Segmentation by test\u2010time optimization for CBCT\u2010based adaptive radiation therapy","volume":"50","author":"Liang","year":"2023a","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib17","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acb4d7","type":"journal-article","article-title":"Deep learning based direct segmentation assisted by deformable image registration for cone-beam CT based auto-segmentation for adaptive radiotherapy","volume":"68","author":"Liang","year":"2023b","journal-title":"Phys. Med. Biol."},{"key":"bpexaeaf5cbib18","article-title":"Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy","author":"Nikolov","year":"2018","type":"preprint"},{"key":"bpexaeaf5cbib19","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.ijrobp.2013.05.008","type":"journal-article","article-title":"Adaptive stereotactic body radiation therapy planning for lung cancer","volume":"87","author":"Qin","year":"2013","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"bpexaeaf5cbib20","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.radonc.2022.08.026","type":"journal-article","article-title":"Simulated computed tomography-guided stereotactic adaptive radiotherapy (CT-STAR) for the treatment of locally advanced pancreatic cancer","volume":"175","author":"Schiff","year":"2022a","journal-title":"Radiother. Oncol."},{"key":"bpexaeaf5cbib21","doi-asserted-by":"publisher","first-page":"1022","DOI":"10.1016\/j.ijrobp.2022.06.078","type":"journal-article","article-title":"In silico trial of computed tomography-guided stereotactic adaptive radiation therapy (CT-STAR) for the treatment of abdominal oligometastases","volume":"114","author":"Schiff","year":"2022b","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"bpexaeaf5cbib22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.radonc.2019.11.021","type":"journal-article","article-title":"Clinical evaluation of a full-image deep segmentation algorithm for the male pelvis on cone-beam CT and CT","volume":"145","author":"Schreier","year":"2020","journal-title":"Radiother. Oncol."},{"key":"bpexaeaf5cbib23","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.radonc.2021.05.003","type":"journal-article","article-title":"Metrics to evaluate the performance of auto-segmentation for radiation treatment planning: a critical review","volume":"160","author":"Sherer","year":"2021","journal-title":"Radiother. Oncol."},{"key":"bpexaeaf5cbib24","doi-asserted-by":"publisher","first-page":"4833","DOI":"10.1200\/JCO.2006.07.5937","type":"journal-article","article-title":"Excessive toxicity when treating central tumors in a phase II study of stereotactic body radiation therapy for medically inoperable early-stage lung cancer","volume":"24","author":"Timmerman","year":"2006","journal-title":"J. Clin. Oncol."},{"key":"bpexaeaf5cbib25","doi-asserted-by":"publisher","first-page":"4568","DOI":"10.1002\/mp.13141","type":"journal-article","article-title":"Autosegmentation for thoracic radiation treatment planning: a grand challenge at AAPM 2017","volume":"45","author":"Yang","year":"2018","journal-title":"Med. Phys."},{"key":"bpexaeaf5cbib26","doi-asserted-by":"publisher","first-page":"i120","DOI":"10.1093\/jrr\/rrt045","type":"journal-article","article-title":"Performance validation of deformable image registration in the pelvic region","volume":"54","author":"Zambrano","year":"2013","journal-title":"J. Radiat. Res."},{"key":"bpexaeaf5cbib27","doi-asserted-by":"publisher","first-page":"7979","DOI":"10.1088\/0031-9155\/58\/22\/7979","type":"journal-article","article-title":"Deformable image registration of CT and truncated cone-beam CT for adaptive radiation therapy","volume":"58","author":"Zhen","year":"2013","journal-title":"Phys. Med. Biol."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T09:06:15Z","timestamp":1791968775000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/aeaf5c"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":27,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2026,10,14]]},"published-print":{"date-parts":[[2026,10,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/aeaf5c","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"assertion":[{"value":"External evaluation of a deep learning-based algorithm for automated lung tumor and esophagus segmentation on CBCT","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":"2026-03-24","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-02","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-10-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}