{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T22:19:51Z","timestamp":1793830791715,"version":"4.6.1"},"reference-count":24,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"vor","delay-in-days":9,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T00:00:00Z","timestamp":1775779200000},"content-version":"tdm","delay-in-days":9,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Purpose<\/jats:italic>\n                    . To investigate how annotation consistency influences deep learning-based auto-contouring performance for organs-at-risk (OARs) in nasopharyngeal cancer radiotherapy.\n                    <jats:italic>Methods<\/jats:italic>\n                    . We evaluated CT scans from 1,301 nasopharyngeal carcinoma patients: 65 contoured by Physician A, 76 by Physician B, and 1,160 by heterogeneous multi-physician teams. Three cohorts (50 samples each for Physicians A\/B; 1,000 for multi-physician) with standardized U-Net training protocols generated Models A, B, and C. Model C underwent physician-specific fine-tuning. Performance was quantified via Dice similarity coefficients (DSC) against ground-truth contours across 14 critical OARs.\n                    <jats:italic>Results<\/jats:italic>\n                    . Each model achieved peak accuracy on physician-matched test data. Critically, small-consistency models (A\/B) outperformed large-heterogeneous Model C on target cohorts (Model A: 0.777 versus Model C\u2019s 0.743 on Test A; Model B: 0.806 versus 0.765 on Test B). Physician-specific fine-tuning closed institutional data gaps, boosting Model C\u2019s DSC to 0.795 (+7.08% versus original) on Test A and 0.814 (+6.32%) on Test B\u2014surpassing both original Model C and dedicated small-data models (Model A: +2.39%; Model B: +0.97%).\n                    <jats:italic>Conclusion<\/jats:italic>\n                    . Annotation consistency supersedes dataset scale as the primary performance driver for OAR auto-contouring. Small high-consistency datasets enable optimal native model accuracy, whereas fine-tuning large pre-trained models with targeted physician data closes domain adaptation gaps and delivers state-of-the-art segmentation, advancing precision radiotherapy for head and neck oncology.\u200b\n                  <\/jats:p>","DOI":"10.1088\/2057-1976\/ae596e","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T22:48:36Z","timestamp":1774997316000},"page":"025066","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["The impact of data consistency on deep learning models for nasopharyngeal cancer organ auto-segmentation"],"prefix":"10.1088","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-7256-7005","authenticated-orcid":true,"given":"Yingtao","family":"Fang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9012-6605","authenticated-orcid":true,"given":"Jiazhou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiayun","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaosu","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2940-1479","authenticated-orcid":true,"given":"Yang","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Mi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shenlun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanju","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4409-6804","authenticated-orcid":true,"given":"Weigang","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,4,10]]},"reference":[{"key":"bpexae596ebib1","doi-asserted-by":"publisher","first-page":"338","DOI":"10.1016\/S0140-6736(24)02319-5","type":"journal-article","article-title":"Radiotherapy toxicities: mechanisms, management, and future directions","volume":"405","author":"Verginadis","year":"2025","journal-title":"Lancet"},{"key":"bpexae596ebib2","doi-asserted-by":"publisher","first-page":"140","DOI":"10.1016\/j.radonc.2014.03.024","type":"journal-article","article-title":"Estimating the demand for radiotherapy from the evidence: a review of changes from 2003 to 2012","volume":"112","author":"Barton","year":"2014","journal-title":"Radiother. Oncol."},{"key":"bpexae596ebib3","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1016\/j.ijrobp.2015.03.030","type":"journal-article","article-title":"Expert consensus contouring guidelines for intensity modulated radiation therapy in esophageal and gastroesophageal junction cancer","volume":"92","author":"Wu","year":"2015","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"bpexae596ebib4","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13470","type":"journal-article","article-title":"Deep learning-based auto-segmentation of clinical target volumes for radiotherapy treatment of cervical cancer","volume":"23","author":"Ma","year":"2022","journal-title":"J Appl Clin Med Phys."},{"key":"bpexae596ebib5","doi-asserted-by":"publisher","first-page":"1206","DOI":"10.3390\/cancers16061206","type":"journal-article","article-title":"Adaptive radiotherapy: next-generation radiotherapy","volume":"16","author":"Dona Lemus","year":"2024","journal-title":"Cancers (Basel)"},{"key":"bpexae596ebib6","doi-asserted-by":"publisher","first-page":"e929","DOI":"10.1002\/mp.14320","type":"journal-article","article-title":"Auto-segmentation of organs at risk for head and neck radiotherapy planning: from atlas-based to deep learning methods","volume":"47","author":"Vrtovec","year":"2020","journal-title":"Med. Phys."},{"key":"bpexae596ebib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110410","type":"journal-article","article-title":"HaN-Seg: The head and neck organ-at-risk CT and MR segmentation challenge","volume":"198","author":"Podobnik","year":"2024","journal-title":"Radiother. Oncol."},{"key":"bpexae596ebib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2025.110914","type":"journal-article","article-title":"Deep learning-based auto-contouring of organs\/structures-at-risk for pediatric upper abdominal radiotherapy","volume":"208","author":"Ding","year":"2025","journal-title":"Radiother. Oncol."},{"key":"bpexae596ebib9","doi-asserted-by":"publisher","first-page":"185012","DOI":"10.1088\/1361-6560\/ac2206","type":"journal-article","article-title":"The impact of training sample size on deep learning-based organ auto-segmentation for head-and-neck patients","volume":"66","author":"Fang","year":"2021","journal-title":"Phys. Med. Biol."},{"key":"bpexae596ebib10","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.semcancer.2022.08.005","type":"journal-article","article-title":"Artificial intelligence in radiotherapy","volume":"86","author":"Li","year":"2022","journal-title":"Semin Cancer Biol."},{"key":"bpexae596ebib11","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110332","type":"journal-article","article-title":"Generalizability of deep learning in organ-at-risk segmentation: a transfer learning study in cervical brachytherapy","volume":"197","author":"Ni","year":"2024","journal-title":"Radiother. Oncol."},{"key":"bpexae596ebib12","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1002\/mp.15507","type":"journal-article","article-title":"General and custom deep learning autosegmentation models for organs in head and neck, abdomen, and male pelvis","volume":"49","author":"Amjad","year":"2022","journal-title":"Med. Phys."},{"key":"bpexae596ebib13","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1016\/j.prro.2023.03.011","type":"journal-article","article-title":"First report on physician assessment and clinical acceptability of custom-retrained artificial intelligence models for clinical target volume and organs-at-risk auto-delineation for postprostatectomy patients","volume":"13","author":"Hobbis","year":"2023","journal-title":"Pract. Radiat. Oncol."},{"key":"bpexae596ebib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102195","type":"journal-article","article-title":"PSA-Net: deep learning-based physician style-aware segmentation network for postoperative prostate cancer clinical target volumes","volume":"121","author":"Balagopal","year":"2021","journal-title":"Artif. Intell. Med."},{"key":"bpexae596ebib15","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/j.radonc.2015.07.041","type":"journal-article","article-title":"CT-based delineation of organs at risk in the head and neck region: DAHANCA, EORTC, GORTEC, HKNPCSG, NCIC CTG, NCRI, NRG Oncology and TROG consensus guidelines","volume":"117","author":"Brouwer","year":"2015","journal-title":"Radiother. Oncol."},{"key":"bpexae596ebib16","first-page":"234","type":"book","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"bpexae596ebib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110615","type":"journal-article","article-title":"Automated segmentation in planning-CT for breast cancer radiotherapy: a review of recent advances","volume":"202","author":"Smine","year":"2025","journal-title":"Radiother. Oncol."},{"key":"bpexae596ebib18","doi-asserted-by":"publisher","first-page":"2560","DOI":"10.1002\/mp.12918","type":"journal-article","article-title":"Technical note: a deep learning-based autosegmentation of rectal tumors in MR images","volume":"45","author":"Wang","year":"2018","journal-title":"Med. Phys."},{"key":"bpexae596ebib19","author":"Chollet","year":"2015","type":"other"},{"key":"bpexae596ebib20","volume":"1","author":"Goodfellow","year":"2016","type":"book"},{"key":"bpexae596ebib21","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1186\/s13014-024-02463-0","type":"journal-article","article-title":"Localized fine-tuning and clinical evaluation of deep-learning based auto-segmentation (DLAS) model for clinical target volume (CTV) and organs-at-risk (OAR) in rectal cancer radiotherapy","volume":"19","author":"Geng","year":"2024","journal-title":"Radiat Oncol."},{"key":"bpexae596ebib22","doi-asserted-by":"publisher","first-page":"6421","DOI":"10.1002\/mp.16437","type":"journal-article","article-title":"Impact of imperfection in medical imaging data on deep learning-based segmentation performance: an experimental study using synthesized data","volume":"50","author":"G\u00fcne\u015f","year":"2023","journal-title":"Med. Phys."},{"key":"bpexae596ebib23","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acc309","type":"journal-article","article-title":"Accurate segmentation of head and neck radiotherapy CT scans with 3D CNNs: consistency is key","volume":"68","author":"Henderson","year":"2023","journal-title":"Phys. Med. Biol."},{"key":"bpexae596ebib24","doi-asserted-by":"publisher","first-page":"4767","DOI":"10.1002\/mp.16997","type":"journal-article","article-title":"Transfer learning for auto-segmentation of 17 organs-at-risk in the head and neck: Bridging the gap between institutional and public datasets","volume":"51","author":"Clark","year":"2024","journal-title":"Med. Phys."}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T14:25:37Z","timestamp":1775831137000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae596e"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,1]]},"references-count":24,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,4,10]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae596e","relation":{},"ISSN":["2057-1976"],"issn-type":[{"value":"2057-1976","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,1]]},"assertion":[{"value":"The impact of data consistency on deep learning models for nasopharyngeal cancer organ auto-segmentation","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":"2025-12-10","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-03-31","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-04-10","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}