{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T12:36:15Z","timestamp":1773923775361,"version":"3.50.1"},"reference-count":34,"publisher":"IOP Publishing","issue":"6","license":[{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T00:00:00Z","timestamp":1773878400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"NPL, UK"},{"name":"Mount Vernon Marie Curie Research Wing Trust"},{"DOI":"10.13039\/501100000272","name":"National Institute for Health and Care Research","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"crossref"}]},{"name":"EPSRC-funded UCL Centre for Doctoral Training in Intelligent, Integrated Imaging in Healthcare","award":["EP\/S021930\/1"],"award-info":[{"award-number":["EP\/S021930\/1"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,3,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    <jats:italic>Objective.<\/jats:italic>\n                    As part of treatment planning for radiotherapy, the organs at risk (OARs) are delineated on the patient\u2019s CT scan. This work aims to develop a method to measure variability in OAR delineations and detect errors.\n                    <jats:italic>Approach.<\/jats:italic>\n                    A normative modelling approach was implemented by training a variational autoencoder (VAE) on a dataset of images and delineations to model the \u201cacceptable\u201d variability distribution. The trained VAE was then used to reconstruct unseen cases. Disagreements between input and reconstructed delineations highlighted regions where the input deviated from the training distribution. This approach was validated by evaluating the reconstructions of spinal cord and brainstem delineations where common clinical errors had been introduced.\n                    <jats:italic>Main results.<\/jats:italic>\n                    Results showed that the model successfully detected errors, even when only a few voxels or slices were added or removed. Distance to agreement maps were generated to quantify the magnitude of the disagreements in misclassified regions. These results were further validated by manually evaluating some of the test cases.\n                    <jats:italic>Significance.<\/jats:italic>\n                    This tool has the potential of assisting clinicians in reviewing and validating OAR delineations.\n                  <\/jats:p>","DOI":"10.1088\/1361-6560\/ae50a7","type":"journal-article","created":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T22:52:37Z","timestamp":1773269557000},"page":"065005","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Detection of errors in organs at risk delineations for radiotherapy for clinical trial reviews"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1838-1273","authenticated-orcid":true,"given":"C","family":"Dronne","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2287-8212","authenticated-orcid":true,"given":"C H","family":"Clark","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9341-2818","authenticated-orcid":true,"given":"X","family":"Loizeau","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0645-4703","authenticated-orcid":true,"given":"E","family":"Miles","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8323-9567","authenticated-orcid":false,"given":"P","family":"Hoskin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4922-0093","authenticated-orcid":true,"given":"J R","family":"McClelland","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"pmbae50a7bib1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.14513","type":"journal-article","article-title":"Automated confidence estimation in deep learning auto-segmentation for brain organs at risk on MRI for radiotherapy","volume":"25","author":"Alzahrani","year":"2024","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbae50a7bib2","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-32245-8_14","type":"preprint","article-title":"PHiSeg: capturing uncertainty in medical image segmentation","author":"Baumgartner","year":"2019"},{"key":"pmbae50a7bib3","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/1748-717X-7-32","type":"journal-article","article-title":"3D Variation in delineation of head and neck organs at risk","volume":"7","author":"Brouwer","year":"2012","journal-title":"Radiat. Oncol."},{"key":"pmbae50a7bib4","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":"pmbae50a7bib5","article-title":"MONAI: An open-source framework for deep learning in healthcare","author":"Cardoso","year":"2022","type":"preprint"},{"key":"pmbae50a7bib6","doi-asserted-by":"publisher","first-page":"1048","DOI":"10.1118\/1.4906197","type":"journal-article","article-title":"Automated contouring error detection based on supervised geometric attribute distribution models for radiation therapy: a general strategy","volume":"42","author":"Chen","year":"2015","journal-title":"Med. Phys."},{"key":"pmbae50a7bib7","doi-asserted-by":"publisher","first-page":"524","DOI":"10.3389\/fonc.2020.00524","type":"journal-article","article-title":"CNN-Based quality assurance for automatic segmentation of breast cancer in radiotherapy","volume":"10","author":"Chen","year":"2020","journal-title":"Front. Oncol."},{"key":"pmbae50a7bib8","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2024.102403","type":"journal-article","article-title":"Uncertainty estimation using a 3D probabilistic U-Net for segmentation with small radiotherapy clinical trial datasets","volume":"116","author":"Chlap","year":"2024","journal-title":"Comput. Med. Imaging Graph."},{"key":"pmbae50a7bib9","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1016\/j.semradonc.2022.06.011","type":"journal-article","article-title":"Quality assurance for AI-based applications in radiation therapy","volume":"32","author":"Claessens","year":"2022","journal-title":"Semin. Radiat. Oncol."},{"key":"pmbae50a7bib10","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1213068","type":"journal-article","article-title":"A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy","volume":"13","author":"Doolan","year":"2023","journal-title":"Front. Oncol."},{"key":"pmbae50a7bib11","doi-asserted-by":"publisher","first-page":"2715","DOI":"10.1002\/mp.16299","type":"journal-article","article-title":"Contouring quality assurance methodology based on multiple geometric features against deep learning auto-segmentation","volume":"50","author":"Duan","year":"2023","journal-title":"Med. Phys."},{"key":"pmbae50a7bib12","article-title":"Dropout as a bayesian approximation: representing model uncertainty in deep learning","author":"Gal","year":"2016","type":"preprint"},{"key":"pmbae50a7bib13","first-page":"319","type":"book","article-title":"Automatic identification of segmentation errors for radiotherapy using geometric learning","author":"Henderson","year":"2022"},{"key":"pmbae50a7bib14","doi-asserted-by":"publisher","first-page":"2089","DOI":"10.1002\/mp.12835","type":"journal-article","article-title":"Quality assurance tool for organ at risk delineation in radiation therapy using a parametric statistical approach","volume":"45","author":"Hui","year":"2018","journal-title":"Med. Phys."},{"key":"pmbae50a7bib15","doi-asserted-by":"publisher","first-page":"2816","DOI":"10.1200\/JCO.20.03697","type":"journal-article","article-title":"Randomized study on dose escalation in definitive chemoradiation for patients with locally advanced esophageal cancer (ARTDECO Study)","volume":"39","author":"Hulshof","year":"2021","journal-title":"J. Clin. Oncol."},{"key":"pmbae50a7bib16","first-page":"492","type":"book","article-title":"CRISP - Reliable uncertainty estimation for medical image segmentation","author":"Judge","year":"2022"},{"key":"pmbae50a7bib17","article-title":"What uncertainties do we need in bayesian deep learning for computer vision?","author":"Kendall","year":"2017","type":"preprint"},{"key":"pmbae50a7bib18","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2017","type":"preprint"},{"key":"pmbae50a7bib19","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2022","type":"preprint"},{"key":"pmbae50a7bib20","article-title":"A probabilistic U-Net for segmentation of ambiguous images","author":"Kohl","year":"2019","type":"preprint"},{"key":"pmbae50a7bib21","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","author":"Lakshminarayanan","year":"2017","type":"preprint"},{"key":"pmbae50a7bib22","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1162\/neco.1992.4.3.448","type":"journal-article","article-title":"A practical bayesian framework for backpropagation networks","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Comput."},{"key":"pmbae50a7bib23","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.radonc.2020.05.038","type":"journal-article","article-title":"Organ at risk delineation for radiation therapy clinical trials: Global Harmonization Group consensus guidelines","volume":"150","author":"Mir","year":"2020","journal-title":"Radiother. Oncol."},{"key":"pmbae50a7bib24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/0284186X.2023.2256958","type":"journal-article","article-title":"Consistency in contouring of organs at risk by artificial intelligence vs oncologists in head and neck cancer patients","volume":"0","author":"Nielsen","year":"2023","journal-title":"Acta Oncol."},{"key":"pmbae50a7bib25","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.ejca.2018.08.006","type":"journal-article","article-title":"Results of a multicentre randomised controlled trial of cochlear-sparing intensity-modulated radiotherapy versus conventional radiotherapy in patients with parotid cancer (COSTAR; CRUK\/08\/004)","volume":"103","author":"Nutting","year":"2018","journal-title":"Eur. J. Cancer"},{"key":"pmbae50a7bib26","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01042","type":"preprint","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"pmbae50a7bib27","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021200218","type":"journal-article","article-title":"Use of variational autoencoders with unsupervised learning to detect incorrect organ segmentations at CT","volume":"3","author":"Sandfort","year":"2021","journal-title":"Radiol.: Artif. Intell."},{"key":"pmbae50a7bib28","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1007\/978-3-031-46914-5_10","type":"conference-proceedings","author":"Sree","year":"2023","edition":"ed"},{"key":"pmbae50a7bib29","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.tipsro.2019.05.001","type":"journal-article","article-title":"Assessment of contour variability in target volumes and organs at risk in lung cancer radiotherapy","volume":"10","author":"Tsang","year":"2019","journal-title":"Tech. Innovations Patient Support Radiat. Oncol."},{"key":"pmbae50a7bib30","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1186\/s13014-020-01677-2","type":"journal-article","article-title":"Interobserver variability in organ at risk delineation in head and neck cancer","volume":"16","author":"van der Veen","year":"2021","journal-title":"Radiat. Oncol."},{"key":"pmbae50a7bib31","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024","type":"journal-article","article-title":"TotalSegmentator: Robust Segmentation of 104 Anatomic Structures in CT Images","volume":"5","author":"Wasserthal","year":"2023","journal-title":"Radiol.: Artif. Intell."},{"key":"pmbae50a7bib32","doi-asserted-by":"publisher","DOI":"10.7937\/J47W-NM11","type":"other","article-title":"Computed tomography images from large head and neck cohort (RADCURE)","author":"Welch","year":"2024"},{"key":"pmbae50a7bib33","article-title":"Quality assurance of organs-at-risk delineation in radiotherapy","author":"Zhao","year":"2024","type":"preprint"},{"key":"pmbae50a7bib34","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2023.100003","type":"preprint","article-title":"A review of uncertainty estimation and its application in medical imaging","author":"Zou","year":"2023"}],"container-title":["Physics in Medicine &amp; Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T08:42:00Z","timestamp":1773909720000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae50a7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,19]]},"references-count":34,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2026,3,19]]},"published-print":{"date-parts":[[2026,3,28]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae50a7","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,19]]},"assertion":[{"value":"Detection of errors in organs at risk delineations for radiotherapy for clinical trial reviews","name":"article_title","label":"Article Title"},{"value":"Physics in Medicine & Biology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2026 The Author(s). Published on behalf of Institute of Physics and Engineering in Medicine by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-07-07","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-03-11","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-03-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}