{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T10:48:51Z","timestamp":1782989331860,"version":"3.54.5"},"reference-count":55,"publisher":"IOP Publishing","issue":"13","license":[{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/questions\/alternative-author-rights-policies\/"}],"funder":[{"name":"F.R.S - FNRS. T\u00e9l\u00e9vie","award":["7451125"],"award-info":[{"award-number":["7451125"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Phys. Med. Biol."],"published-print":{"date-parts":[[2026,7,14]]},"abstract":"Abstract<\/jats:title>\n \n Objective.<\/jats:italic>\n Artificial intelligence (AI) is transforming segmentation tasks in radiotherapy, but model reliability remains a critical concern, particularly for tumor segmentation. While deep ensembles are among the most reliable uncertainty quantification strategies, their computational cost often drives practitioners toward other approaches. This study explores different sources of model diversity to assess the trade-off between training efficiency and reliability.\n Approach.<\/jats:italic>\n cross-validation ensemble (CVE) served as the baseline, compared against two alternative strategies: Checkpoint ensemble (CPE), a training-efficient approach leveraging temporal diversity from a single training run, and data diversity ensemble (DDE), which enforces strong data diversity through clustering-based subgroup partitioning rather than random data splits. Evaluations were conducted on three 3D tumor segmentation tasks: lung CT (NSCLC), brain MRI (BraTS) and prostate MRI (LUND-PROBE).\n Main results.<\/jats:italic>\n CPE achieves segmentation performance comparable to CVE, with marginal Dice differences (\n \n \n \n <\/jats:tex-math>\n \n \n \u2212<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 1.20% on NSCLC,\n \n \n \n <\/jats:tex-math>\n \n \n \u2212<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 0.27% on BraTS, and +0.05% on LUND-PROBE), while requiring only a single training run. In contrast, DDE exhibits larger performance degradation on NSCLC (\n \n \n \n <\/jats:tex-math>\n \n \n \u2212<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 5.67%), while the differences are smaller on BraTS (\n \n \n \n <\/jats:tex-math>\n \n \n \u2212<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 0.81%) and LUND-PROBE (\n \n \n \n <\/jats:tex-math>\n \n \n \u2212<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n 0.11%). We evaluate reliability by measuring the correlation between Dice and global uncertainty metrics. The results reveal a dataset-dependent pattern: On NSCLC and BraTS, CPE achieves the strongest uncertainty\u2013performance associations, with Spearman correlations between mean foreground entropy and Dice of\n \n \n \n <\/jats:tex-math>\n \n \n |<\/mml:mo>\n \n \u03c1<\/mml:mi>\n \n s<\/mml:mi>\n <\/mml:mrow>\n <\/mml:msub>\n \n |<\/mml:mo>\n <\/mml:mrow>\n =<\/mml:mo>\n 0.85<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n and 0.73, respectively. In contrast, on LUND-PROBE, DDE shows substantially higher correlations (\n \n \n \n <\/jats:tex-math>\n \n \n |<\/mml:mo>\n \n \u03c1<\/mml:mi>\n \n s<\/mml:mi>\n <\/mml:mrow>\n <\/mml:msub>\n \n |<\/mml:mo>\n <\/mml:mrow>\n =<\/mml:mo>\n 0.53<\/mml:mn>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>\n ) compared to CVE and CPE (0.28 and 0.29).\n Significance.<\/jats:italic>\n Our findings highlight that the effectiveness of ensemble diversity for UQ depends on the interplay between dataset characteristics, diversity sources, and evaluation metrics. CPE provides uncertainty estimates comparable to CVE with substantially reduced computational cost, offering a practical trade-off between efficiency and reliability.\n <\/jats:p>","DOI":"10.1088\/1361-6560\/ae7eeb","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T22:55:05Z","timestamp":1781736905000},"page":"135010","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Uncertainty-aware 3D tumor segmentation with deep ensembles: an evaluation of temporal versus data diversity"],"prefix":"10.1088","volume":"71","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-8699-5099","authenticated-orcid":true,"given":"Chuxin","family":"Zhang","sequence":"first","affiliation":[{"name":"Molecular Imaging, Radiation and Oncology (MIRO) Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5848-217X","authenticated-orcid":true,"given":"Dany","family":"Rimez","sequence":"additional","affiliation":[{"name":"Molecular Imaging, Radiation and Oncology (MIRO) Laboratory"},{"name":"Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5218-759X","authenticated-orcid":false,"given":"John","family":"Aldo Lee","sequence":"additional","affiliation":[{"name":"Molecular Imaging, Radiation and Oncology (MIRO) Laboratory"},{"name":"Information and Communication Technologies, Electronics and Applied Mathematics (ICTEAM)"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9485-3076","authenticated-orcid":false,"given":"Ana","family":"Mar\u00eda Barrag\u00e1n Montero","sequence":"additional","affiliation":[{"name":"Molecular Imaging, Radiation and Oncology (MIRO) Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2026,7,2]]},"reference":[{"key":"pmbae7eebbib1","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.inffus.2021.05.008","type":"journal-article","article-title":"A review of uncertainty quantification in deep learning: techniques, applications and challenges","volume":"76","author":"Abdar","year":"2021","journal-title":"Inf. Fusion"},{"key":"pmbae7eebbib2","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2015.PF0M9REI","type":"other","article-title":"Data from NSCLC-radiomics (version 4) [Data set]","author":"Aerts","year":"2014a"},{"key":"pmbae7eebbib3","doi-asserted-by":"publisher","first-page":"4006","DOI":"10.1038\/ncomms5006","type":"journal-article","article-title":"Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach","volume":"5","author":"Aerts","year":"2014b","journal-title":"Nat. Commun."},{"key":"pmbae7eebbib4","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1186\/s12909-023-04698-z","type":"journal-article","article-title":"Revolutionizing healthcare: the role of artificial intelligence in clinical practice","volume":"23","author":"Alowais","year":"2023","journal-title":"BMC Med. Educ."},{"key":"pmbae7eebbib5","doi-asserted-by":"publisher","DOI":"10.7937\/jc8x-9874","type":"other","article-title":"RSNA-ASNR-MICCAI-BraTS-2021 dataset","author":"Baid","year":"2023"},{"key":"pmbae7eebbib6","doi-asserted-by":"publisher","first-page":"689","DOI":"10.21037\/tlcr.2017.09.02","type":"journal-article","article-title":"Magnetic resonance imaging in precision radiation therapy for lung cancer","volume":"6","author":"Bainbridge","year":"2017","journal-title":"Transl. Lung Cancer Res."},{"key":"pmbae7eebbib7","first-page":"pp 376","type":"conference-proceedings","article-title":"Mri brain tumor segmentation and uncertainty estimation using 3d-unet architectures","author":"Ballestar","year":"2020"},{"key":"pmbae7eebbib8","first-page":"1345","type":"journal-article","article-title":"Clustering on the unit hypersphere using von mises-fisher distributions","volume":"6","author":"Banerjee","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"pmbae7eebbib9","doi-asserted-by":"crossref","first-page":"11TR01","DOI":"10.1088\/1361-6560\/ac678a","type":"journal-article","article-title":"Towards a safe and efficient clinical implementation of machine learning in radiation oncology by exploring model interpretability, explainability and data-model dependency","volume":"67","author":"Barrag\u00e1n-Montero","year":"2022","journal-title":"Phys. Med. Biol."},{"key":"pmbae7eebbib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2023.109574","type":"journal-article","article-title":"Benefits of automated gross tumor volume segmentation in head and neck cancer using multi-modality information","volume":"182","author":"Bollen","year":"2023","journal-title":"Radiother. Oncol."},{"key":"pmbae7eebbib11","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1016\/j.ejmp.2021.07.027","type":"journal-article","article-title":"Deep learning methods to generate synthetic CT from MRI in radiotherapy: a literature review","volume":"89","author":"Boulanger","year":"2021","journal-title":"Phys. Medica"},{"key":"pmbae7eebbib12","article-title":"Checkpoint ensembles: Ensemble methods from a single training process","author":"Chen","year":"2017","type":"preprint"},{"key":"pmbae7eebbib13","first-page":"pp 2025","type":"other","article-title":"Deep learning ntcp model for late dysphagia after radiotherapy for head and neck cancer patients based on 3d dose, ct and segmentations","author":"de Vette","year":"2025"},{"key":"pmbae7eebbib14","doi-asserted-by":"publisher","first-page":"297","DOI":"10.2307\/1932409","type":"journal-article","article-title":"Measures of the amount of ecologic association between species","volume":"26","author":"Dice","year":"1945","journal-title":"Ecology"},{"key":"pmbae7eebbib15","first-page":"pp 1","type":"conference-proceedings","article-title":"Ensemble methods in machine learning","author":"Dietterich","year":"2000"},{"key":"pmbae7eebbib16","article-title":"Regulation (eu) 2024\/1689 of the european parliament and of the council\u2013artificial intelligence act","author":"European Commission","year":"2024","type":"other"},{"key":"pmbae7eebbib17","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1098\/rspa.1953.0064","type":"journal-article","article-title":"Dispersion on a sphere","volume":"217","author":"Fisher","year":"1953","journal-title":"Proc. R. Soc. A"},{"key":"pmbae7eebbib18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1175\/1520-0493(1950)078%3C0001:VOFEIT%3E2.0.CO;2","type":"journal-article","article-title":"Verification of forecasts expressed in terms of probability","volume":"78","author":"Glenn","year":"1950","journal-title":"Mon. Weather Rev."},{"key":"pmbae7eebbib19","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1111\/j.2517-6161.1952.tb00104.x","type":"journal-article","article-title":"Rational decisions","volume":"14","author":"Good","year":"1952","journal-title":"J. R. Stat. Soc. B"},{"key":"pmbae7eebbib20","doi-asserted-by":"crossref","DOI":"10.1117\/12.2548722","type":"other","article-title":"An exploration of uncertainty information for segmentation quality assessment","author":"Hoebel","year":"2020"},{"key":"pmbae7eebbib21","article-title":"Snapshot ensembles: train 1, get m for free","author":"Huang","year":"2017","type":"preprint"},{"key":"pmbae7eebbib22","doi-asserted-by":"publisher","first-page":"7369","DOI":"10.1002\/mp.17287","type":"journal-article","article-title":"Can input reconstruction be used to directly estimate uncertainty of a dose prediction u-net model?","volume":"51","author":"Huet-Dastarac","year":"2024a","journal-title":"Med. Phys."},{"key":"pmbae7eebbib23","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110545","type":"journal-article","article-title":"Quantifying and visualising uncertainty in deep learning-based segmentation for radiation therapy treatment planning: what do radiation oncologists and therapists want?","volume":"201","author":"Huet-Dastarac","year":"2024b","journal-title":"Radiother. Oncol."},{"key":"pmbae7eebbib24","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","type":"journal-article","article-title":"nnu-net: a self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"pmbae7eebbib25","first-page":"pp 488","type":"conference-proceedings","article-title":"nnu-net revisited: a call for rigorous validation in 3d medical image segmentation","author":"Isensee","year":"2024"},{"key":"pmbae7eebbib26","first-page":"pp 48","type":"conference-proceedings","article-title":"Assessing reliability and challenges of uncertainty estimations for medical image segmentation","author":"Jungo","year":"2019"},{"key":"pmbae7eebbib27","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/S1076-6332(03)00671-8","type":"journal-article","article-title":"Statistical validation of image segmentation quality based on a spatial overlap index","volume":"11","author":"Kelly","year":"2004","journal-title":"Acad. Radiol."},{"key":"pmbae7eebbib28","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1007\/s10278-021-00460-3","type":"journal-article","article-title":"Novel autosegmentation spatial similarity metrics capture the time required to correct segmentations better than traditional metrics in a thoracic cavity segmentation workflow","volume":"34","author":"Kiser","year":"2021","journal-title":"J. Dig. Imaging"},{"key":"pmbae7eebbib29","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1016\/j.radonc.2015.03.014","type":"journal-article","article-title":"Pet\/ct imaging for target volume delineation in curative intent radiotherapy of non-small cell lung cancer: Iaea consensus report 2014","volume":"116","author":"Konert","year":"2015","journal-title":"Radiother. Oncol."},{"key":"pmbae7eebbib30","type":"conference-proceedings","article-title":"Simple and scalable predictive uncertainty estimation using deep ensembles","volume":"vol 30","author":"Lakshminarayanan","year":"2017"},{"key":"pmbae7eebbib31","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.radonc.2015.06.007","type":"journal-article","article-title":"Primary tumor delineation based on 18fdg pet for locally advanced head and neck cancer treated by chemo-radiotherapy","volume":"116","author":"Leclerc","year":"2016","journal-title":"Radiother. Oncol."},{"key":"pmbae7eebbib32","doi-asserted-by":"publisher","first-page":"e357","DOI":"10.1016\/j.ijrobp.2025.06.2315","type":"journal-article","article-title":"Deep learning-based synthetic ct generation from mri for head and neck cancer radiation therapy planning ASTRO 2025: 67th Annual Meeting","volume":"123","author":"Liefman","year":"2025","journal-title":"Int. J. Rad. Oncol. Biol. Phys."},{"key":"pmbae7eebbib33","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad1a26","type":"journal-article","article-title":"Clinical assessment of deep learning-based uncertainty maps in lung cancer segmentation","volume":"69","author":"Maruccio","year":"2024","journal-title":"Phys. Med. Biol."},{"key":"pmbae7eebbib34","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102914","type":"journal-article","article-title":"Benchmarking common uncertainty estimation methods with histopathological images under domain shift and label noise","volume":"89","author":"Mehrtens","year":"2023","journal-title":"Med. Image Anal."},{"key":"pmbae7eebbib35","first-page":"pp 179","type":"conference-proceedings","article-title":"Mri-based head and neck tumor segmentation using nnu-net with 15-fold cross-validation ensemble","author":"Mol","year":"2024"},{"key":"pmbae7eebbib36","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1109\/TBME.2022.3232730","type":"journal-article","article-title":"Estimating uncertainty in neural networks for cardiac mri segmentation: a benchmark study","volume":"70","author":"Ng","year":"2023","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmbae7eebbib37","doi-asserted-by":"publisher","first-page":"1955","DOI":"10.1109\/TBME.2022.3232730","type":"journal-article","article-title":"Estimating uncertainty in neural networks for cardiac mri segmentation: a benchmark study","volume":"70","author":"Ng","year":"2022","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"pmbae7eebbib38","article-title":"Deep learning to achieve clinically applicable segmentation of head and neck anatomy for radiotherapy","author":"Nikolov","year":"2018","type":"preprint"},{"key":"pmbae7eebbib39","type":"conference-proceedings","article-title":"Measuring calibration in deep learning","volume":"vol 2","author":"Nixon","year":"2019"},{"key":"pmbae7eebbib40","type":"conference-proceedings","article-title":"Can you trust your model\u2019s uncertainty? evaluating predictive uncertainty under dataset shift","volume":"vol 32","author":"Ovadia","year":"2019"},{"key":"pmbae7eebbib41","first-page":"pp 139","type":"conference-proceedings","article-title":"Estimating expected calibration errors","author":"Posocco","year":"2021"},{"key":"pmbae7eebbib42","first-page":"pp 20063","type":"conference-proceedings","article-title":"Uncertainty quantification and deep ensembles","volume":"vol 34","author":"Rahaman","year":"2021"},{"key":"pmbae7eebbib43","doi-asserted-by":"publisher","first-page":"611","DOI":"10.23698\/aida\/lund-probe","type":"journal-article","article-title":"Lund-probe\u2013lund prostate radiotherapy open benchmarking and evaluation dataset","volume":"12","author":"Rogowski","year":"2025a","journal-title":"Sci. Data"},{"key":"pmbae7eebbib44","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.70221","type":"journal-article","article-title":"Impact of deep learning model uncertainty on manual corrections to mri-based auto-segmentation in prostate cancer radiotherapy","volume":"26","author":"Rogowski","year":"2025b","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"pmbae7eebbib45","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ad1cfc","type":"journal-article","article-title":"Transformer cyclegan with uncertainty estimation for cbct based synthetic ct in adaptive radiotherapy","volume":"69","author":"Rusanov","year":"2024","journal-title":"Phys. Med. Biol."},{"key":"pmbae7eebbib46","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1515\/raon-2016-0023","type":"journal-article","article-title":"Uncertainties in target volume delineation in radiotherapy\u2013are they relevant and what can we do about them?","volume":"50","author":"Segedin","year":"2016","journal-title":"Radiol. Oncol."},{"key":"pmbae7eebbib47","type":"journal-article","article-title":"Ai in health care: what do the public and nhs staff think","author":"Thornton","year":"2024","journal-title":"Health Found."},{"key":"pmbae7eebbib48","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","type":"journal-article","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"Topol","year":"2019","journal-title":"Nat. Med."},{"key":"pmbae7eebbib49","article-title":"Health Canada and Mhra. Good machine learning practice for medical device development: guiding principles","author":"U.S. Food and Drug Administration","year":"2023","type":"other"},{"key":"pmbae7eebbib50","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ae110c","type":"journal-article","article-title":"Reliability of uncertainty quantification methods for deep learning auto-segmentation in head and neck organs at risk","volume":"70","author":"van Aalst","year":"2025","journal-title":"Phys. Med. Biol."},{"key":"pmbae7eebbib51","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1016\/s0167-8140(01)00453-4","type":"journal-article","article-title":"Definition of gross tumor volume in lung cancer: inter-observer variability","volume":"62","author":"Van de Steene","year":"2002","journal-title":"Radiother. Oncol."},{"key":"pmbae7eebbib52","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110542","type":"journal-article","article-title":"Artificial intelligence uncertainty quantification in radiotherapy applications- a scoping review","volume":"201","author":"Wahid","year":"2024","journal-title":"Radiother. Oncol."},{"key":"pmbae7eebbib53","doi-asserted-by":"publisher","first-page":"015006","DOI":"10.1117\/1.JMI.5.1.015006","type":"journal-article","article-title":"Family of boundary overlap metrics for the evaluation of medical image segmentation","volume":"5","author":"Yeghiazaryan","year":"2018","journal-title":"J. Med. Imaging"},{"key":"pmbae7eebbib54","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110367","type":"journal-article","article-title":"A novel fully automatic segmentation and counting system for metastatic lymph nodes on multimodal magnetic resonance imaging: evaluation and prognostic implications in nasopharyngeal carcinoma","volume":"197","author":"Zhou","year":"2024","journal-title":"Radiother. Oncol."},{"key":"pmbae7eebbib55","doi-asserted-by":"publisher","DOI":"10.1016\/j.metrad.2023.100003","type":"journal-article","article-title":"A review of uncertainty estimation and its application in medical imaging","volume":"1","author":"Zou","year":"2023","journal-title":"Meta-Radiol."}],"container-title":["Physics in Medicine & Biology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T09:45:33Z","timestamp":1782985533000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/1361-6560\/ae7eeb"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,2]]},"references-count":55,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2026,7,2]]},"published-print":{"date-parts":[[2026,7,14]]}},"URL":"https:\/\/doi.org\/10.1088\/1361-6560\/ae7eeb","relation":{},"ISSN":["0031-9155","1361-6560"],"issn-type":[{"value":"0031-9155","type":"print"},{"value":"1361-6560","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,2]]},"assertion":[{"value":"Uncertainty-aware 3D tumor segmentation with deep ensembles: an evaluation of temporal versus data diversity","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 Institute of Physics and Engineering in Medicine. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2026-02-10","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-06-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2026-07-02","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}