{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T11:43:20Z","timestamp":1768391000192,"version":"3.49.0"},"reference-count":17,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Anatomical segmentation is one of the biggest sources of uncertainty in the online adaptive radiotherapy workflow. The aim of this study was to investigate the relation between the estimated uncertainty in deep learning (DL)-based segmentation and the correctness of the segmentations. In addition, the ability to capture out-of-distribution (OOD) data with uncertainty estimation was tested.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>The Monte Carlo dropout method was applied to estimate the uncertainty of a DL model for magnetic resonance (MR)-guided radiotherapy prostate cancer images, trained to segment the clinical target volume (CTV), bladder, and rectum. The training\/validation set consisted of 151 T2 MR scans from 26 patients, while the test set consisted of 65 scans from 10 patients. Predictive entropy (PE) was used to capture predictive (model and data) uncertainty. The PE distributions for correct and incorrect predictions were used to find a threshold value. Predicted segmentations with PE values above this threshold value were allocated to the \u201cuncertain group,\u201d and those below to the \u201ccertain group.\u201d Dice scores were computed for both groups, using manual segmentations as ground truth. Mutual information (MI) was additionally used to capture epistemic (model) uncertainty as a means to separate in-distribution (ID) from OOD data. Balanced steady-state free precession MRI scans of 10 healthy volunteers were used as OOD data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The segmentation model obtained Dice scores of 85.7% for the CTV, 94.8% for the bladder, and 86.6% for the rectum. The highest PE values were found at the segmentation borders. Higher PE threshold values resulted in better separation between the certain and uncertain groups. This shows the ability to detect incorrect predictions with uncertainty estimation. A 100% separation between ID and OOD data was achieved with MI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Uncertainty estimation from a DL-based segmentation model was seen to correlate with Dice scores for segmentation of MR-guided radiotherapy prostate cancer images. This implies that uncertainty estimation could be used to label the quality of the segmentations in the online adaptive radiotherapy workflow. Preliminary results showed that uncertainty estimation could be used to distinguish between ID and OOD data.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2025.1637198","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T06:35:37Z","timestamp":1768372537000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing online adaptive radiotherapy with uncertainty based segmentation error and out-of-distribution detection"],"prefix":"10.3389","volume":"15","author":[{"given":"Marissa","family":"van Lente","sequence":"first","affiliation":[{"name":"Department of Biomedical Engineering, Eindhoven University of Technology","place":["Eindhoven, Netherlands"]},{"name":"Department of Medical Imaging, Radboud University Medical Center","place":["Nijmegen, Netherlands"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josien","family":"Pluim","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Eindhoven University of Technology","place":["Eindhoven, Netherlands"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Fransson","sequence":"additional","affiliation":[{"name":"Department of Medical Physics, Uppsala University Hospital","place":["Uppsala, Sweden"]},{"name":"Department of Surgical Sciences, Uppsala University","place":["Uppsala, Sweden"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robin","family":"Strand","sequence":"additional","affiliation":[{"name":"Department of Surgical Sciences, Uppsala University","place":["Uppsala, Sweden"]},{"name":"Department of Information Technology, Uppsala University","place":["Uppsala, Sweden"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Tilly","sequence":"additional","affiliation":[{"name":"Department of Medical Physics, Uppsala University Hospital","place":["Uppsala, Sweden"]},{"name":"Department of Immunology, Genetics and Pathology, Uppsala University","place":["Uppsala, Sweden"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1515\/raon-2016-0023","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":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1811.12709","article-title":"Evaluating bayesian deep learning methods for semantic segmentation","author":"Mukhoti","year":"2018","journal-title":"arXiv preprint arXiv:1811.12709"},{"key":"B3","unstructured":"Gal\n              Y\n            \n          \n          Cambridge, United Kingdom\n          University of Cambridge\n          Uncertainty in Deep Learning\n          \n          2016"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1506.02157","article-title":"Dropout as a bayesian approximation","author":"Gal","year":"2016","journal-title":"Appendix"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1207.0580","article-title":"Improving neural networks by preventing co-adaptation of feature detectors","author":"Hinton","year":"2012"},{"key":"B6","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2021.100658","article-title":"Using spatial probability maps to highlight potential inaccuracies in deep learning-based contours: facilitating online adaptive radiation therapy","volume":"6","author":"van Rooij","year":"2021","journal-title":"Adv Radiat Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2023.109794","article-title":"Clinical target volume delineation quality assurance for mri-guided prostate radiotherapy using deep learning with uncertainty estimation","volume":"186","author":"Min","year":"2023","journal-title":"Radiotherapy Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110542","article-title":"Artificial intelligence uncertainty quantification in radiotherapy applications- a scoping review","volume":"201","author":"Wahid","year":"2024","journal-title":"Radiotherapy Oncol"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.3390\/s21217241","article-title":"Monte carlo dropout for uncertainty estimation and motor imagery classification","volume":"21","author":"Milan\u00e9s-Hermosilla","year":"2021","journal-title":"Sensors"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1803.08533","article-title":"Understanding measures of uncertainty for adversarial example detection","author":"Smith","year":"2018","journal-title":"arXiv preprint arXiv:1803.08533"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.05.010","article-title":"Artificial intelligence in magnetic resonance guided radiotherapy: Medical and physical considerations on state of art and future perspectives","volume":"85","author":"Cusumano","year":"2021","journal-title":"Physica Med"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07832","article-title":"Concrete dropout","volume":"30","author":"Gal","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: A method for stochastic optimization","author":"Diederik","year":"2014","journal-title":"arXiv preprint arXiv:1412.6980"},{"key":"B15","doi-asserted-by":"publisher","first-page":"e230275","DOI":"10.1148\/radiol.230275","article-title":"Prediction variability to identify reduced ai performance in cancer diagnosis at mri and ct","volume":"308","author":"Alves","year":"2023","journal-title":"Radiology"},{"key":"B16","article-title":"On pitfalls in ood detection: Predictive entropy considered harmful","author":"Kirsch","year":"2021","journal-title":"Presented at ICML 2021 Workshop Uncertainty Robustness Deep Learn"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2019.11.006","article-title":"Deep learning-based auto-segmentation of targets and organs-at-risk for magnetic resonance imaging only planning of prostate radiotherapy","volume":"12","author":"Elguindi","year":"2019","journal-title":"Phys Imaging Radiat Oncol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1637198\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T06:35:39Z","timestamp":1768372539000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2025.1637198\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":17,"alternative-id":["10.3389\/fonc.2025.1637198"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2025.1637198","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]},"article-number":"1637198"}}