{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T18:10:12Z","timestamp":1790964612348,"version":"4.1.0"},"reference-count":35,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T00:00:00Z","timestamp":1734566400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008672","name":"Wilhelm Sander-Stiftung","doi-asserted-by":"publisher","award":["2019.162.2"],"award-info":[{"award-number":["2019.162.2"]}],"id":[{"id":"10.13039\/100008672","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Manual contour corrections during fractionated magnetic resonance (MR)\u2010guided radiotherapy (MRgRT) are time\u2010consuming. Conventional population models for deep learning auto\u2010segmentation might be suboptimal for MRgRT at MR\u2010Linacs since they do not incorporate manual segmentation from treatment planning and previous fractions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>In this work, we investigate patient\u2010specific (PS) auto\u2010segmentation methods leveraging expert\u2010segmented planning and prior fraction MR images (MRIs) to improve auto\u2010segmentation on consecutive treatment\u00a0days.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>\n                      Data from 151 abdominal cancer patients treated at a 0.35\u00a0T MR\u2010Linac (151 planning and 215 fraction MRIs) were included. Population baseline models (BMs) were trained on 107 planning MRIs for one\u2010class segmentation of the aorta, bowel, duodenum, kidneys, liver, spinal canal, and stomach. PS models were obtained by fine\u2010tuning the BMs using the planning MRI (). Maximal improvement by continuously updating the PS models was investigated by adding the first four out of five fraction MRIs (). Similarly, PS models without BM were trained ( and ). All hyperparameters were optimized using 23 patients, and the methods were tested on the remaining 21 patients. Evaluation involved Dice similarity coefficient (DSC), average () and the 95\n                      <jats:sup>th<\/jats:sup>\n                      percentile (HD\n                      <jats:sub>95<\/jats:sub>\n                      ) Hausdorff distance. A qualitative contour assessment by a radiation oncologist was performed for BM, , and .\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>and  networks had the best geometric performance.  and BMs showed similar DSC and HDs values, however  models outperformed BMs.  predictions scored the best in the qualitative evaluation, followed by the BMs and \u00a0models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Personalized auto\u2010segmentation models outperformed the population BMs. In most cases,  delineations were judged to be directly usable for treatment adaptation without further corrections, suggesting a potential time saving during fractionated\u00a0treatment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.17580","type":"journal-article","created":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T08:23:31Z","timestamp":1734596611000},"page":"2295-2304","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Personalized deep learning auto\u2010segmentation models for adaptive fractionated magnetic resonance\u2010guided radiation therapy of the abdomen"],"prefix":"10.1002","volume":"52","author":[{"given":"Maria","family":"Kawula","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sebastian","family":"Marschner","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengtao","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marvin F.","family":"Ribeiro","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanie","family":"Corradini","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claus","family":"Belka","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"},{"name":"German Cancer Consortium (DKTK) partner site Munich, a partnership between DKFZ and LMU University Hospital Munich Munich Germany"},{"name":"Bavarian Cancer Research Center (BZKF) Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Landry","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Kurz","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, LMU University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,12,19]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.12.011"},{"key":"e_1_2_8_3_1","first-page":"98","article-title":"Technical design and concept of a 0.35 T MR\u2010Linac","volume":"18","author":"Kl\u00fcter S","year":"2019","journal-title":"Clin Transl Oncol"},{"key":"e_1_2_8_4_1","first-page":"54","article-title":"Adaptive radiotherapy: the Elekta Unity MR\u2010linac concept","volume":"18","author":"Winkel D","year":"2019","journal-title":"Clin Transl Oncol"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2018.08.010"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-019-1308-y"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.zemedi.2023.05.001"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.07.001"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13221"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-023-02330-4"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2021.12.003"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2018.08.001"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16056"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15793"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2022.06.001"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2022.11.004"},{"key":"e_1_2_8_17_1","unstructured":"SharpGC LiR WolfgangJ et\u00a0al.Plastimatch: an open source software suite for radiotherapy image processing. In:Proceedings of the XVI'th International Conference on the use of Computers in Radiotherapy (ICCR).IEEE;2010."},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2022-068906"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2020.09.005"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/acafd4"},{"key":"e_1_2_8_21_1","unstructured":"CardosoMJ et\u00a0al.MONAI: An open\u2010source framework for deep learning in healthcare. arXiv preprint arXiv:2211.027012022."},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"KerfootE CloughJ OksuzI LeeJ KingAP SchnabelJA.Left\u2010ventricle quantification using residual U\u2010Net. In:International Workshop on Statistical Atlases and Computational Models of the Heart.Springer;2018:371\u2010380.","DOI":"10.1007\/978-3-030-12029-0_40"},{"key":"e_1_2_8_23_1","unstructured":"UlyanovD VedaldiA LempitskyV.Instance Normalization: The Missing Ingredient for Fast Stylization.arXiv preprint arXiv:1607.080222016."},{"key":"e_1_2_8_24_1","doi-asserted-by":"crossref","unstructured":"DingB QianH ZhouJ.Activation functions and their characteristics in deep neural networks. In:2018 Chinese control and decision conference (CCDC).IEEE;2018:1836\u20131841.","DOI":"10.1109\/CCDC.2018.8407425"},{"key":"e_1_2_8_25_1","unstructured":"BridleJS.Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters. In:Proceedings of the 2nd International Conference on Neural Information Processing Systems.MIT Press;1990:211\u2013217."},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiS\u2010A.V\u2010net: fully convolutional neural networks for volumetric medical image segmentation. In:2016 fourth international conference on 3D vision (3DV).IEEE;2016:565\u2010571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_8_27_1","first-page":"675","article-title":"The use of ranks to avoid the assumption of normality implicit in the analysis of variance","volume":"32","author":"Friedman M","year":"1937","journal-title":"J Stat Data Sci Educ"},{"key":"e_1_2_8_28_1","volume-title":"Distribution\u2010free multiple comparisons","author":"Nemenyi PB","year":"1963"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-020-01008-z"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.230024"},{"key":"e_1_2_8_31_1","unstructured":"D'AntonoliTA BergerLK IndrakantiAK et\u00a0al.TotalSegmentator MRI: Sequence\u2010Independent Segmentation of 59 Anatomical Structures in MR images.2024."},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2022.06.078"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2018.12.007"},{"key":"e_1_2_8_34_1","doi-asserted-by":"crossref","unstructured":"KlymenkoT KimST LauberK et\u00a0al.Butterfly\u2010Net: spatial\u2010temporal architecture for medical image segmentation. In:2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI).IEEE;2021:616\u2013620.","DOI":"10.1109\/ISBI48211.2021.9433939"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106236"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-022-01985-9"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17580","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,11]],"date-time":"2025-08-11T12:30:35Z","timestamp":1754915435000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17580"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,19]]},"references-count":35,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10.1002\/mp.17580"],"URL":"https:\/\/doi.org\/10.1002\/mp.17580","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,19]]},"assertion":[{"value":"2024-01-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-29","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-12-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}