{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T15:11:18Z","timestamp":1789571478624,"version":"build-2803163510"},"reference-count":39,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:00:00Z","timestamp":1667779200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008672","name":"Wilhelm Sander-Stiftung","doi-asserted-by":"publisher","award":["2019.162.1"],"award-info":[{"award-number":["2019.162.1"]}],"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":[[2023,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Online adaptive radiation therapy (RT) using hybrid magnetic resonance linear accelerators (MR\u2010Linacs) can administer a tailored radiation dose at each treatment fraction. Daily MR imaging followed by organ and target segmentation adjustments allow to capture anatomical changes, improve target volume coverage, and reduce the risk of side effects. The introduction of automatic segmentation techniques could help to further improve the online adaptive workflow by shortening the re\u2010contouring time and reducing intra\u2010 and inter\u2010observer variability. In fractionated RT, prior knowledge, such as planning images and manual expert contours, is usually available before irradiation, but not used by current artificial intelligence\u2010based autocontouring\u00a0approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>The goal of this study was to train convolutional neural networks (CNNs) for automatic segmentation of bladder, rectum (organs at risk, OARs), and clinical target volume (CTV) for prostate cancer patients treated at 0.35 T MR\u2010Linacs. Furthermore, we tested the CNNs generalization on data from independent facilities and compared them with the MR\u2010Linac treatment planning system (TPS) propagated structures currently used in clinics. Finally, expert planning delineations were utilized for patient\u2010 (PS) and facility\u2010specific (FS) transfer learning to improve auto\u2010segmentation of CTV and OARs on fraction\u00a0images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, data from fractionated treatments at 0.35\u00a0T MR\u2010Linacs were leveraged to develop a 3D U\u2010Net\u2010based automatic segmentation. Cohort C1 had 73 planning images and cohort C2 had 19 planning and 240 fraction images. The baseline models (BMs) were trained solely on C1 planning data using 53 MRIs for training and 10 for validation. To assess their accuracy, the models were tested on three data subsets: (i) 10 C1 planning images not used for training, (ii) 19 C2 planning, and (iii) 240 C2 fraction images. BMs also served as a starting point for FS and PS transfer learning, where the planning images from C2 were used for network parameter fine tuning. The segmentation output of the different trained models was compared against expert ground truth by means of geometric metrics. Moreover, a trained physician graded the network segmentations as well as the segmentations propagated by the clinical\u00a0TPS.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The BMs showed dice similarity coefficients (DSC) of 0.88(4) and 0.93(3) for the rectum and the bladder, respectively, independent of the facility. CTV segmentation with the BM was the best for intermediate\u2010 and high\u2010risk cancer patients from C1 with DSC=0.84(5) and worst for C2 with DSC=0.74(7). The PS transfer learning brought a significant improvement in the CTV segmentation, yielding DSC=0.72(4) for post\u2010prostatectomy and low\u2010risk patients and DSC=0.88(5) for intermediate\u2010 and high\u2010risk patients. The FS training did not improve the segmentation accuracy considerably. The physician's assessment of the TPS\u2010propagated versus network\u2010generated structures showed a clear advantage of the\u00a0latter.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The obtained results showed that the presented segmentation technique has potential to improve automatic segmentation for MR\u2010guided\u00a0RT.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/mp.16056","type":"journal-article","created":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T04:55:24Z","timestamp":1666155324000},"page":"1573-1585","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Patient\u2010specific transfer learning for auto\u2010segmentation in adaptive 0.35 T MRgRT of prostate cancer: a bi\u2010centric evaluation"],"prefix":"10.1002","volume":"50","author":[{"given":"Maria","family":"Kawula","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Indrawati","family":"Hadi","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lukas","family":"Nierer","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marica","family":"Vagni","sequence":"additional","affiliation":[{"name":"Fondazione Policlinico Universitario \u201cAgostino Gemelli\u201d IRCCS Rome Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Davide","family":"Cusumano","sequence":"additional","affiliation":[{"name":"Fondazione Policlinico Universitario \u201cAgostino Gemelli\u201d IRCCS Rome Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Boldrini","sequence":"additional","affiliation":[{"name":"Fondazione Policlinico Universitario \u201cAgostino Gemelli\u201d IRCCS Rome Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Placidi","sequence":"additional","affiliation":[{"name":"Fondazione Policlinico Universitario \u201cAgostino Gemelli\u201d IRCCS Rome Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanie","family":"Corradini","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claus","family":"Belka","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University Hospital LMU Munich Munich Germany"},{"name":"German Cancer Consortium (DKTK) Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Landry","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Kurz","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University Hospital LMU Munich Munich Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,11,7]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2019.04.001"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2018.08.010"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-021-01858-7"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-019-1308-y"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.03.035"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.08.007"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2020.07.003"},{"issue":"12","key":"e_1_2_9_9_1","article-title":"First 500 fractions delivered with a magnetic resonance\u2010guided radiotherapy system: initial experience","volume":"11","author":"Sahin B","year":"2019","journal-title":"Cureus"},{"issue":"8","key":"e_1_2_9_10_1","article-title":"Online adaptive radiation therapy: implementation of a new process of care","volume":"9","author":"Lamb J","year":"2017","journal-title":"Cureus"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13071523"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-022-01981-z"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2019.04.007"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.05.010"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.02.040"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2020.05.013"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8140(98)00021-8"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.07.001"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13221"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13994"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2020.02.44"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14659"},{"key":"e_1_2_9_23_1","first-page":"424","volume-title":"International Conference on Medical Image Computing and Computer\u2010Assisted Intervention","author":"\u00c7i\u00e7ek \u00d6","year":"2016"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2021.102195"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15352"},{"key":"e_1_2_9_26_1","volume-title":"Proceedings of the XVI'th International Conference on the use of Computers in Radiotherapy (ICCR)","author":"Sharp GC","year":"2010"},{"key":"e_1_2_9_27_1","article-title":"Project MONAI","author":"Ma N","year":"2021","journal-title":"Zenodo CERN"},{"key":"e_1_2_9_28_1","first-page":"371","volume-title":"International Workshop on Statistical Atlases and Computational Models of the Heart","author":"Kerfoot E","year":"2018"},{"key":"e_1_2_9_29_1","unstructured":"UlyanovD VedaldiA LempitskyV.Instance normalization: the missing ingredient for fast stylization.2016. arXiv:1607.08022."},{"key":"e_1_2_9_30_1","doi-asserted-by":"crossref","unstructured":"DingB QianH ZhouJ.Activation functions and their characteristics in deep neural networks.Chinese control and decision conference (CCDC).IEEE;2018:1836\u20101841.","DOI":"10.1109\/CCDC.2018.8407425"},{"key":"e_1_2_9_31_1","first-page":"211","article-title":"Training stochastic model recognition algorithms as networks can lead to maximum mutual information estimation of parameters","volume":"2","author":"Bridle JS","year":"1990","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"MilletariF NavabN AhmadiSA.V\u2010net: Fully convolutional neural networks for volumetric medical image segmentation.Fourth international conference on 3D vision (3DV).IEEE;2016:565\u2010571.","DOI":"10.1109\/3DV.2016.79"},{"key":"e_1_2_9_33_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization.2014.arXiv:1412.6980."},{"key":"e_1_2_9_34_1","first-page":"31","article-title":"Deep\u2010learning\u2010based segmentation of organs\u2010at\u2010risk in the head for MR\u2010assisted radiation therapy planning","volume":"2","author":"Rusk\u00f3 L","year":"2021","journal-title":"BIOIMAGING"},{"key":"e_1_2_9_35_1","first-page":"8026","article-title":"Pytorch: an imperative style, high\u2010performance deep learning library","volume":"32","author":"Paszke A","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106236"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2019.11.006"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014-020-01528-0"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.06.076"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15285"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16056","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.16056","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16056","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T20:37:32Z","timestamp":1692650252000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16056"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,7]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["10.1002\/mp.16056"],"URL":"https:\/\/doi.org\/10.1002\/mp.16056","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,7]]},"assertion":[{"value":"2022-05-03","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-25","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-11-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}