{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,29]],"date-time":"2026-08-29T11:09:15Z","timestamp":1788001755362,"version":"build-2784847793"},"reference-count":36,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:00:00Z","timestamp":1722902400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2024,11]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Daily adaptive radiotherapy, as performed with the Elekta Unity MR\u2010Linac, requires choosing between different adaptation methods, namely ATP (Adapt to Position) and ATS (Adapt to Shape), where the latter requires daily re\u2010contouring to obtain a dose plan tailored to the daily anatomy. These steps are inherently resource\u2010intensive, and quickly predicting the dose distribution and the dosimetric evaluation criteria while the patient is on the table could facilitate a fast selection of adaptation method and decrease the treatment times.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>In this work, we aimed to develop a deep\u2010learning\u2010based dose\u2010prediction pipeline for prostate MR\u2010Linac treatments.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Two hundred twelve MR\u2010images, structure sets, and dose distributions from 35 prostate patients treated with 6.1\u00a0Gy for 7 or 6 fractions at our MR\u2010Linac were included, split into train\/test partitions of 152\/60 images, respectively. A deep\u2010learning segmentation network was trained to segment the CTV (prostate), bladder, and rectum. A second network was trained to predict the dose distribution based on manually delineated structures. At inference, the predicted segmentations acted as input to the dose prediction network, and the predicted dose was compared to the true (optimized in the treatment planning system) dose distribution.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Median DSC values from the segmentation network were 0.90\/0.94\/0.87 for CTV\/bladder\/rectum. Predicted segmentations as input to the dose prediction resulted in mean differences between predicted and true doses of 0.7%\/0.7%\/1.7% (relative to the prescription dose) for <jats:italic>D<\/jats:italic><jats:sub>98%<\/jats:sub>\/<jats:italic>D<\/jats:italic><jats:sub>95%<\/jats:sub>\/<jats:italic>D<\/jats:italic><jats:sub>2%<\/jats:sub> for the CTV. For the bladder, the difference was 0.7%\/0.3% for <jats:italic>D<\/jats:italic><jats:sub>mean<\/jats:sub><jats:italic>\/D<\/jats:italic><jats:sub>2%<\/jats:sub> and for the rectum 0.1\/0.2\/0.2 pp (percentage points) for <jats:italic>V<\/jats:italic><jats:sub>33Gy<\/jats:sub>\/<jats:italic>V<\/jats:italic><jats:sub>38Gy<\/jats:sub>\/<jats:italic>V<\/jats:italic><jats:sub>41Gy<\/jats:sub>. In comparison, true segmentations as input resulted in differences of 1.1%\/0.9%\/1.6% for CTV, 0.5%\/0.4% for bladder, and 0.7\/0.4\/0.3 pp for the rectum. Only <jats:italic>D<\/jats:italic><jats:sub>2%<\/jats:sub> for CTV and <jats:italic>D<\/jats:italic><jats:sub>mean<\/jats:sub>\/<jats:italic>D<\/jats:italic><jats:sub>2%<\/jats:sub> for bladder were found to be statistically significantly better when using true structures instead of predicted structures as input to the dose prediction.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Small differences in the fulfillment of clinical dose\u2010volume constraints are seen between utilizing deep\u2010learning predicted structures as input to a dose prediction network and manual structures. Overall mean differences\u00a0&lt;2% indicate that the dose\u2010prediction pipeline is useful as a decision support tool where differences are\u00a0&gt;2%.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.17312","type":"journal-article","created":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T19:50:16Z","timestamp":1722973816000},"page":"8087-8095","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Deep learning\u2010based dose prediction for magnetic resonance\u2010guided prostate radiotherapy"],"prefix":"10.1002","volume":"51","author":[{"given":"Samuel","family":"Fransson","sequence":"first","affiliation":[{"name":"Department of Medical Physics Uppsala University Hospital  Uppsala Sweden"},{"name":"Department of Surgical Sciences Uppsala University  Uppsala Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robin","family":"Strand","sequence":"additional","affiliation":[{"name":"Department of Surgical Sciences Uppsala University  Uppsala Sweden"},{"name":"Department of Information Technology Uppsala University  Uppsala Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Tilly","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Uppsala University Hospital  Uppsala Sweden"},{"name":"Department of Immunology Genetics and Pathology Uppsala University  Uppsala Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,8,6]]},"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.ctro.2019.04.007"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.7759\/cureus.1618"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.06.044"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13014\u2010021\u201001916\u20100"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.meddos.2021.08.005"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16192"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.11.019"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16047"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1186\/1748\u2010717X\u20107\u2010160"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1213068"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.11.012"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2021.07.027"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers15174226"},{"key":"e_1_2_9_16_1","doi-asserted-by":"crossref","unstructured":"KamathA PoelR WillmannJ AndratschkeN ReyesM.How sensitive are deep learning based radiotherapy dose prediction models to variability in organs at risk segmentation?2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI) Cartagena Colombia 2023:1\u20104. doi:10.1109\/isbi53787.2023.10230559","DOI":"10.1109\/ISBI53787.2023.10230559"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010018\u201037741\u2010x"},{"key":"e_1_2_9_18_1","first-page":"234","article-title":"U\u2010net: convolutional networks for biomedical image segmentation","volume":"9351","author":"Ronneberger O","year":"2015","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2021.07.008"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab2146"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.10.027"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15461"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.13630"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0232697"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108324"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/acm2.12884"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.2307\/1932409"},{"key":"e_1_2_9_28_1","unstructured":"PhilT AlbrechtT GayS RasmusseME.Sikerdebaard\/dcmrtstruct2nii: dcmrtstruct2nii v5 (Version v5). doi:10.5281\/zenodo.4037864"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10278\u2010017\u20100037\u20108"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v086.i08"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2013.00045"},{"key":"e_1_2_9_32_1","unstructured":"OktayO SchlemperJ FolgocLL et\u00a0al.Attention U\u2010Net: learning where to look for the pancreas. arXiv.2018. arXiv:1804.03999."},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41592\u2010020\u201001008\u2010z"},{"key":"e_1_2_9_34_1","unstructured":"UlyanovD VedaldiA LempitskyV.Instance normalization: the missing ingredient for fast stylization.arXiv.2017. arXiv:1607.08022."},{"key":"e_1_2_9_35_1","unstructured":"KingmaDP BaJL.Adam: a method for stochastic optimization.Proceedings of the 3rd International Conference on Learning Representations San Diego CA USA 7\u20139 May 2015:1\u201015."},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0229839"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ac8d45"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.17312","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T20:03:52Z","timestamp":1733169832000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.17312"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,6]]},"references-count":36,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11]]}},"alternative-id":["10.1002\/mp.17312"],"URL":"https:\/\/doi.org\/10.1002\/mp.17312","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,6]]},"assertion":[{"value":"2024-01-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-08-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}