{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T16:38:01Z","timestamp":1790440681284,"version":"4.1.0"},"reference-count":22,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T00:00:00Z","timestamp":1686700800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2023,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Deep learning\u2010based auto\u2010planning is an active research field; however, for some tasks a treatment planning system (TPS) is still required.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>To introduce a deep learning\u2010based model generating deliverable DICOM RT treatment plans that can be directly irradiated by a linear accelerator (LINAC). The model was based on an encoder\u2010decoder network and can predict multileaf collimator (MLC) motion sequences for prostate VMAT radiotherapy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A total of 619 treatment plans from 460 patients treated for prostate cancer with single\u2010arc VMAT were included in this study. An encoder\u2010decoder network was trained using 465 clinical treatment plans and validated on 77 plans. The performance was analyzed on a separate test set of 77 treatment plans. Separate L1 losses were computed for the leaf and jaw positions as well as the monitor units, with the leaf loss being weighted by a factor of 100 before being added to the other losses. The generated treatment plans were recalculated in a treatment planning system and the dose\u2010volume metrics and gamma passing rates were compared to the original dose.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>All generated treatment plans showed good agreement with the original data, with an average gamma passing rate (3%\/3\u00a0mm) of 91.9\u00a0\u00b1\u00a07.1%. However, the coverage of the PTVs. was slightly lower for the generated plans (D<jats:sub>98%<\/jats:sub>\u00a0=\u00a092.9\u00a0\u00b1\u00a02.6%) in comparison to the original plans (<jats:italic>D<\/jats:italic><jats:sub>98%<\/jats:sub>\u00a0=\u00a095.7\u00a0\u00b1\u00a02.2%). There was no significant difference in mean dose to the bladder between the predicted and original plan (<jats:italic>D<\/jats:italic><jats:sub>mean<\/jats:sub> of 28.0\u00a0\u00b1\u00a013.5\u00a0vs. 28.1\u00a0\u00b1\u00a013.3% of prescribed dose) or rectum (<jats:italic>D<\/jats:italic><jats:sub>mean<\/jats:sub> of 42.3\u00a0\u00b1\u00a07.4\u00a0vs. 42.6\u00a0\u00b1\u00a07.5%). The maximum dose to bladder was only slightly higher in the predicted plans (D2% of 100.7\u00a0\u00b1\u00a05.3\u00a0vs. 99.8\u00a0\u00b1\u00a04.0%) and for the rectum it was even lower (D2% of 100.5\u00a0\u00b1\u00a03.7\u00a0vs. 100.1\u00a0\u00b1\u00a04.3).<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The deep learning\u2010based model could predict MLC motion sequences in prostate VMAT plans, eliminating the need for sequencing inside a TPS, thus revolutionizing autonomous treatment planning workflows. This research completes the loop in deep learning\u2010based treatment planning processes, enabling more efficient workflows for real\u2010time or online adaptive radiotherapy.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16545","type":"journal-article","created":{"date-parts":[[2023,6,14]],"date-time":"2023-06-14T12:46:40Z","timestamp":1686746800000},"page":"5088-5094","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Generating deliverable DICOM RT treatment plans for prostate VMAT by predicting MLC motion sequences with an encoder\u2010decoder network"],"prefix":"10.1002","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7461-3956","authenticated-orcid":false,"given":"Gerd","family":"Heilemann","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0099-2276","authenticated-orcid":false,"given":"Lukas","family":"Zimmermann","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Raphael","family":"Schotola","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9211-7510","authenticated-orcid":false,"given":"Wolfgang","family":"Lechner","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0830","authenticated-orcid":false,"given":"Marco","family":"Peer","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9972-6690","authenticated-orcid":false,"given":"Joachim","family":"Widder","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gregor","family":"Goldner","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8327-3877","authenticated-orcid":false,"given":"Dietmar","family":"Georg","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2961-1692","authenticated-orcid":false,"given":"Peter","family":"Kuess","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology Comprehensive Cancer Center Vienna Medical University Vienna Vienna Austria"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2023,6,14]]},"reference":[{"key":"e_1_2_9_2_1","article-title":"A review on application of deep learning algorithms in external beam radiotherapy automated treatment planning","volume":"10","author":"Wang M","year":"2020","journal-title":"Front Oncol"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20180270"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14774"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14845"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac80e5"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-37186-2"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aba5eb"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15530"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/abc12c"},{"key":"e_1_2_9_11_1","unstructured":"ChenS MaK ZhengY Med3D: Transfer Learning for 3D Medical Image Analysis.1\u201012(2019)."},{"key":"e_1_2_9_12_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ Deep residual learning for image recognition.Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition2016\u2010Decem 2016:770\u2010778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_13_1","unstructured":"HowardAG ZhuM ChenB et\u00a0al.MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. (2017)."},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"SmithLN TopinN Super\u2010convergence: very fast training of neural networks using large learning rates.36(2019) doi:10.1117\/12.2520589","DOI":"10.1117\/12.2520589"},{"key":"e_1_2_9_15_1","unstructured":"ChenX LiangC HuangD et\u00a0al.Symbolic Discovery of Optimization Algorithms.1\u201029(2023)."},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13271"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13896"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aa71f8"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/aba165"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"HibbardL Adversarial Prediction of Radiotherapy Treatment Machine Parameters. (2020).","DOI":"10.1007\/978-3-030-60946-7_9"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.02.040"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.zemedi.2021.11.006"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.09.038"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T14:54:32Z","timestamp":1755874472000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16545"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,14]]},"references-count":22,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2023,8]]}},"alternative-id":["10.1002\/mp.16545"],"URL":"https:\/\/doi.org\/10.1002\/mp.16545","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,14]]},"assertion":[{"value":"2023-03-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-05-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-06-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}