{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T03:16:15Z","timestamp":1787800575587,"version":"build-2784847793"},"reference-count":30,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2022,11,29]],"date-time":"2022-11-29T00:00:00Z","timestamp":1669680000000},"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":[[2023,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>A clinical study regarding the potential of range verification in proton therapy (PT) by prompt gamma imaging (PGI) is carried out at our institution. Manual interpretation of the detected spot\u2010wise range shift information is time\u2010consuming, highly complex, and therefore not feasible in a broad routine application.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Here, we present an approach to automatically detect and classify treatment deviations in realistically simulated PGI data for head\u2010and\u2010neck cancer (HNC) treatments using convolutional neural networks (CNNs) and conventional machine learning (ML) approaches.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>For 12 HNC patients and 1 anthropomorphic head phantom (<jats:italic>n<\/jats:italic>\u00a0=\u00a013), pencil beam scanning (PBS) treatment plans were generated, and 1 field per plan was assumed to be monitored with a PGI slit camera system. In total, 386 scenarios resembling different relevant or non\u2010relevant treatment deviations were simulated on planning and control CTs and manually classified into 7 classes: non\u2010relevant changes (NR) and relevant changes (RE) triggering treatment intervention due to range prediction errors (\u00b1RP), setup errors in beam direction (\u00b1SE), anatomical changes (AC), or a combination of such errors (CB). PBS spots with reliable PGI information were considered with their nominal Bragg peak position for the generation of two 3D spatial maps of 16\u00a0\u00d7 16\u00a0\u00d7\u00a016 voxels containing PGI\u2010determined range shift and proton number information. Three complexity levels of simulated PGI data were investigated: (I) optimal PGI data, (II) realistic PGI data with simulated Poisson noise based on the locally delivered proton number, and (III) realistic PGI data with an additional positioning uncertainty of the slit camera following an experimentally determined distribution. For each complexity level, 3D\u2010CNNs were trained on a data subset (<jats:italic>n<\/jats:italic>\u00a0=\u00a09) using patient\u2010wise leave\u2010one\u2010out cross\u2010validation and tested on an independent test cohort (<jats:italic>n<\/jats:italic>\u00a0=\u00a04). Both the binary task of detecting RE and the multi\u2010class task of classifying the underlying error source were investigated. Similarly, four different conventional ML classifiers (logistic regression, multilayer perceptron, random forest, and support vector machine) were trained using five previously established handcrafted features extracted from the PGI data and used for performance comparison.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>On the test data, the CNN ensemble achieved a binary accuracy of 0.95, 0.96, and 0.93 and a multi\u2010class accuracy of 0.83, 0.81, and 0.76 for the complexity levels (I), (II), and (III), respectively. In the case of binary classification, the CNN ensemble detected treatment deviations in the most realistic scenario with a sensitivity of 0.95 and a specificity of 0.88. The best performing ML classifiers showed a similar test performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>This study demonstrates that CNNs can reliably detect relevant changes in realistically simulated PGI data and classify most of the underlying sources of treatment deviations. The CNNs extracted meaningful features from the PGI data with a performance comparable to ML classifiers trained on previously established handcrafted features. These results highlight the potential of a reliable, automatic interpretation of PGI data for treatment verification, which is highly desired for a broad clinical application and a prerequisite for the inclusion of PGI in an automated feedback loop for online adaptive PT.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15975","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T13:50:10Z","timestamp":1663163410000},"page":"506-517","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Automatic detection and classification of treatment deviations in proton therapy from realistically simulated prompt gamma imaging data"],"prefix":"10.1002","volume":"50","author":[{"given":"Julian","family":"Pietsch","sequence":"first","affiliation":[{"name":"OncoRay\u2014National Center for Radiation Research in Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden Helmholtz\u2010Zentrum Dresden\u2010Rossendorf  Dresden Germany"},{"name":"Helmholtz\u2010Zentrum Dresden\u2010Rossendorf Institute of Radiooncology\u2014OncoRay  Dresden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chirasak","family":"Khamfongkhruea","sequence":"additional","affiliation":[{"name":"OncoRay\u2014National Center for Radiation Research in Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden Helmholtz\u2010Zentrum Dresden\u2010Rossendorf  Dresden Germany"},{"name":"Princess Srisavangavadhana College of Medicine Chulabhorn Royal Academy  Bangkok Thailand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Berthold","sequence":"additional","affiliation":[{"name":"OncoRay\u2014National Center for Radiation Research in Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden Helmholtz\u2010Zentrum Dresden\u2010Rossendorf  Dresden Germany"},{"name":"Helmholtz\u2010Zentrum Dresden\u2010Rossendorf Institute of Radiooncology\u2014OncoRay  Dresden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guillaume","family":"Janssens","sequence":"additional","affiliation":[{"name":"Ion Beam Applications SA  Louvain\u2010la\u2010Neuve Belgium"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristin","family":"St\u00fctzer","sequence":"additional","affiliation":[{"name":"OncoRay\u2014National Center for Radiation Research in Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden Helmholtz\u2010Zentrum Dresden\u2010Rossendorf  Dresden Germany"},{"name":"Helmholtz\u2010Zentrum Dresden\u2010Rossendorf Institute of Radiooncology\u2014OncoRay  Dresden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steffen","family":"L\u00f6ck","sequence":"additional","affiliation":[{"name":"OncoRay\u2014National Center for Radiation Research in Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden Helmholtz\u2010Zentrum Dresden\u2010Rossendorf  Dresden Germany"},{"name":"German Cancer Research Center (DKFZ) Heidelberg and German Cancer Consortium (DKTK) partner site Dresden  Dresden Germany"},{"name":"Department of Radiotherapy and Radiation Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden  Dresden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Richter","sequence":"additional","affiliation":[{"name":"OncoRay\u2014National Center for Radiation Research in Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden Helmholtz\u2010Zentrum Dresden\u2010Rossendorf  Dresden Germany"},{"name":"Helmholtz\u2010Zentrum Dresden\u2010Rossendorf Institute of Radiooncology\u2014OncoRay  Dresden Germany"},{"name":"German Cancer Research Center (DKFZ) Heidelberg and German Cancer Consortium (DKTK) partner site Dresden  Dresden Germany"},{"name":"Department of Radiotherapy and Radiation Oncology Faculty of Medicine and University Hospital Carl Gustav Carus Technische Universit\u00e4t Dresden  Dresden Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,11,29]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190787"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/58\/15\/R131"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.1350587"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/57\/11\/R99"},{"key":"e_1_2_9_6_1","unstructured":"StichelbautF JongenY.Verification of the proton beam position in the patient by the detection of prompt gamma\u2010rays emission. In:39th meeting of the Particle Therapy Co\u2010Operative Group.San Francisco;2003."},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.2378561"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/57\/11\/3371"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.nima.2017.07.063"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190619"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.04.027"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/abcd16"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14393"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2017.10.013"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2021.06.036"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.12.008"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2016.10.022"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4801899"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/60\/12\/4915"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/61\/22\/7881"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_9_22_1","unstructured":"KingmaDP BaJ.Adam: a method for stochastic optimization. Int Conf Learn Represent. Published online2014.http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"e_1_2_9_23_1","unstructured":"IsenseeF J\u00e4gerP DavidWJZ et\u00a0al.batchgenerators \u2013 a python framework for data augmentation. Published online2020."},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"AkibaT SanoS YanaseT OhtaT KoyamaM. In:Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.ACM;2019:2623\u20102631.https:\/\/doi.org\/10.1145\/3292500.3330701","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmp.2019.12.006"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab3564"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14443"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab9707"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/abaa5e"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1088\/2057\u20101976\/ac396d"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/59\/19\/5849"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15975","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15975","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,21]],"date-time":"2023-08-21T20:29:05Z","timestamp":1692649745000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15975"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,29]]},"references-count":30,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1]]}},"alternative-id":["10.1002\/mp.15975"],"URL":"https:\/\/doi.org\/10.1002\/mp.15975","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,29]]},"assertion":[{"value":"2022-04-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-29","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-11-29","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}