{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T18:52:43Z","timestamp":1792176763396,"version":"4.4.0"},"reference-count":22,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2020,8,13]],"date-time":"2020-08-13T00:00:00Z","timestamp":1597276800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2020,10]]},"abstract":"<jats:sec><jats:title>Purpose<\/jats:title><jats:p>Despite being the standard metric in patient\u2010specific quality assurance (QA) for intensity\u2010modulated radiotherapy (IMRT), gamma analysis has two shortcomings: (a) it lacks sensitivity to small but clinically relevant errors (b) it does not provide efficient means to classify the error sources. The purpose of this work is to propose a dual neural network method to achieve simultaneous error detection and classification in patient\u2010specific IMRT QA.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>For a pair of dose distributions, we extracted the dose difference histogram (DDH) for the low dose gradient region and two signed distance\u2010to\u2010agreement (sDTA) maps (one in x direction and one in y direction) for the high dose gradient region. An artificial neural network (ANN) and a convolutional neural network (CNN) were designed to analyze the DDH and the two sDTA maps, respectively. The ANN was trained to detect and classify six classes of dosimetric errors: incorrect multileaf collimator (MLC) transmission (\u00b11%) and four types of monitor unit (MU) scaling errors (\u00b11% and \u00b12%). The CNN was trained to detect and classify seven classes of spatial errors: incorrect effective source size, 1\u00a0mm MLC leaf bank overtravel or undertravel, 2\u00a0mm single MLC leaf overtravel or undertravel, and device misalignment errors (1\u00a0mm in x\u2010 or y direction). An in\u2010house planar dose calculation software was used to simulate measurements with errors and noise introduced. Both networks were trained and validated with 13 IMRT plans (totaling 88 fields). A fivefold cross\u2010validation technique was used to evaluate their accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Distinct features were found in the DDH and the sDTA maps. The ANN perfectly identified all four types of MU scaling errors and the specific accuracies for the classes of no error, MLC transmission increase, MLC transmission decrease were 98.9%, 96.6%, and 94.3%, respectively. For the CNN, the largest confusion occurred between the 1\u2010mm\u2010MLC bank overtravel class and the 1\u2010mm\u2010device alignment error in x\u2010direction class, which brought the specific accuracies down to 90.9% and 92.0%, respectively. The specific accuracy for the 2\u2010mm\u2010single MLC leaf undertravel class was 93.2% as it misclassified 5.7% of the class as being error free (false negative). Otherwise, the specific accuracy was above 95%. The overall accuracies across the fivefold were 98.3\u00a0\u00b1\u00a00.7% and 95.6%\u00a0\u00b1\u00a01.5% for the ANN and the CNN, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Both the DDH and the sDTA maps are suitable features for error classification in IMRT QA. The proposed dual neural network method achieved simultaneous error detection and classification with excellent accuracy. It could be used in complement with the gamma analysis to potentially shift the IMRT QA paradigm from passive pass\/fail analysis to active error detection and root cause identification.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.14416","type":"journal-article","created":{"date-parts":[[2020,7,29]],"date-time":"2020-07-29T00:27:18Z","timestamp":1595982438000},"page":"4711-4720","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["Error detection and classification in patient\u2010specific IMRT QA with dual neural networks"],"prefix":"10.1002","volume":"47","author":[{"given":"Nicholas J.","family":"Potter","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology University of Florida Gainesville FL USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karl","family":"Mund","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Florida Gainesville FL USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jacqueline M.","family":"Andreozzi","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Florida Gainesville FL USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan G.","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Florida Gainesville FL USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chihray","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Florida Gainesville FL USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanghua","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology University of Florida Gainesville FL USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2020,8,13]]},"reference":[{"key":"e_1_2_7_2_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3600524"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3514120"},{"key":"e_1_2_7_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12810"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/0360-3016(93)90206-B"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.598363"},{"key":"e_1_2_7_7_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.598248"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1120\/jacmp.v10i1.2915"},{"key":"e_1_2_7_9_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3425781"},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3544657"},{"key":"e_1_2_7_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13338"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.08.013"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2017.03.049"},{"key":"e_1_2_7_14_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/53\/8\/004"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/57\/21\/6761"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031-9155\/59\/9\/N49"},{"key":"e_1_2_7_17_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13264"},{"key":"e_1_2_7_18_1","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems 25","author":"Krizhevsky A","year":"2012"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.1598711"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12890"},{"key":"e_1_2_7_21_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4953835"},{"key":"e_1_2_7_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13752"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2018.05.033"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fmp.14416","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.14416","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.14416","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.14416","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T08:37:29Z","timestamp":1745483849000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.14416"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,8,13]]},"references-count":22,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["10.1002\/mp.14416"],"URL":"https:\/\/doi.org\/10.1002\/mp.14416","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,8,13]]},"assertion":[{"value":"2020-04-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-07-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-08-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}