{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T23:26:07Z","timestamp":1792106767295,"version":"4.4.0"},"reference-count":44,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2022,8,23]],"date-time":"2022-08-23T00:00:00Z","timestamp":1661212800000},"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":[[2022,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>In cone\u2010beam computed tomography (CBCT)\u2010guided radiotherapy, off\u2010by\u2010one vertebral\u2010body misalignments are rare but serious errors that lead to wrong\u2010site treatments.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>An automatic error detection algorithm was developed that uses a three\u2010branch convolutional neural network error detection model (EDM) to detect off\u2010by\u2010one vertebral\u2010body misalignments using planning computed tomography (CT) images and setup CBCT images.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Algorithm training and test data consisted of planning CTs and CBCTs from 480 patients undergoing radiotherapy treatment in the thoracic and abdominal regions at two radiotherapy clinics. The clinically applied registration was used to derive true\u2010negative (no error) data. The setup and planning images were then misaligned by one vertebral\u2010body in both the superior and inferior directions, simulating the most likely misalignment scenarios. For each of the aligned and misaligned 3D image pairs, 2D slice pairs were automatically extracted in each anatomical plane about a point within the vertebral column. The three slice pairs obtained were then inputted to the EDM that returned a probability of vertebral misalignment. One model (EDM<jats:sub>1<\/jats:sub>) was trained solely on data from institution 1. EDM<jats:sub>1<\/jats:sub> was further trained using a lower learning rate on a dataset from institution 2 to produce a fine\u2010tuned model, EDM<jats:sub>2<\/jats:sub>. Another model, EDM<jats:sub>3<\/jats:sub>, was trained from scratch using a training dataset composed of data from both institutions. These three models were validated on a randomly selected and unseen dataset composed of images from both institutions, for a total of 303 image pairs. The model performances were quantified using a receiver operating characteristic analysis. Due to the rarity of vertebral\u2010body misalignments in the clinic, a minimum threshold value yielding a specificity of at least 99% was selected. Using this threshold, the sensitivity was calculated for each model, on each institution's test set separately.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>When applied to the combined test set, EDM<jats:sub>1<\/jats:sub>, EDM<jats:sub>2<\/jats:sub>, and EDM<jats:sub>3<\/jats:sub> resulted in an area under curve of 99.5%, 99.4%, and 99.5%, respectively. EDM<jats:sub>1<\/jats:sub> achieved a sensitivity of 96% and 88% on Institution 1 and Institution 2 test set, respectively. EDM<jats:sub>2<\/jats:sub> obtained a sensitivity of 95% on each institution's test set. EDM<jats:sub>3<\/jats:sub> achieved a sensitivity of 95% and 88% on Institution 1 and Institution 2 test set, respectively.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The proposed algorithm demonstrated accuracy in identifying off\u2010by\u2010one vertebral\u2010body misalignments in CBCT\u2010guided radiotherapy that was sufficiently high to allow for practical implementation. It was found that fine\u2010tuning the model on a multi\u2010facility dataset can further enhance the generalizability of the algorithm.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.15927","type":"journal-article","created":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T17:25:01Z","timestamp":1660411501000},"page":"6410-6423","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Development and interinstitutional validation of an automatic vertebral\u2010body misalignment error detector for cone\u2010beam CT\u2010guided radiotherapy"],"prefix":"10.1002","volume":"49","author":[{"given":"Dishane C.","family":"Luximon","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timothy","family":"Ritter","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Fields","sequence":"additional","affiliation":[{"name":"Department of Medical Physics Virginia Commonwealth University  Richmond Virginia USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Neylon","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rachel","family":"Petragallo","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasin","family":"Abdulkadir","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Charters","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel A.","family":"Low","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James M.","family":"Lamb","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, David Geffen School of Medicine University of California  Los Angeles California USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,8,23]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.11.047"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2011.04.036"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.icrp.2012.06.011"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3522875"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tipsro.2020.02.001"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2013.05.010"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167\u20108140(96)91799\u20105"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2017.10.007"},{"issue":"6","key":"e_1_2_9_10_1","article-title":"Anatomical variations that can lead to spine surgery at the wrong level: part II thoracic spine","volume":"12","author":"Shah M","year":"2020","journal-title":"Cureus"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.3675973"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1118\/1.4769428"},{"key":"e_1_2_9_13_1","doi-asserted-by":"publisher","DOI":"10.1088\/0031\u20109155\/52\/13\/019"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2013.05.021"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prro.2015.06.004"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591\u2010018\u20100316\u2010z"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"LongJ ShelhamerE DarrellT.Fully convolutional networks for semantic segmentation.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2015:3431\u20103440.","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_2_9_18_1","first-page":"25","volume-title":"Advances in Neural Information Processing Systems","author":"Krizhevsky A","year":"2012"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65981-7_12"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.21037\/atm.2020.02.44"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548\u2010017\u20101605\u20106"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1080\/21681163.2015.1124249"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1164\/rccm.201705\u20100860OC"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2008.06.1926"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"HuangG LiuZ Van Der MaatenL WeinbergerKQ.Densely connected convolutional networks.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017:4700\u20104708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14507"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TUFFC.2020.3015081"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJ.Deep residual learning for image recognition.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_9_29_1","first-page":"32","volume-title":"Advances in Neural Information Processing Systems","author":"Raghu M","year":"2019"},{"key":"e_1_2_9_30_1","unstructured":"DaK.A method for stochastic optimization.2014. arXiv preprint arXiv:1412.6980."},{"key":"e_1_2_9_31_1","unstructured":"JanochaK CzarneckiWM.On loss functions for deep neural networks in classification.2017. arXiv preprint arXiv:1702.05659."},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"e_1_2_9_33_1","doi-asserted-by":"crossref","unstructured":"GoutteC GaussierE.A probabilistic interpretation of precision recall and F\u2010score with implication for evaluation.European Conference on Information Retrieval.Berlin Heidelberg.Springer; March2005:345\u2010359.","DOI":"10.1007\/978-3-540-31865-1_25"},{"key":"e_1_2_9_34_1","unstructured":"GuilfordJP.Psychometric methods.1954."},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12864\u2010019\u20106413\u20107"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00586\u2010010\u20101326\u20109"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/42.563664"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1259\/dmfr\/30642039"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.01.012"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2018.09.008"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0167\u20108140(03)00245\u20107"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1590\/s1020\u201049892006000800013"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.14030"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2012.04.036"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15927","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.15927","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.15927","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,20]],"date-time":"2023-08-20T09:54:44Z","timestamp":1692525284000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.15927"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,23]]},"references-count":44,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2022,10]]}},"alternative-id":["10.1002\/mp.15927"],"URL":"https:\/\/doi.org\/10.1002\/mp.15927","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,23]]},"assertion":[{"value":"2022-04-12","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-05","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-23","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}