{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T02:56:47Z","timestamp":1790650607426,"version":"4.1.0"},"reference-count":22,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["J Applied Clin Med Phys"],"published-print":{"date-parts":[[2026,10]]},"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Accurate CT\/MR registration is important in stereotactic brain radiotherapy, where small spatial errors may affect target localization and treatment planning. In many clinical settings, registration quality is still assessed primarily through manual visual inspection. However, time and workflow constraints may limit the consistency and depth of manual evaluation.<\/jats:p>\n <\/jats:sec>\n \n Purpose<\/jats:title>\n \n This study aimed to develop a 3D convolutional neural network (3D CNN)\u2010based quality assurance (QA) method for rigid brain CT\/MR registration using paired sub\u2010volumes and a registration\u2010level mean probability score (\n \u03bc<\/jats:italic>\n ). The proposed method classifies local CT\/MR registration quality, while the final registration\u2010level assessment is based on\n \u03bc<\/jats:italic>\n across the sampled sub\u2010volumes.\n <\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n \n The study included 209 patients. Of these, 202 comprised the primary cohort and were divided patient\u2010wise into 128 training, 33 validation, and 41 test patients. For each patient, 25 skull\u2010based CT\/MR sub\u2010volumes of 42\u00a0\u00d7\u00a0 42\u00a0\u00d7\u00a0 42 voxels were used as a two\u2010channel CNN input. High\u2010quality examples were obtained from clinically approved registrations, while low\u2010quality examples were generated using rigid perturbations of the complete MR volume. The mean predicted probability across the 25 sub\u2010volumes was used as the registration\u2010level score\n \u03bc<\/jats:italic>\n , and the validation\u2010derived threshold of 0.5871 was fixed for testing. Seven additional patients, separate from the 202\u2010patient cohort, were evaluated after model development and threshold selection were completed using registrations before and after physician correction.\n <\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n On the held\u2010out test set, patch\u2010level accuracy was 85.90%, with an ROC AUC of 0.929 and average precision of 0.920. At the registration level, accuracy was 97.56% and ROC AUC was 0.999. All 41 low\u2010quality registrations were correctly flagged, while 39 of 41 high\u2010quality registrations were correctly accepted. In the additional clinical evaluation, all seven initial registrations requiring correction were classified as low quality, while six of seven corrected registrations were classified as high quality, resulting in an overall accuracy of 92.86%.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n \n The proposed method combined local CNN predictions into a registration\u2010level\n \u03bc<\/jats:italic>\n score and showed strong performance on held\u2010out and clinical cases. It may provide a quantitative screening measure for rigid brain CT\/MR registration QA while maintaining clinical review as the final decision step.\n <\/jats:p>\n <\/jats:sec>","DOI":"10.1002\/acm2.70828","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T02:02:20Z","timestamp":1790647340000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated quality assurance of rigid brain CT\/MR image registration using a 3D convolutional neural network"],"prefix":"10.1002","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3373-8199","authenticated-orcid":false,"given":"Zeinab A.","family":"Chahrour","sequence":"first","affiliation":[{"name":"Department of Physics Beirut Arab University Beirut Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nour F.","family":"Obeid","sequence":"additional","affiliation":[{"name":"Department of Computer Science American University of Beirut Beirut Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1240-3785","authenticated-orcid":false,"given":"Ali","family":"El\u2010Zaart","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science Faculty of Sciences Beirut Arab University Beirut Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wassila","family":"EL Kanawati","sequence":"additional","affiliation":[{"name":"Department of Physics Beirut Arab University Beirut Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abbas","family":"Mkanna","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology American University of Beirut Medical Center Beirut Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rida","family":"Assaf","sequence":"additional","affiliation":[{"name":"Department of Computer Science American University of Beirut Beirut Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8071-7463","authenticated-orcid":false,"given":"Bilal H.","family":"Shahine","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology American University of Beirut Medical Center Beirut Lebanon"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"key":"e_1_2_12_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12256"},{"key":"e_1_2_12_3_1","doi-asserted-by":"publisher","DOI":"10.1120\/JACMP.v5i1.1951"},{"key":"e_1_2_12_4_1","doi-asserted-by":"publisher","DOI":"10.3390\/s19102361"},{"key":"e_1_2_12_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/J.NEUCOM.2006.01.007"},{"key":"e_1_2_12_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13890"},{"issue":"8","key":"e_1_2_12_7_1","doi-asserted-by":"crossref","first-page":"4078","DOI":"10.1118\/1.3438081","article-title":"Stereotactic body radiation therapy: the report of AAPM Task Group 101","volume":"37","author":"Benedict SH","year":"2010","journal-title":"Med Phys"},{"key":"e_1_2_12_8_1","doi-asserted-by":"publisher","DOI":"10.3389\/fradi.2024.1385742"},{"key":"e_1_2_12_9_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017170706"},{"key":"e_1_2_12_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2016.2536809"},{"key":"e_1_2_12_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548\u2010016\u20101467\u20103"},{"key":"e_1_2_12_12_1","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2017162326"},{"key":"e_1_2_12_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978\u20103\u2010540\u201030135\u20106_100"},{"key":"e_1_2_12_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2014.2344911"},{"key":"e_1_2_12_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/tmi.2015.2481609"},{"key":"e_1_2_12_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.12321"},{"key":"e_1_2_12_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548\u2010022\u201002786\u2010x"},{"key":"e_1_2_12_18_1","doi-asserted-by":"publisher","DOI":"10.1088\/1361\u20106560\/ab843e"},{"key":"e_1_2_12_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15875"},{"key":"e_1_2_12_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2023.102263"},{"key":"e_1_2_12_21_1","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2013.00045"},{"key":"e_1_2_12_22_1","doi-asserted-by":"publisher","DOI":"10.3390\/asi6050087"},{"key":"e_1_2_12_23_1","volume-title":"Understanding the fundamentals of machine learning and AI for digital business","author":"Ismail A","year":"2023"}],"container-title":["Journal of Applied Clinical Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70828","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/acm2.70828","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acm2.70828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T02:02:22Z","timestamp":1790647342000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/acm2.70828"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":22,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2026,10]]}},"alternative-id":["10.1002\/acm2.70828"],"URL":"https:\/\/doi.org\/10.1002\/acm2.70828","archive":["Portico"],"relation":{},"ISSN":["1526-9914","1526-9914"],"issn-type":[{"value":"1526-9914","type":"print"},{"value":"1526-9914","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"2026-02-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-16","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70828"}}