{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T10:57:34Z","timestamp":1771930654487,"version":"3.50.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T00:00:00Z","timestamp":1770249600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and validate an unsupervised machine learning\u2013based approach for near-real-time alerting of statistically abnormal six-dimensional (6D) radiotherapy setup errors. Using large-scale clinical datasets, the robustness of the proposed approach was evaluated across different immobilization methods and treatment sites to support quality assurance alerting.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 7,539 CBCT-based 6D setup error records collected at our center between May 2022 and March 2025 were analyzed. After data standardization and construction of proxy anomalous samples, two unsupervised models\u2014Isolation Forest (IF) and Local Outlier Factor (LOF)\u2014were developed. Model performance was assessed using ROC-AUC, PR-AUC, and sensitivity at a fixed false positive rate (FPR \u2248 5%). Subgroup analyses were performed by immobilization method and treatment site. Interpretability was explored using principal component analysis (PCA) and Spearman correlation. To provide minimal translational context, geometric tolerance exceedance rates based on translational and rotational thresholds were quantified.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Overall, IF outperformed LOF (ROC-AUC = 0.960 [95% CI: 0.956\u20130.964] vs. 0.880 [95% CI: 0.872\u20130.888]). Most immobilization methods achieved AUC \u2265 0.92 (range: 0.912\u20131.000), with dual-face SRT masks and neck\u2013thorax mask plus vacuum cushion combinations approaching ideal performance (AUC \u2248 1.00). Interpretability analyses indicated that the AP, Pitch, and LR directions were the primary contributors to abnormality detection. Longitudinal evaluation revealed stable performance without model drift.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study demonstrates the feasibility of applying unsupervised learning to identify statistically unusual setup patterns and proposes a closed-loop \u201csetup\u2013monitoring\u2013alert\u201d framework. The approach is intended as an auxiliary alerting tool to support clinical workflows, rather than to replace dosimetric evaluation or clinical decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1733312","type":"journal-article","created":{"date-parts":[[2026,2,5]],"date-time":"2026-02-05T05:23:12Z","timestamp":1770268992000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Research on real-time detection of radiotherapy setup errors and intelligent quality control methods based on artificial intelligence and big data"],"prefix":"10.3389","volume":"16","author":[{"given":"Weixiang","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Radiation Oncology, Ganzhou Cancer Hospital","place":["Ganzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjian","family":"Xiao","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Ganzhou Cancer Hospital","place":["Ganzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangjie","family":"Xiao","sequence":"additional","affiliation":[{"name":"National Cancer Laboratory (South China), Department of Radiation Therapy, Sun Yat-sen University Cancer Center","place":["Guangzhou, Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianlan","family":"Fang","sequence":"additional","affiliation":[{"name":"National Cancer Laboratory (South China), Department of Radiation Therapy, Sun Yat-sen University Cancer Center","place":["Guangzhou, Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobin","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Ganzhou Cancer Hospital","place":["Ganzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongwen","family":"Fang","sequence":"additional","affiliation":[{"name":"National Cancer Laboratory (South China), Department of Radiation Therapy, Sun Yat-sen University Cancer Center","place":["Guangzhou, Guangdong, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1007\/s13246-021-01090-3","article-title":"Organ dose from Varian XI and Varian OBI systems are clinically comparable for pelvic CBCT imaging","volume":"45","author":"Gilling","year":"2022","journal-title":"Phys Eng Sci Med"},{"key":"B2","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1093\/rpd\/ncw285","article-title":"Imaging dose of human organs from kv-cbct in image-guided radiation therapy","volume":"175","author":"Son","year":"2017","journal-title":"Radiat Prot Dosim"},{"key":"B3","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1186\/s13014-018-1109-8","article-title":"Imaging dose and secondary cancer risk in image-guided radiotherapy of pediatric patients","volume":"13","author":"Dzierma","year":"2018","journal-title":"Radiat Oncol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2018.05.030","article-title":"Artificial intelligence in radiation oncology: a specialty-wide disruptive transformation","volume":"129","author":"Thompson","year":"2018","journal-title":"Radiother Oncol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.577620","article-title":"Integration of AI and machine learning in radiotherapy QA","volume":"3","author":"Chan","year":"2020","journal-title":"Front Artif Intell"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacr.2019.06.001","article-title":"Using artificial intelligence to improve the quality and safety of radiation therapy","volume":"16","author":"Pillai","year":"2019","journal-title":"J Am Coll Radiol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1213068","article-title":"A clinical evaluation of the performance of five commercial artificial intelligence contouring systems for radiotherapy","volume":"13","author":"Doolan","year":"2023","journal-title":"Front Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1554-4","article-title":"Anomaly detection based on isolation mechanisms: A survey","volume":"22","author":"Cao","year":"2025","journal-title":"Mach Intell Res"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.3748\/wjg.v28.i5.605","article-title":"Machine learning models and over-fitting considerations","volume":"28","author":"Charilaou","year":"2022","journal-title":"World J Gastroenterol"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e49023","DOI":"10.2196\/49023","article-title":"Practical considerations and applied examples of cross-validation for model development and evaluation in health care","volume":"2","author":"Wilimitis","year":"2023","journal-title":"JMIR Artif Intell"},{"key":"B11","doi-asserted-by":"publisher","first-page":"101234","DOI":"10.1016\/j.adro.2023.101234","article-title":"Augmenting quality assurance measures in treatment review with machine learning in radiation oncology","volume":"8","author":"Pillai","year":"2023","journal-title":"Adv Radiat Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1002\/mp.18013","article-title":"Complexity-based unsupervised machine learning for patient-specific VMAT quality assurance","volume":"52","author":"Cilla","year":"2025","journal-title":"Med Phys"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1002\/mp.13445","article-title":"Radiation therapy quality assurance tasks and tools: the many roles of machine learning","volume":"47","author":"Kalet","year":"2020","journal-title":"Med Phys"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2023.1142947","article-title":"Anomaly detection in radiotherapy plans using deep autoencoder networks","volume":"13","author":"Huang","year":"2023","journal-title":"Front Oncol"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2024.1462745","article-title":"Unsupervised machine learning model for detecting anomalous volumetric modulated arc therapy plans for lung cancer patients","volume":"7","author":"Huang","year":"2024","journal-title":"Front Big Data"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1901.03407","article-title":"Deep learning for anomaly detection: A survey","author":"Chalapathy","year":"","journal-title":"arXiv"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6114","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"","journal-title":"arXiv"},{"key":"B18","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1145\/335191.335388","article-title":"LOF: identifying density-based local outliers","volume":"29","author":"Breunig","year":"2000","journal-title":"SIGMOD Rec"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1109\/ICDM.2008.17","article-title":"Isolation forest","author":"Liu","year":"2008"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1162\/089976601750264965","article-title":"Estimating the support of a high-dimensional distribution","volume":"13","author":"Sch\u00f6lkopf","year":"2001","journal-title":"Neural Comput"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2013.12.026","article-title":"A review of novelty detection","volume":"99","author":"Pimentel","year":"2014","journal-title":"Signal Process"},{"key":"B22","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1145\/3439950","article-title":"Deep learning for anomaly detection: A review","volume":"54","author":"Pang","year":"2021","journal-title":"ACM Comput Surv"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20201289","article-title":"Volumetric modulated arc therapy (VMAT): a review of clinical outcomes-what is the clinical evidence for the most effective implementation","volume":"95","author":"Hunte","year":"2022","journal-title":"Br J Radiol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1118\/1.3690466","article-title":"Quality assurance for image-guided radiation therapy utilizing CT-based technologies: A report of the AAPM TG-179","volume":"39","author":"Bissonnette","year":"2012","journal-title":"Med Phys"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering12080897","article-title":"A Time-Series Approach for Machine Learning-Based Patient-Specific Quality Assurance of Radiosurgery Plans","volume":"12","author":"Buzzi","year":"2025","journal-title":"Bioengineering"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2022.06.011","article-title":"Quality Assurance for AI-Based Applications in Radiation Therapy","volume":"32","author":"Claessens","year":"2022","journal-title":"Semin Radiat Oncol."},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2025.103500","article-title":"MedIAnomaly: A comparative study of anomaly detection in medical images","volume":"102","author":"Yu","year":"2025","journal-title":"Med Image Anal"},{"key":"B28","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-59050-9_12","volume-title":"Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery","author":"Schlegl","year":"2017"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1118\/1.4747261","article-title":"AAPM Task Group 147: Quality assurance for non-radiographic radiotherapy localization and positioning systems","volume":"39","author":"Li","year":"2012","journal-title":"Med Phys"},{"key":"B30","doi-asserted-by":"publisher","first-page":"e15532","DOI":"10.1002\/mp.15532","article-title":"AAPM task group 302: surface-guided radiotherapy (SGRT)","volume":"49","author":"AlHallaq","year":"2022","journal-title":"Med Phys"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1733312\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T09:56:36Z","timestamp":1771926996000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1733312\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,5]]},"references-count":30,"alternative-id":["10.3389\/fonc.2026.1733312"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1733312","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,5]]},"article-number":"1733312"}}