{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T23:45:26Z","timestamp":1791762326438,"version":"4.3.4"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:00:00Z","timestamp":1783641600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000},"content-version":"vor","delay-in-days":94,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    To predict and classify the gamma passing rate (GPR) for patient-specific quality assurance (PSQA) in VMAT using a deep learning approach based on accelerator dynamic log files. Dynamic log files of 438 VMAT plans were analyzed. GPR were measured by using Delta4. Using dynamic log files as inputs and GPR under five different criteria as outputs, the Resnet-based model was trained by a five-fold cross-validation method. The average absolute error (MAE), mean square error (MSE), root mean square error (RMSE), Spearman\u2019s rank correlation coefficient (Sr), coefficient of determination (R\n                    <jats:sup>2<\/jats:sup>\n                    ), and Classification performance were calculated. In the test dataset, the predictive model demonstrated good agreement with measured GPR values across different gamma criteria, with MAE ranging from 0.59 to 2.05%, RMSE ranging from 1.02 to 3.94%, and R\n                    <jats:sup>2<\/jats:sup>\n                    ranging from 0.76 to 0.88. Significant correlations were observed between predicted and measured GPR values under all gamma criteria (Sr\u2009=\u20090.83\u20130.94,\n                    <jats:italic>p<\/jats:italic>\n                    \u2009&lt;\u20090.001).For the classification models, the accuracy ranged from 0.87 to 0.96, while the AUC values ranged from 0.89 to 0.97 across different gamma criteria, indicating favorable classification performance. We developed a deep learning model that demonstrated promising performance in predicting and classifying GPR for VMAT PSQA. The model is promising as it streamlines the PSQA process and may reduces the associated workload, demonstrating substantial clinical potential.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-61312-0","type":"journal-article","created":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T14:13:44Z","timestamp":1783692824000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep learning for patient-specific quality assurance of volumetric modulated arc therapy: predicting gamma passing rate based on accelerator dynamic log files"],"prefix":"10.1038","volume":"16","author":[{"given":"Haihua","family":"Lei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Te","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qianhong","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenhang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxiang","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangshan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxin","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yihan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianwen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodong","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuangui","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,10]]},"reference":[{"key":"61312_CR1","doi-asserted-by":"publisher","first-page":"e53","DOI":"10.1002\/mp.12810","volume":"45","author":"M Miften","year":"2018","unstructured":"Miften, M. et al. Tolerance limits and methodologies for IMRT measurement-based verification QA: Recommendations of AAPM Task Group No. 218. Med. Phys. 45, e53\u2013e83 (2018).","journal-title":"Med. Phys."},{"key":"61312_CR2","doi-asserted-by":"publisher","first-page":"5359","DOI":"10.1118\/1.3238104","volume":"36","author":"GA Ezzell","year":"2009","unstructured":"Ezzell, G. A. et al. IMRT commissioning: Multiple institution planning and dosimetry comparisons, a report from AAPM Task Group 119. Med. Phys. 36, 5359\u20135373 (2009).","journal-title":"Med. Phys."},{"key":"61312_CR3","doi-asserted-by":"publisher","first-page":"1813","DOI":"10.1118\/1.3117563","volume":"36","author":"D L\u00e9tourneau","year":"2009","unstructured":"L\u00e9tourneau, D., Publicover, J., Kozelka, J., Moseley, D. J. & Jaffray, D. A. Novel dosimetric phantom for quality assurance of volumetric modulated arc therapy. Med. Phys. 36, 1813\u20131821 (2009).","journal-title":"Med. Phys."},{"key":"61312_CR4","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1118\/1.598248","volume":"25","author":"DA Low","year":"1998","unstructured":"Low, D. A., Harms, W. B., Mutic, S. & Purdy, J. A. A technique for the quantitative evaluation of dose distributions. Med. Phys. 25, 656\u2013661 (1998).","journal-title":"Med. Phys."},{"key":"61312_CR5","doi-asserted-by":"publisher","first-page":"2159","DOI":"10.1118\/1.1500398","volume":"29","author":"AJ Olch","year":"2002","unstructured":"Olch, A. J. Dosimetric performance of an enhanced dose range radiographic film for intensity-modulated radiation therapy quality assurance. Med. Phys. 29, 2159\u20132168 (2002).","journal-title":"Med. Phys."},{"key":"61312_CR6","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.radonc.2008.07.008","volume":"88","author":"W Van Elmpt","year":"2008","unstructured":"Van Elmpt, W. et al. A literature review of electronic portal imaging for radiotherapy dosimetry. Radiother. Oncol. 88, 289\u2013309 (2008).","journal-title":"Radiother. Oncol."},{"key":"61312_CR7","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/S0167-8140(02)00174-3","volume":"65","author":"A Van Esch","year":"2002","unstructured":"Van Esch, A. et al. Acceptance tests and quality control (QC) procedures for the clinical implementation of intensity modulated radiotherapy (IMRT) using inverse planning and the sliding window technique: Experience from five radiotherapy departments. Radiother. Oncol. 65, 53\u201370 (2002).","journal-title":"Radiother. Oncol."},{"key":"61312_CR8","doi-asserted-by":"publisher","first-page":"103204","DOI":"10.1016\/j.ejmp.2023.103204","volume":"117","author":"W Sun","year":"2024","unstructured":"Sun, W. et al. Machine learning-based ensemble prediction model for the gamma passing rate of VMAT-SBRT plan. Phys. Med. 117, 103204 (2024).","journal-title":"Phys. Med."},{"key":"61312_CR9","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1016\/j.radonc.2020.07.031","volume":"153","author":"H Hirashima","year":"2020","unstructured":"Hirashima, H. et al. Improvement of prediction and classification performance for gamma passing rate by using plan complexity and dosiomics features. Radiother. Oncol. 153, 250\u2013257 (2020).","journal-title":"Radiother. Oncol."},{"key":"61312_CR10","doi-asserted-by":"publisher","first-page":"893","DOI":"10.1016\/j.ijrobp.2019.07.049","volume":"105","author":"J Li","year":"2019","unstructured":"Li, J. et al. Machine learning for patient-specific quality assurance of VMAT: Prediction and classification accuracy. Int. J. Radiat. Oncol. Biol. Phys. 105, 893\u2013902 (2019).","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"61312_CR11","doi-asserted-by":"publisher","first-page":"e2180","DOI":"10.7717\/peerj-cs.2180","volume":"10","author":"SY Chin","year":"2024","unstructured":"Chin, S. Y. et al. Bacterial image analysis using multi-task deep learning approaches for clinical microscopy. PeerJ Comput. Sci. 10, e2180 (2024).","journal-title":"PeerJ Comput. Sci."},{"key":"61312_CR12","doi-asserted-by":"publisher","first-page":"e2082","DOI":"10.7717\/peerj-cs.2082","volume":"10","author":"JR Teoh","year":"2024","unstructured":"Teoh, J. R., Hasikin, K., Lai, K. W., Wu, X. & Li, C. Enhancing early breast cancer diagnosis through automated microcalcification detection using an optimized ensemble deep learning framework. PeerJ Comput. Sci. 10, e2082 (2024).","journal-title":"PeerJ Comput. Sci."},{"key":"61312_CR13","doi-asserted-by":"publisher","first-page":"11142","DOI":"10.1002\/int.23036","volume":"37","author":"H Wang","year":"2022","unstructured":"Wang, H., Zhang, X., Xia, Y. & Wu, X. A differential privacy-preserving deep learning caching framework for heterogeneous communication network systems. Int. J. Intell. Syst. 37, 11142\u201311166 (2022).","journal-title":"Int. J. Intell. Syst."},{"key":"61312_CR14","doi-asserted-by":"publisher","first-page":"235023","DOI":"10.1088\/1361-6560\/abb31c","volume":"65","author":"L Wang","year":"2020","unstructured":"Wang, L. et al. Multi-task autoencoder based classification-regression model for patient-specific VMAT QA. Phys. Med. Biol. 65, 235023 (2020).","journal-title":"Phys. Med. Biol."},{"key":"61312_CR15","doi-asserted-by":"publisher","first-page":"2672","DOI":"10.1002\/mp.12890","volume":"45","author":"Y Interian","year":"2018","unstructured":"Interian, Y. et al. Deep nets vs expert designed features in medical physics: An IMRT QA case study. Med. Phys. 45, 2672\u20132680 (2018).","journal-title":"Med. Phys."},{"key":"61312_CR16","doi-asserted-by":"publisher","first-page":"110593","DOI":"10.1016\/j.radonc.2024.110593","volume":"202","author":"Y Liu","year":"2025","unstructured":"Liu, Y. et al. A feasibility study of dose-band prediction in radiation therapy: Predicting a spectrum of plan dose. Radiother. Oncol. 202, 110593 (2025).","journal-title":"Radiother. Oncol."},{"key":"61312_CR17","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1007\/s13246-022-01172-w","volume":"45","author":"T Matsuura","year":"2022","unstructured":"Matsuura, T. et al. Predictive gamma passing rate of 3D detector array-based volumetric modulated arc therapy quality assurance for prostate cancer via deep learning. Phys. Eng. Sci. Med. 45, 1073\u20131081 (2022).","journal-title":"Phys. Eng. Sci. Med."},{"key":"61312_CR18","doi-asserted-by":"publisher","first-page":"2488","DOI":"10.1002\/mp.16210","volume":"50","author":"T Matsuura","year":"2023","unstructured":"Matsuura, T. et al. A synthesized gamma distribution-based patient-specific VMAT QA using a generative adversarial network. Med. Phys. 50, 2488\u20132498 (2023).","journal-title":"Med. Phys."},{"key":"61312_CR19","doi-asserted-by":"publisher","first-page":"7891","DOI":"10.1002\/mp.16567","volume":"50","author":"S Yoganathan","year":"2023","unstructured":"Yoganathan, S. et al. Virtual pretreatment patient-specific quality assurance of volumetric modulated arc therapy using deep learning. Med. Phys. 50, 7891\u20137903 (2023).","journal-title":"Med. Phys."},{"key":"61312_CR20","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1002\/mp.14682","volume":"48","author":"S Tomori","year":"2021","unstructured":"Tomori, S. et al. Systematic method for a deep learning-based prediction model for gamma evaluation in patient-specific quality assurance of volumetric modulated arc therapy. Med. Phys. 48, 1003\u20131018 (2021).","journal-title":"Med. Phys."},{"key":"61312_CR21","doi-asserted-by":"publisher","first-page":"104500","DOI":"10.1016\/j.ejmp.2024.104500","volume":"125","author":"G Li","year":"2024","unstructured":"Li, G. et al. Deep learning for patient-specific quality assurance of volumetric modulated arc therapy: Prediction accuracy and cost-sensitive classification performance. Phys. Med. 125, 104500 (2024).","journal-title":"Phys. Med."},{"key":"61312_CR22","doi-asserted-by":"publisher","first-page":"20150489","DOI":"10.1259\/bjr.20150489","volume":"89","author":"CK McGarry","year":"2016","unstructured":"McGarry, C. K. et al. The use of log file analysis within VMAT audits. Br. J. Radiol. 89, 20150489 (2016).","journal-title":"Br. J. Radiol."},{"key":"61312_CR23","doi-asserted-by":"publisher","first-page":"e0278422","DOI":"10.1371\/journal.pone.0278422","volume":"17","author":"J Deng","year":"2022","unstructured":"Deng, J., Huang, Y., Wu, X., Hong, Y. & Zhao, Y. Comparison of dosimetric effects of MLC positional errors on VMAT and IMRT plans for SBRT radiotherapy in non-small cell lung cancer. PLoS ONE 17, e0278422 (2022).","journal-title":"PLoS ONE"},{"key":"61312_CR24","doi-asserted-by":"publisher","first-page":"153303382211048","DOI":"10.1177\/15330338221104881","volume":"21","author":"Y Huang","year":"2022","unstructured":"Huang, Y. et al. Deep learning for patient-specific quality assurance: Predicting gamma passing rates for IMRT based on delivery fluence informed by log files. Technol. Cancer Res. Treat. 21, 153303382211048 (2022).","journal-title":"Technol. Cancer Res. Treat."},{"key":"61312_CR25","volume-title":"Eclipse Photon and Electron Algorithms Reference Guide","author":"H Way","year":"2015","unstructured":"Way, H. et al. Eclipse Photon and Electron Algorithms Reference Guide (Varian Medical Systems, Inc, 2015)."},{"key":"61312_CR26","first-page":"100062028","volume-title":"Millennium MLC Instructions for Use","author":"H Way","year":"2014","unstructured":"Way, H. et al. Millennium MLC Instructions for Use 100062028\u2013100062102 (Varian Medical Systems, Inc., 2014)."},{"key":"61312_CR27","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.patcog.2017.10.013","volume":"77","author":"J Gu","year":"2018","unstructured":"Gu, J. et al. Recent advances in convolutional neural networks. Pattern Recognit. 77, 321\u2013341 (2018).","journal-title":"Pattern Recognit."},{"key":"61312_CR28","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1080\/10485252.2015.1010532","volume":"27","author":"Y Jung","year":"2015","unstructured":"Jung, Y. & Hu, J. A K-fold averaging cross-validation procedure. J. Nonparametric Stat. 27, 167\u2013179 (2015).","journal-title":"J. Nonparametric Stat."},{"key":"61312_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-51260-6","author":"Y Wei","year":"2024","unstructured":"Wei, Y. et al. Focal liver lesion diagnosis with deep learning and multistage CT imaging. Nat. Commun. https:\/\/doi.org\/10.1038\/s41467-024-51260-6 (2024).","journal-title":"Nat. Commun."},{"key":"61312_CR30","doi-asserted-by":"publisher","first-page":"1509449","DOI":"10.3389\/fonc.2025.1509449","volume":"15","author":"J Miao","year":"2025","unstructured":"Miao, J., Xu, Y., Men, K. & Dai, J. A feasibility study of deep learning prediction model for VMAT patient-specific QA. Front. Oncol. 15, 1509449 (2025).","journal-title":"Front. Oncol."},{"key":"61312_CR31","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1002\/mp.17485","volume":"52","author":"X Cui","year":"2025","unstructured":"Cui, X. et al. A StarGAN and transformer-based hybrid classification-regression model for multi-institution VMAT patient-specific quality assurance. Med. Phys. 52, 685\u2013702 (2025).","journal-title":"Med. Phys."},{"key":"61312_CR32","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1120\/jacmp.v16i5.5515","volume":"16","author":"K Nithiyanantham","year":"2015","unstructured":"Nithiyanantham, K. et al. Analysis of direct clinical consequences of MLC positional errors in volumetric-modulated arc therapy using 3D dosimetry system. J. Appl. Clin. Med. Phys. 16, 296\u2013305 (2015).","journal-title":"J. Appl. Clin. Med. Phys."},{"key":"61312_CR33","doi-asserted-by":"publisher","first-page":"111722","DOI":"10.1118\/1.4826166","volume":"40","author":"BE Nelms","year":"2013","unstructured":"Nelms, B. E. et al. Evaluating IMRT and VMAT dose accuracy: Practical examples of failure to detect systematic errors when applying a commonly used metric and action levels. Med. Phys. 40, 111722 (2013).","journal-title":"Med. Phys."},{"key":"61312_CR34","doi-asserted-by":"publisher","first-page":"1982","DOI":"10.1118\/1.4943953","volume":"43","author":"JM Steers","year":"2016","unstructured":"Steers, J. M. & Fraass, B. A. IMRT QA: Selecting gamma criteria based on error detection sensitivity. Med. Phys. 43, 1982\u20131994 (2016).","journal-title":"Med. Phys."},{"key":"61312_CR35","doi-asserted-by":"publisher","first-page":"015013","DOI":"10.1088\/2057-1976\/ad124a","volume":"10","author":"D Tardi","year":"2024","unstructured":"Tardi, D. et al. Analysis of dose distribution reproducibility based on a fluence map of in vivo transit dose using an electronic portal imaging device. Biomed. Phys. Eng. Express 10, 015013 (2024).","journal-title":"Biomed. Phys. Eng. Express"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61312-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61312-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61312-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,11]],"date-time":"2026-10-11T23:05:54Z","timestamp":1791759954000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-61312-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,10]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["61312"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-61312-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,10]]},"assertion":[{"value":"24 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The study protocol was reviewed and approved by the Medical Ethics Committee of Fujian Medical University Union Hospital (Approval No. 2025KY148). As a retrospective analysis without any intervention in patient treatment, the Ethics Committees waived the requirement for individual informed consent. All procedures were performed in compliance with the Declaration of Helsinki, and patient confidentiality was strictly protected.","order":2,"name":"Ethics","label":"Ethical statement","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"31758"}}