Ruijie Yang1, Xueying Yang2, Le Wang3, Dingjie Li4, Yuexin Guo5, Ying Li6, Yumin Guan7, Xiangyang Wu8, Shouping Xu9, Shuming Zhang10, Maria F Chan11, Lisheng Geng12, Jing Sui13. 1. Department of Radiation Oncology, Peking University Third Hospital, Beijing, China. 2. School of Physics, Beihang University, Beijing, China. 3. Brainnetome Center & National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China; School of Artificial Intelligence, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Beijing, China. 4. Department of Radiation Therapy, Henan Cancer Hospital, Zhengzhou, China. 5. Department of Radiation Oncology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China. 6. Department of Oncology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China. 7. Department of Radiation Therapy, Yantai Yuhuangding Hospital, Yantai, China. 8. Department of Radiotherapy, Shanxi Provincial Cancer Hospital, Xi'an, China. 9. Department of Radiation Oncology, General Hospital of People's Liberation Army, Beijing, China. 10. Department of Radiation Oncology, Peking University Third Hospital, Beijing, China; Department of Ultrasound, Beijing Hospital, Beijing, China. 11. Medical Physics Department, Memorial Sloan Kettering Cancer Center, New York, NY, United States. 12. School of Physics, Beihang University, Beijing, China; Beijing Advanced Innovation Center for Big Data-Based Precision Medicine, School of Medicine and Engineering, Beihang University, Beijing, China. Electronic address: lisheng.geng@buaa.edu.cn. 13. School of Artificial Intelligence, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Beijing, China; State Key Laboratory of Cognitive Neuroscience and Learning, Beijing Normal University, Beijing, China.. Electronic address: jsui@bnu.edu.cn.
Abstract
BACKGROUND AND PURPOSE: To commission and implement an Autoencoder based Classification-Regression (ACLR) model for VMAT patient-specific quality assurance (PSQA) in a multi-institution scenario. MATERIALS AND METHODS: 1835 VMAT plans from seven institutions were collected for the ACLR model commissioning and multi-institutional validation. We established three scenarios to validate the gamma passing rates (GPRs) prediction and classification accuracy with the ACLR model for different delivery equipment, QA devices, and treatment planning systems (TPS). The prediction performance of the ACLR model was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The classification performance was evaluated using sensitivity and specificity. An independent end-to-end test (E2E) and routine QA of the ACLR model were performed to validate the clinical use of the model. RESULTS: For multi-institution validations, the MAEs were 1.30-2.80% and 2.42-4.60% at 3%/3 mm and 3%/2 mm, respectively, and RMSEs were 1.55-2.98% and 2.83-4.95% at 3%/3 mm and 3%/2 mm, respectively, with different delivery equipment, QA devices, and TPS, while the sensitivity was 90% and specificity was 70.1% at 3%/2 mm. For the E2E, the deviations between the predicted and measured results were within 3%, and the model passed the consistency check for clinical implementation. The predicted results of the model were the same in daily QA, while the deviations between the repeated monthly measured GPRs were all within 2%. CONCLUSIONS: The performance of the ACLR model in multi-institution scenarios was validated on a large scale. Routine QA of the ACLR model was established and the model could be used for VMAT PSQA clinically.
BACKGROUND AND PURPOSE: To commission and implement an Autoencoder based Classification-Regression (ACLR) model for VMAT patient-specific quality assurance (PSQA) in a multi-institution scenario. MATERIALS AND METHODS: 1835 VMAT plans from seven institutions were collected for the ACLR model commissioning and multi-institutional validation. We established three scenarios to validate the gamma passing rates (GPRs) prediction and classification accuracy with the ACLR model for different delivery equipment, QA devices, and treatment planning systems (TPS). The prediction performance of the ACLR model was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The classification performance was evaluated using sensitivity and specificity. An independent end-to-end test (E2E) and routine QA of the ACLR model were performed to validate the clinical use of the model. RESULTS: For multi-institution validations, the MAEs were 1.30-2.80% and 2.42-4.60% at 3%/3 mm and 3%/2 mm, respectively, and RMSEs were 1.55-2.98% and 2.83-4.95% at 3%/3 mm and 3%/2 mm, respectively, with different delivery equipment, QA devices, and TPS, while the sensitivity was 90% and specificity was 70.1% at 3%/2 mm. For the E2E, the deviations between the predicted and measured results were within 3%, and the model passed the consistency check for clinical implementation. The predicted results of the model were the same in daily QA, while the deviations between the repeated monthly measured GPRs were all within 2%. CONCLUSIONS: The performance of the ACLR model in multi-institution scenarios was validated on a large scale. Routine QA of the ACLR model was established and the model could be used for VMAT PSQA clinically.
Authors: Eric E Klein; Joseph Hanley; John Bayouth; Fang-Fang Yin; William Simon; Sean Dresser; Christopher Serago; Francisco Aguirre; Lijun Ma; Bijan Arjomandy; Chihray Liu; Carlos Sandin; Todd Holmes Journal: Med Phys Date: 2009-09 Impact factor: 4.071
Authors: Dao Lam; Xizhe Zhang; Harold Li; Yang Deshan; Brayden Schott; Tianyu Zhao; Weixiong Zhang; Sasa Mutic; Baozhou Sun Journal: Med Phys Date: 2019-08-27 Impact factor: 4.071
Authors: Matthew J Nyflot; Phawis Thammasorn; Landon S Wootton; Eric C Ford; W Art Chaovalitwongse Journal: Med Phys Date: 2018-12-28 Impact factor: 4.071
Authors: Gilmer Valdes; Maria F Chan; Seng Boh Lim; Ryan Scheuermann; Joseph O Deasy; Timothy D Solberg Journal: J Appl Clin Med Phys Date: 2017-08-17 Impact factor: 2.102
Authors: Jennifer B Smilowitz; Indra J Das; Vladimir Feygelman; Benedick A Fraass; Stephen F Kry; Ingrid R Marshall; Dimitris N Mihailidis; Zoubir Ouhib; Timothy Ritter; Michael G Snyder; Lynne Fairobent Journal: J Appl Clin Med Phys Date: 2015-09-08 Impact factor: 2.102