Commissioning and clinical implementation of an Autoencoder based Classification-Regression model for VMAT patient-specific QA in a multi-institution scenario

作者全名："Yang, Ruijie; Yang, Xueying; Wang, Le; Li, Dingjie; Guo, Yuexin; Li, Ying; Guan, Yumin; Wu, Xiangyang; Xu, Shouping; Zhang, Shuming; Chan, Maria F.; Geng, Lisheng; Sui, Jing"

作者地址："[Yang, Ruijie; Zhang, Shuming] Peking Univ Third Hosp, Dept Radiat Oncol, Beijing, Peoples R China; [Yang, Xueying; Geng, Lisheng] Beihang Univ, Sch Phys, 9 Nansan St,Shahe Higher Educ Pk, Beijing 102206, Peoples R China; [Wang, Le] Chinese Acad Sci, Inst Automat, Brainnetome Ctr, Beijing, Peoples R China; [Wang, Le] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China; [Wang, Le; Sui, Jing] Univ Chinese Acad Sci, Chinese Acad Sci, Sch Artificial Intelligence, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China; [Li, Dingjie] Henan Canc Hosp, Dept Radiat Therapy, Zhengzhou, Peoples R China; [Guo, Yuexin] Zhengzhou Univ, Dept Radiat Oncol, Affiliated Hosp 1, Zhengzhou, Peoples R China; [Li, Ying] Chongqing Med Univ, Dept Oncol, Affiliated Hosp 1, Chongqing, Peoples R China; [Guan, Yumin] Yantai Yuhuangding Hosp, Dept Radiat Therapy, Yantai, Peoples R China; [Wu, Xiangyang] Shanxi Prov Canc Hosp, Dept Radiotherapy, Xian, Peoples R China; [Xu, Shouping] Gen Hosp Peoples Liberat Army, Dept Radiat Oncol, Beijing, Peoples R China; [Zhang, Shuming] Beijing Hosp, Dept Ultrasound, Beijing, Peoples R China; [Chan, Maria F.] Mem Sloan Kettering Canc Ctr, Dept Med Phys, New York, NY 10021 USA; [Geng, Lisheng] Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Sch Med & Engn, Beijing, Peoples R China; [Sui, Jing] Beijing Normal Univ, State Key Lab Cognit Neurosci & Learning, Beijing, Peoples R China"

通信作者："Geng, LS (corresponding author), Beihang Univ, Sch Phys, 9 Nansan St,Shahe Higher Educ Pk, Beijing 102206, Peoples R China.; Sui, J (corresponding author), Univ Chinese Acad Sci, Chinese Acad Sci, Sch Artificial Intelligence, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China."

来源：RADIOTHERAPY AND ONCOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:000678802700032

JCR分区：Q1

影响因子：5.7

年份：2021

卷号：161

期号：　

开始页：230

结束页：240

文献类型：Article

关键词：Machine learning; VMAT patient-specific QA; Multi-institution validation; Commissioning; Clinical implementation

摘要："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 com-missioning 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, respec-tively, with different delivery equipment, QA devices, and TPS, while the sensitivity was 90% and speci-ficity 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 mea-sured 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. (c) 2021 Elsevier B.V. All rights reserved. Radiotherapy and Oncology 161 (2021) 230-240"

基金机构："National Key Research and Development Program [2020YFE020088]; National Natural Science Foundation of ChinaNational Natural Science Foundation of China (NSFC) [11735003, 11975041, 11961141004, 61773380, 82022035, 81071237]; Beijing Municipal Commission of Science and Technology Collabo-rative Innovation Project [Z201100005620012, Z181100001518005]; Beijing Natural Science FoundationBeijing Natural Science Foundation [7202223]; Capital's Funds for Health Improvement and Research [20202Z40919]; fundamental Research Funds for the Central UniversitiesFundamental Research Funds for the Central Universities; Key project of Henan Provincial Department of Education [20B320035]; NIH/NCI P30 Cancer Center Support Grant [CA008748]; China International Medical Foundation [HDRS2020030206]"

基金资助正文："This work was partly supported by National Key Research and Development Program (2020YFE020088) , National Natural Science Foundation of China (No. 11735003, No. 11975041, No. 11961141004, No. 61773380, No. 82022035, and No. 81071237) , Beijing Municipal Commission of Science and Technology Collabo-rative Innovation Project (Z201100005620012 and Z181100001518005) , Beijing Natural Science Foundation (No. 7202223) , Capital's Funds for Health Improvement and Research (20202Z40919) , the fundamental Research Funds for the Central Universities, Key project of Henan Provincial Department of Educa-tion (20B320035) , the NIH/NCI P30 Cancer Center Support Grant (No. CA008748) , and China International Medical Foundation (HDRS2020030206) . The funding organizations had no role in the design and con-duct of the study; collection, management, analysis, and interpre-tation of the data; preparation, review, or approval of the manuscript; and decision to submit the manuscript for publication."