Clinical Implementation of Deep Learning-Based VMAT Patient-Specific QA
X Yang*1,2, L Wang3, D Li4, Y Guo5, Y Li6, Y Guan7, X Wu8, S Xu9, S Zhang10, M Chan11,R Yang1, L Geng2, J Sui3 (1)Peking University Third Hospital, Beijing, CN, (2)Beihang university, Beijing, CN, (3)Institute of Automation, Chinese Academy of Sciences, Beijing, CN, (4)Henan Cancer Hospital, Zhengzhou, Henan, CN, (5)The First Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan, CN, (6)The First Affiliated Hospital of Chongqing Medical University, Chongqing, CN, (7)Yantai Yuhuangding Hospital, Yantai, Shandong, CN, (8)Shanxi Provincial Cancer Hospital, Xi'an, Shanxi, CN, (9)General Hospital of People's Liberation Army, Beijing, CN, (10)Beijing Hospital, Beijing, CN, (11)Memorial Sloan Kettering Cancer Center, New York, NY
Presentations
WE-IePD-TRACK 6-4 (Wednesday, 7/28/2021) 5:30 PM - 6:00 PM [Eastern Time (GMT-4)]
Purpose: To commission and implement an Autoencoder based Classification-Regression (ACLR) model for VMAT patient-specific quality assurance (PSQA) in a multi-institution scenario.
Methods: 1836 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%/3mm and 3%/2mm, respectively, and RMSEs were 1.55-2.98% and 2.83-4.95% at 3%/3mm and 3%/2mm, respectively, with different delivery equipment, QA devices, and TPS, while the sensitivity was 90% and specificity was 70.1% at 3%/2mm. For the E2E, the deviations between the predicted and measured results were within 3%, and the model passed the consistency check for clinical implementation. And 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%.
Conclusion: 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.
ePosters
Keywords
Quality Assurance, Commissioning, Validation
Taxonomy
IM/TH- Formal Quality Management Tools: Machine Learning
Contact Email