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

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

Automated summary

The study aimed to commission and implement an ACLR model for VMAT patient-specific quality assurance in a multi-institution scenario. Through multi-institutional validation, the model's prediction and classification accuracy were confirmed under different equipment and systems, with established routine QA for clinical use.