Deep learning for patient-specific quality assurance of volumetric modulated arc therapy: Prediction accuracy and cost-sensitive classification performance.

Abstract

To evaluate a deep learning model's performance in predicting and classifying patient-specific quality assurance (PSQA) results for volumetric modulated arc therapy (VMAT), aiming to streamline PSQA workflows and reduce the onsite measurement workload. A total of 761 VMAT plans were analyzed using 3D-MResNet to process multileaf collimator images and monitor unit data, with the gamma passing rate (GPR) as the output. Thresholds for the predicted GPR (Th-p) and measured GPR (Th-m) were established to aid in PSQA decision-making, using cost curves and error rates to assess classification performance. The mean absolute errors of the model for the test set were 1.63% and 2.38% at 3%/2 mm and 2%/2 mm, respectively. For the classification of the PSQA results, Th-m was 88.3% at 2%/2 mm and 93.3% at 3%/2 mm. The lowest cost-sensitive error rates of 0.0127 and 0.0925 were obtained when Th-p was set as 91.2% at 2%/2 mm and 96.4% at 3%/2 mm, respectively. Additionally, the 2%/2 mm classifier also achieved a lower total expected cost of 0.069 compared with 0.110 for the 3%/2 mm classifier. The deep learning classifier under the 2%/2 mm gamma criterion had a sensitivity and specificity of 100% (10/10) and 83.5% (167/200), respectively, for the test set. The developed 3D-MResNet model can accurately predict and classify PSQA results based on VMAT plans. The introduction of a deep learning model into the PSQA workflow has considerable potential for improving the VMAT PSQA process and reducing workloads.