Using machine learning to predict gamma passing rate in volumetric-modulated arc therapy treatment plans.

PURPOSE: This study aims to develop an algorithm to predict gamma passing rate (GPR) in the volumetric-modulated arc therapy (VMAT) technique. MATERIALS AND METHODS: A total of 118 clinical VMAT plans, including 28 mediastina, 25 head and neck, 40 brains intensity-modulated radiosurgery, and 25 prostate cases, were created in RayStation treatment planning system for Edge and TrueBeam linacs. In-house scripts were developed to compute Modulation indices such as plan-averaged beam area (PA), plan-averaged beam irregularity (PI), total monitor unit (MU), leaf travel/arc length, mean dose rate variation, and mean gantry speed variation. Pretreatment verifications were performed on ArcCHECK phantom with SNC software. GPR was calculated with 3%/2 mm and 10% threshold. The dataset was randomly split into a training (70%) and a test (30%) dataset. A random forest regression (RFR) model and support vector regression (SVR) with linear kernel were trained to predict GPR using the complexity metrics as input. The prediction performance was evaluated by calculating the mean absolute error (MAE), R2 , and root mean square error (RMSE). RESULTS: RMSEs at γ 3%/2 mm for RFR and SVR were 1.407 ± 0.103 and 1.447 ± 0.121, respectively. MAE was 1.14 ± 0.084 for RFR and 1.101 ± 0.09 for SVR. R2 was equal to 0.703 ± 0.027 and 0.689 ± 0.053 for RFR and SVR, respectively. GPR of 3%/2 mm with a 10% threshold can be predicted with an error smaller than 3% for 94% of plans using RFR and SVR models. The most important metrics that had the greatest impact on how accurately GPR can be predicted were determined to be the PA, PI, and total MU. CONCLUSION: In terms of its prediction values and errors, SVR (linear) appeared to be comparable with RFR for this dataset. Based on our results, the PA, PI, and total MU calculations may be useful in guiding VMAT plan evaluation and ultimately reducing uncertainties in planning and radiation delivery.

Evaluation of parameters affecting gamma passing rate in patient-specific QAs for multiple brain lesions IMRS treatments using ray-station treatment planning system.

PURPOSE: Using intensity-modulated radiosurgery (IMRS) with single isocenter for the treatment of multiple brain lesions has gained acceptance in recent years. One of the challenges of this technique is conducting a patient-specific quality assurance (QA), involving accurate gamma passing rate (GPR) calculations for small and wide spread-out targets. We evaluated effects of parameters such as dose grid and energy on GPR using our clinical IMRS plans. METHODS: Ten patients with total of 40 volumetric modulated arc therapy (VMAT) plans were created in Raystation (V.8A) treatment planning system (TPS) for the Varian Edge Linac using 6 and 10 flattening filter-free (FFF) beams and planned dose grids of 1 mm and 2 mm resulting in four plans with 6-10 targets per patient. All parameters and objectives except dose grid and energy were kept the same in all plans. Next, patient-specific QAs were measured evaluating GPR with 10% threshold, 3%/3 mm objective, and an acceptance criterion of 95%. Modulation factors (MF) and confidence intervals were calculated. Two modes of measurements, standard density (SD) and high density (HD), were used. RESULTS: Generally, plans computed with 1 mm dose grid have higher GPRs than those with 2 mm dose grid for both energies used. The GPRs of 6 FFF plans were higher than those of 10 FFF plans. GPR showed no noticeable difference between HD and SD measurements. Negative correlation between MF and GPR was observed. The HD pass rates fall within the confidence interval of SD. CONCLUSION: Calculated dose grid should be less than or equal to one-third of distance to agreement, thus 1 mm planned dose grid is recommended to reduce artifacts in gamma calculation. GPR of SD and HD measurement modes is almost the same, which indicates that SD mode is clinically preferable for performing patient-specific QAs. According to our results, using 6 FFF beams with 1 mm planned dose grid is more accurate and reliable for dose calculation of IMRS plans.