Automatic couch position calculation using eclipse scripting for external beam radiotherapy

Improved planning efficiency in multiple brain lesion SRS VMAT cases using Eclipse scripting

Though dosimetry has a multitude of treatment modalities, software, and workflows to aid in the treatment planning process, treatment planners are still responsible for several tedious and monotonous tasks that could decrease their planning efficiency. The purpose of this study was to determine if scripting could improve treatment planning efficiency for multiple brain lesion stereotactic radiosurgery (SRS) volumetric arc therapy cases by reducing planning time commitment. A script was developed for multiple brain lesion SRS cases using Eclipse scripting application programming interface with the intention of improving treatment planning efficiency by creating optimization structures and importing prescription and suggested OS dose metrics to the optimizer. Nine treatment planners were each provided with 3 different multiple brain lesion, single-isocenter SRS cases. Each planner created 2 plans for each case. One of these 2 plans used the SRS script, and the other did not. There were 54 treatment plans developed, totaling 27 plan comparisons. Each of the 54 treatment plans were considered clinically acceptable based on the participating institution's plan quality guidelines. Statistical analyses of planning time commitment with and without the SRS script were performed using RStudio. The mean and median planning times with and without the SRS script were compared using a paired T-test and Wilcoxon Signed Rank test, respectively, and effect size was evaluated using Cohen's classification. Using the SRS script resulted in statistically significant reduction in total contouring time (11.3 vs 2.8 minutes, p < 0.001), optimizer preparation time (7.7 vs 2.1 minutes, p < 0.001), and overall planning time (105.1 vs 77.9 minutes, p < 0.001). This study concluded that scripts developed using Eclipse scripting application programming interface offer an opportunity to improve treatment planning efficiency by reducing the planning time commitment for treatment planners.

Machine learning-based treatment couch parameter prediction in support of surface guided radiation therapy

•

Optimizing surface guided radiation therapy workflow.

•

Machine learning-based automatic treatment couch parameters prediction.

•

quality assurance for patient positioning.

Purpose

A fully independent, machine learning-based automatic treatment couch parameters prediction was developed to support surface guided radiation therapy (SGRT)-based patient positioning protocols. Additionally, this approach also acts as a quality assurance tool for patient positioning.

Materials/Methods

Setup data of 183 patients, divided into four different groups based on used setup devices, was used to calculate the difference between the predicted and the acquired treatment couch value.

Results

Couch parameters can be predicted with high precision μ=0.90,σ=0.92. A significant difference (p < 0.01) between the variances of Lung and Brain patients was found. Outliers were not related to the prediction accuracy, but are due to inconsistencies during initial patient setup.

Conclusion

Couch parameters can be predicted with high accuracy and can be used as starting point for SGRT-based patient positioning. In case of large deviations (>1.5 cm), patient setup has to be verified to optimally use the surface scanning system.