# Sharing a flexible urethral sparing SBRT prostate RapidPlan model and quantifying plan quality via dosimetric scorecard with clinical implementation

## TL;DR

This paper introduces a new model for prostate radiation therapy planning that improves plan quality and consistency using a detailed dosimetric scorecard.

## Contribution

A flexible, dosimetric scorecard-guided KBP model for prostate SBRT is developed and validated.

## Key findings

- The KBP model improved average scorecard scores from 166.2/229 to 197.4/229.
- The model consistently generated high-quality plans for both VMAT and IMRT techniques.
- The model adapts to various dose levels and clinical scenarios, including urethral dose constraints.

## Abstract

To develop and validate a Knowledge-Based Planning (KBP) model for prostate stereotactic body radiation therapy (SBRT) using a comprehensive dosimetric scorecard, aiming to improve plan quality and consistency while meeting the stringent criteria of the Adaptive Radiation Therapy Individualized Approach - Prostate (ARTIA) trial.

A KBP model (ProstateSBRT-ARTIA-SIB40-36 Gy v1.1) was developed using RapidPlan v15.6 with 41 carefully selected prostate SBRT cases. A 35-metric dosimetric scorecard was created to guide the model development and evaluation process. The model was trained iteratively, with the scorecard used to tune optimization objectives and priorities. 10 independent cases were used for validation, testing both VMAT and IMRT beam arrangements.

The KBP model demonstrated significant improvement in plan quality compared to original clinical plans, with the average scorecard score increasing from 166.2/229 to 197.4/229 points. Validation cases showed consistent high-quality plan generation for both VMAT and IMRT techniques. The model exhibited flexibility in adapting to various dose levels and clinical scenarios, including the ability to scale urethral dose constraints.

The dosimetric scorecard-guided KBP model for prostate SBRT demonstrates the potential to generate high-quality treatment plans efficiently and consistently. This approach offers a powerful method for translating complex clinical intent into actionable planning objectives, potentially improving treatment quality and reducing inter-planner variability. Future work will focus on expanding the model’s capabilities, including boosting gross disease volumes and exploring direct optimization based on comprehensive dosimetric scorecards.