Knowledge-Based Volumetric Modulated Arc Therapy Treatment Planning for Breast Cancer

Area of Science:

• Medical Physics
• Radiation Oncology
• Computational Biology

Background:

• Volumetric Modulated Arc Therapy (VMAT) is a sophisticated radiotherapy technique.
• Knowledge-based planning (KBP) aims to improve treatment plan quality and efficiency.
• Developing accurate KBP models for breast cancer treatment is crucial for optimizing patient care.

Purpose of the Study:

• To create and validate knowledge-based VMAT models for breast cancer treatments.
• To exclude lymph node irradiation from the treatment planning process.
• To assess the impact of these models on planning time and plan quality.

Main Methods:

• Two knowledge-based VMAT models (left and right breast) were created using RapidPlan™ with 100 manual plans.
• Model performance was evaluated using goodness-of-fit (R², χ²) and goodness-of-estimation (MSE) statistics.
• Validation involved re-optimizing plans with and without the models (closed and open validation).
• Dosimetric parameters for organs at risk (Heart, Lungs, Contralateral Breast) and planning time were analyzed.

Main Results:

• Models demonstrated good estimation power with no overfitting (MSE < 0.05).
• Closed validation showed significant differences for Homolateral Lung and Heart in specific models.
• Open validation yielded no statistically significant differences, indicating robustness.
• A 30% reduction in planning time was observed for beginner planners, with minimal impact on expert planners.

Conclusions:

• Successfully implemented two knowledge-based VMAT models for breast cancer treatment.
• These models reduce optimization planning time and enhance treatment planning efficiency.
• The use of knowledge-based models ensures high-quality treatment plans, irrespective of planner experience.