Automatic VMAT planning for post-operative prostate cancer cases using particle swarm optimization: A proof of
Luise A Künzel1, Sara Leibfarth1, Oliver S Dohm2
1Section for Biomedical Physic, Department for Radiation Oncology, University Hospital Tübingen, Hoppe-Seyler-Str. 3, 72076 Tübingen, Germany.
Summary
Particle Swarm Optimization (PSO) shows potential for fully automatic VMAT radiotherapy planning, generating comparable plans to manual methods. Further research is needed for clinical integration of this automated radiotherapy approach.
Area of Science:
- Medical Physics
- Radiotherapy Optimization
- Computational Intelligence
Background:
- Volumetric Modulated Arc Therapy (VMAT) is a complex radiotherapy technique requiring precise treatment planning.
- Manual VMAT planning is time-consuming and relies heavily on planner expertise.
- Automated planning methods aim to improve efficiency and consistency in radiotherapy.
Purpose of the Study:
- To evaluate the efficacy of Particle Swarm Optimization (PSO) for fully automatic VMAT radiotherapy treatment planning.
- To compare the quality of PSO-generated VMAT plans against manually optimized plans.
Main Methods:
- Particle Swarm Optimization (PSO) was employed to search for optimal VMAT plans by iteratively refining a population of candidate solutions.
- A Plan Quality Score (PQS), based on dose-volume histogram (DVH) parameters, was developed for evaluating and selecting the best treatment plan.
- The automated PSO planning method was retrospectively applied to 10 prostate cancer cases, comparing results to manually created VMAT plans.
Main Results:
- PSO successfully generated VMAT plans comparable to manual plans in 9 out of 10 cases.
- PSO plans demonstrated significantly lower rectal doses (D2% = 66.1 Gy) compared to manual plans (D2% = 67.0 Gy).
- Plan Quality Scores (PQS) were higher for PSO-generated plans, indicating superior quality compared to manual plans.
Conclusions:
- Particle Swarm Optimization (PSO) enables fully automatic VMAT plan generation with quality comparable to manual optimization.
- Further investigation into PSO-specific parameter tuning and PQS refinement is necessary for clinical implementation.
- Automated VMAT planning using PSO offers a promising avenue for improving radiotherapy treatment planning efficiency and quality.
