Session Item

Radiation therapy treatment planning is a time-consuming and labor-intensive process. Typically, planners perform manual, iterative adjustments of hyperparameters until a clinically acceptable plan has been generated. To automate the treatment planning process, we propose a meta-optimization framework, called MetaPlanner (MP). 

The proposed MP algorithm performs optimization of treatment planning hyperparameters using a two-loop optimization approach. In the outer loop, the algorithm uses a derivative-free method (i.e. parallel NelderMead simplex search) to search for weight configurations that minimize a meta-scoring function. In the inner loop, traditional inverse planning optimization (i.e. fluence map optimization) is performed. Meta-scoring is performed by constructing a tier list to rank planner preferences and mimic the clinical decision-making process. The source code for the MP algorithm is publicly available through github (https://github.com/chh105/MetaPlanner).

The proposed MP method is retrospectively evaluated on two datasets (21 prostate cases and 6 head and neck cases) collected as part of clinical workflow. MP is applied to both IMRT and VMAT planning and compared to a baseline of manual VMAT plans. MP in both IMRT and VMAT scenarios has comparable or better performance than manual VMAT planning for all evaluated metrics (e.g. dose conformity, dose homogeneity, OAR sparing, etc.).

The MP method is a general framework for automated treatment planning with the potential to substantially reduce planning workload while maintaining or improving plan quality.