High-dimensional automated radiation therapy treatment planning via Bayesian optimization

Abstract

Purpose: Radiation therapy treatment planning can be viewed as an iterative hyperparameter tuning process to balance conflicting clinical goals. In this work, we investigated the performance of modern Bayesian optimization (BO) methods on automated treatment planning problems in high-dimensional settings.

Methods: Twenty locally advanced rectal cancer patients treated with intensity-modulated radiation therapy (IMRT) were retrospectively selected as test cases. The adjustable planning parameters included both dose objectives and their corresponding weights. We implemented an automated treatment planning framework and tested the performance of two BO methods on the treatment planning task: one standard BO method (Gaussian Process with Expected Improvement [GPEI]) and one BO method dedicated to high-dimensional problems (Sparse Axis Aligned Subspace BO [SAAS-BO]). Another derivative-free method (Nelder-Mead simplex search) and the random tuning method were also included as baselines. The four automated methods' plan quality and planning efficiency were compared with the clinical plans regarding target coverage and organs at risk (OAR) sparing. The predictive models in both BO methods were compared to analyze the different search patterns of the two BO methods.

Results: For the target structures, the SAAS-BO plans achieved comparable hot spot control ( $p=0.43$ ) and homogeneity ( $p=0.96$ ) with the clinical plans, significantly better than the GPEI and Nelder-Mead plans ( $p<0.05$ ). Both SAAS-BO and GPEI plans significantly outperformed the clinical plans in conformity and dose spillage ( $p<0.05$ ). Compared with the clinical plans, the treatment plans generated by the four automated methods all made reductions in evaluated dosimetric indices for the femoral head and the bladder. The Nelder-Mead plans achieved similar plan quality scores compared with the BO plans, but exhibited poorer control in the target hot spot and dose spillage. The analysis of the underlying predictive models has shown that both BO methods have identified similar sensitive planning parameters.

Conclusions: This work implemented a BO-based hyperparameter tuning framework for automated treatment planning. Both tested BO methods were able to produce high-quality treatment plans and reduce the workload of treatment planners. The model analysis also confirmed the intrinsic low dimensionality of the tested treatment planning problems.

Keywords: Bayesian Optimization; automated treatment planning; hyperparameter tuning.