A reinforcement learning approach for finding optimal policy of adaptive radiation therapy considering uncertain tumor biological response

作者：

Highlights：

• Proposed a tumor response model to predict weekly tumor volume regression during the course of radiation therapy treatment.

• Developed a reinforcement learning model to find the optimal policy for adaptive radiation therapy treatment (ART).

• Achieved a robust optimal ART treatment plan under high uncertainty in the biological parameters

• Increased the mean biological effective dose (BED) value of the tumor while maintaining the OAR BED within +0.5%.

• Reduced the BED variability in worst cases in an adaptive fractionation scheme.

摘要

•Proposed a tumor response model to predict weekly tumor volume regression during the course of radiation therapy treatment.•Developed a reinforcement learning model to find the optimal policy for adaptive radiation therapy treatment (ART).•Achieved a robust optimal ART treatment plan under high uncertainty in the biological parameters•Increased the mean biological effective dose (BED) value of the tumor while maintaining the OAR BED within +0.5%.•Reduced the BED variability in worst cases in an adaptive fractionation scheme.

论文关键词：Reinforcement learning,Radiotherapy,Biological tumor response,Adaptive radiation therapy.

论文评审过程：Received 1 March 2021, Revised 25 August 2021, Accepted 5 October 2021, Available online 14 October 2021, Version of Record 16 October 2021.

论文官网地址：https://doi.org/10.1016/j.artmed.2021.102193