Multi-Agent Reinforcement Learning Meets Leaf Sequencing in Radiotherapy

TL;DR

This paper introduces a novel multi-agent deep reinforcement learning model called Reinforced Leaf Sequencer (RLS) for leaf sequencing in radiotherapy, aiming to improve efficiency and accuracy over traditional optimization methods.

Contribution

The paper presents the first multi-agent DRL approach for leaf sequencing in radiotherapy, demonstrating improved speed and accuracy compared to existing optimization-based methods.

Findings

Reduced fluence reconstruction errors with RLS

Faster convergence when integrated into optimization pipelines

Promising results in a full AI radiotherapy pipeline

Abstract

In contemporary radiotherapy planning (RTP), a key module leaf sequencing is predominantly addressed by optimization-based approaches. In this paper, we propose a novel deep reinforcement learning (DRL) model termed as Reinforced Leaf Sequencer (RLS) in a multi-agent framework for leaf sequencing. The RLS model offers improvements to time-consuming iterative optimization steps via large-scale training and can control movement patterns through the design of reward mechanisms. We have conducted experiments on four datasets with four metrics and compared our model with a leading optimization sequencer. Our findings reveal that the proposed RLS model can achieve reduced fluence reconstruction errors, and potential faster convergence when integrated in an optimization planner. Additionally, RLS has shown promising results in a full artificial intelligence RTP pipeline. We hope this pioneer multi-agent RL leaf sequencer can foster future research on machine learning for RTP.