Multi-objective optimization of radiotherapy: distributed Q-learning and agent-based simulation

Abstract Radiotherapy (RT) is among the regular techniques for the treatment of cancerous tumours. Many of cancer patients are treated by this manner. Treatment planning is the most important phase in RT and it plays a key role in therapy quality achievement. As the goal of RT is to irradiate the tumour with adequately high levels of radiation while sparing neighbouring healthy tissues as much as possible, it is a multi-objective problem naturally. In this study, we propose an agent-based model of vascular tumour growth and also effects of RT. Next, we use multi-objective distributed Q-learning algorithm to find Pareto-optimal solutions for calculating RT dynamic dose. We consider multiple objectives and each group of optimizer agents attempt to optimise one of them, iteratively. At the end of each iteration, agents compromise the solutions to shape the Pareto-front of multi-objective problem. We propose a new approach by defining three schemes of treatment planning created based on different combinations of our objectives namely invasive, conservative and moderate. In invasive scheme, we enforce killing cancer cells and pay less attention about irradiation effects on normal cells. In conservative scheme, we take more care of normal cells and try to destroy cancer cells in a less stressed manner. The moderate scheme stands in between. For implementation, each of these schemes is handled by one agent in MDQ-learning algorithm and the Pareto optimal solutions are discovered by the collaboration of agents. By applying this methodology, we could reach Pareto treatment plans through building different scenarios of tumour growth and RT. The proposed multi-objective optimisation algorithm generates robust solutions and finds the best treatment plan for different conditions.