Real-time control of proton therapy delivery using two-stage stochastic programming

As an advanced radiation treatment, proton therapy is a highly targeted treatment for tumors and can minimize damage to surrounding normal tissues. Its dose-depth curve is helpful for improving patient treatment outcomes, making proton therapy a preferred choice for patients. A typical proton therapy facility consists of one proton accelerator and multiple gantries, and at any time the proton accelerator can only serve one gantry. Such a resource sharing feature of the proton therapy delivery makes patients wait on treatment couches of gantries. Long waiting time compromises treatment precision, causes patient muscle injuries, and reduces the delivery efficiency. To address this challenge, we propose a two-stage stochastic programming model for real-time control of proton therapy delivery. The model considers uncertainties of durations in each step of the proton therapy delivery and optimizes patient waiting times and resource utilization. The two-stage stochastic programming model is capable of managing uncertainties, providing more flexible and effective control solutions than the traditional first-come-first-served policy. Numerical experiments show improved performance of the proposed method. Integrating two-stage stochastic programming into the proton therapy delivery control provides substantial enhancements for current proton therapy systems in terms of both care quality and system efficiency.