Operator Splitting for Adaptive Radiation Therapy with Nonlinear Health Dynamics

TL;DR

This paper introduces a fast, scalable optimization method for adaptive radiation therapy that accounts for nonlinear patient health dynamics, improving treatment planning by efficiently handling model errors and patient changes.

Contribution

It develops an operator splitting approach combined with ADMM for nonlinear control problems in radiation therapy, with an open-source implementation.

Findings

Method is fast and robust to model errors.

Algorithm scales to large clinical cases.

Demonstrated effectiveness on multiple examples.

Abstract

We present an optimization-based approach to radiation treatment planning over time. Our approach formulates treatment planning as an optimal control problem with nonlinear patient health dynamics derived from the standard linear-quadratic cell survival model. As the formulation is nonconvex, we propose a method for obtaining an approximate solution by solving a sequence of convex optimization problems. This method is fast, efficient, and robust to model error, adapting readily to changes in the patient's health between treatment sessions. Moreover, we show that it can be combined with the operator splitting method ADMM to produce an algorithm that is highly scalable and can handle large clinical cases. We introduce an open-source Python implementation of our algorithm, AdaRad, and demonstrate its performance on several examples.