Distributed Objective Function Evaluation for Optimization of Radiation Therapy Treatment Plans

TL;DR

This paper presents a distributed computing approach to accelerate radiation therapy treatment plan optimization, achieving significant speedups by parallelizing objective function and gradient calculations across multiple nodes.

Contribution

It introduces a novel distributed method for objective function evaluation in radiation therapy optimization, enabling efficient parallel computation on clinical datasets.

Findings

Achieved 2-3.5x speedup over serial computation

Demonstrated effective parallelization on real clinical cases

Validated approach with the IPOPT solver on the TROTS dataset

Abstract

The modern workflow for radiation therapy treatment planning involves mathematical optimization to determine optimal treatment machine parameters for each patient case. The optimization problems can be computationally expensive, requiring iterative optimization algorithms to solve. In this work, we investigate a method for distributing the calculation of objective functions and gradients for radiation therapy optimization problems across computational nodes. We test our approach on the TROTS dataset -- which consists of optimization problems from real clinical patient cases -- using the IPOPT optimization solver in a leader/follower type approach for parallelization. We show that our approach can utilize multiple computational nodes efficiently, with a speedup of approximately 2-3.5 times compared to the serial version.