Latent Space Arc Therapy Optimization

TL;DR

This paper introduces a deep learning approach to reduce the dimensionality of arc therapy plans, enabling faster and more efficient optimization for radiation treatment planning.

Contribution

It presents a novel method that uses unsupervised deep learning to lower the effective dimension of treatment plans, improving optimization speed and efficiency.

Findings

Faster planning times compared to traditional methods

Reduced overparameterization improves optimization efficiency

Low-dimensional representations maintain plan quality

Abstract

Volumetric modulated arc therapy planning is a challenging problem in high-dimensional, non-convex optimization. Traditionally, heuristics such as fluence-map-optimization-informed segment initialization use locally optimal solutions to begin the search of the full arc therapy plan space from a reasonable starting point. These routines facilitate arc therapy optimization such that clinically satisfactory radiation treatment plans can be created in about 10 minutes. However, current optimization algorithms favor solutions near their initialization point and are slower than necessary due to plan overparameterization. In this work, arc therapy overparameterization is addressed by reducing the effective dimension of treatment plans with unsupervised deep learning. An optimization engine is then built based on low-dimensional arc representations which facilitates faster planning times.