Machine Learning to Generate Adjustable Dose Distributions in Head-and-Neck Cancer Radiation Therapy

TL;DR

This paper introduces a machine learning approach that generates adjustable 3D dose distributions for head-and-neck cancer radiation therapy, enabling real-time customization of doses to balance organ risks.

Contribution

It presents a novel pair of models per organ-at-risk that allow dynamic dose adjustments, capturing clinical trade-offs within the training data.

Findings

Models produce clinically reasonable dose trade-offs.

Adjustable distributions enable real-time dose customization.

Method captures inherent clinical dose trade-offs.

Abstract

In this work, we propose a Machine Learning model that generates an adjustable 3D dose distribution for external beam radiation therapy for head-and-neck cancer treatments. In contrast to existing Machine Learning methods that provide a single model, we create pairs of models for each organ-at-risk, namely lower-extreme and upper-extreme models. These model pairs for an organ-at-risk propose doses that give lower and higher doses to that organ-at-risk, while also encapsulating the dose trade-off to other organs-at-risk. By weighting and combining the model pairs for all organs-at-risk, we are able to dynamically create adjustable dose distributions that can be used, in real-time, to move doses between organs-at-risk, thereby customizing the dose distribution to the needs of a particular patient. We leverage a key observation that the training data set inherently contains the clinical trade-offs. We show that the adjustable distributions are able to provide reasonable clinical dose latitude in the trade-off of doses between organs-at-risk.