Probabilistic dose prediction using mixture density networks for automated radiation therapy treatment planning

TL;DR

This paper demonstrates that mixture density networks can predict dose distributions in radiation therapy, capturing uncertainty and supporting clinical decision-making, thereby enhancing automated treatment planning.

Contribution

It introduces the application of mixture density networks for probabilistic dose prediction in radiation therapy, reflecting uncertainties and aiding clinical tradeoff management.

Findings

MDNs produce accurate dose distribution predictions.

Predicted modes align well with ground truth data.

MDN-based dose mimicking creates deliverable treatment plans.

Abstract

We demonstrate the application of mixture density networks (MDNs) in the context of automated radiation therapy treatment planning. It is shown that an MDN can produce good predictions of dose distributions as well as reflect uncertain decision making associated with inherently conflicting clinical tradeoffs, in contrast to deterministic methods previously investigated in literature. A two-component Gaussian MDN is trained on a set of treatment plans for postoperative prostate patients with varying extents to which rectum dose sparing was prioritized over target coverage. Examination on a test set of patients shows that the predicted modes follow their respective ground truths well both spatially and in terms of their dose-volume histograms. A special dose mimicking method based on the MDN output is used to produce deliverable plans and thereby showcase the usability of voxel-wise predictive densities. Thus, this type of MDN may serve to support clinicians in managing clinical tradeoffs and has the potential to improve quality of plans produced by an automated treatment planning pipeline.