Uncertainty in multitask learning: joint representations for probabilistic MR-only radiotherapy planning

TL;DR

This paper introduces a probabilistic multi-task neural network for MR-only radiotherapy planning that jointly predicts synthetic CT scans and organ segmentations, providing uncertainty estimates for improved accuracy and quality assurance.

Contribution

It presents a novel probabilistic multi-task model that estimates both intrinsic and parameter uncertainty, enhancing joint predictions and quality assurance in radiotherapy planning.

Findings

More accurate and consistent synCTs

State-of-the-art OAR segmentation results

Effective uncertainty estimation for quality assurance

Abstract

Multi-task neural network architectures provide a mechanism that jointly integrates information from distinct sources. It is ideal in the context of MR-only radiotherapy planning as it can jointly regress a synthetic CT (synCT) scan and segment organs-at-risk (OAR) from MRI. We propose a probabilistic multi-task network that estimates: 1) intrinsic uncertainty through a heteroscedastic noise model for spatially-adaptive task loss weighting and 2) parameter uncertainty through approximate Bayesian inference. This allows sampling of multiple segmentations and synCTs that share their network representation. We test our model on prostate cancer scans and show that it produces more accurate and consistent synCTs with a better estimation in the variance of the errors, state of the art results in OAR segmentation and a methodology for quality assurance in radiotherapy treatment planning.