Automatic Online Quality Control of Synthetic CTs

TL;DR

This paper proposes an ensemble-based online quality control method for synthetic CT images in MR-only radiotherapy workflows, detecting out-of-distribution inputs and potential generation errors to ensure safety and reliability.

Contribution

It introduces an uncertainty measure based on ensemble disagreement for automatic online quality control of synthetic CTs in radiotherapy.

Findings

Uncertainty measure effectively detects out-of-distribution MR images.

Method identifies synthetic CTs with potential errors.

Enables safer MR-only radiotherapy workflows.

Abstract

Accurate MR-to-CT synthesis is a requirement for MR-only workflows in radiotherapy (RT) treatment planning. In recent years, deep learning-based approaches have shown impressive results in this field. However, to prevent downstream errors in RT treatment planning, it is important that deep learning models are only applied to data for which they are trained and that generated synthetic CT (sCT) images do not contain severe errors. For this, a mechanism for online quality control should be in place. In this work, we use an ensemble of sCT generators and assess their disagreement as a measure of uncertainty of the results. We show that this uncertainty measure can be used for two kinds of online quality control. First, to detect input images that are outside the expected distribution of MR images. Second, to identify sCT images that were generated from suitable MR images but potentially contain errors. Such automatic online quality control for sCT generation is likely to become an integral part of MR-only RT workflows.