Uncertainty quantification in computed tomography pulmonary angiography

TL;DR

This paper introduces a Bayesian method to quantify uncertainty in detecting pulmonary embolisms in CT scans, helping distinguish artifacts from real conditions.

Contribution

A scalable Bayesian framework for uncertainty quantification in CT imaging of pulmonary embolism detection is introduced.

Findings

The Bayesian framework can quantify uncertainty in identifying compact structures as pulmonary embolisms.

The method performs well in high-noise environments and with limited data.

This approach provides a proof of concept for scalable hypothesis testing in CT imaging.

Abstract

Computed tomography (CT) imaging of the thorax is widely used for the detection and monitoring of pulmonary embolism (PE). However, CT images can contain artifacts due to the acquisition or the processes involved in image reconstruction. Radiologists often have to distinguish between such artifacts and actual PEs. We provide a proof of concept in the form of a scalable hypothesis testing method for CT, to enable quantifying uncertainty of possible PEs. In particular, we introduce a Bayesian Framework to quantify the uncertainty of an observed compact structure that can be identified as a PE. We assess the ability of the method to operate under high-noise environments and with insufficient data.

Figures