Prediction of low-keV monochromatic images from polyenergetic CT scans for improved automatic detection of pulmonary embolism

TL;DR

This study develops convolutional neural networks to generate low-keV monoenergetic images from standard CT scans, enhancing pulmonary embolism detection accuracy by improving image quality and classification performance.

Contribution

The paper introduces a multi-task CNN framework that simultaneously generates monoE images and improves PE classification, outperforming traditional image-translation methods.

Findings

Enhanced PE detection with AuROC increased from 0.8142 to 0.8420.

Multi-task optimization improves both image quality and classification accuracy.

Proposed method outperforms conventional image-translation approaches.

Abstract

Detector-based spectral computed tomography is a recent dual-energy CT (DECT) technology that offers the possibility of obtaining spectral information. From this spectral data, different types of images can be derived, amongst others virtual monoenergetic (monoE) images. MonoE images potentially exhibit decreased artifacts, improve contrast, and overall contain lower noise values, making them ideal candidates for better delineation and thus improved diagnostic accuracy of vascular abnormalities. In this paper, we are training convolutional neural networks~(CNN) that can emulate the generation of monoE images from conventional single energy CT acquisitions. For this task, we investigate several commonly used image-translation methods. We demonstrate that these methods while creating visually similar outputs, lead to a poorer performance when used for automatic classification of pulmonary embolism (PE). We expand on these methods through the use of a multi-task optimization approach, under which the networks achieve improved classification as well as generation results, as reflected by PSNR and SSIM scores. Further, evaluating our proposed framework on a subset of the RSNA-PE challenge data set shows that we are able to improve the Area under the Receiver Operating Characteristic curve (AuROC) in comparison to a na\"ive classification approach from 0.8142 to 0.8420.