A semi-automated segmentation method for detection of pulmonary embolism in True-FISP MRI sequences

TL;DR

This paper introduces a semi-automated segmentation method for True-FISP MRI images to improve pulmonary embolism detection accuracy, reducing false positives caused by artifacts and matching CT angiography performance.

Contribution

A novel segmentation algorithm that enhances True-FISP MRI diagnostic accuracy for pulmonary embolism by quantitatively analyzing clot features.

Findings

Increased diagnostic accuracy by 6% with the new method.

Achieved accuracy comparable to CT angiography.

Validated on 37 patient cases.

Abstract

Pulmonary embolism (PE) is a highly mortal disease, currently assessed by pulmonary CT angiography. True-FISP MRI has emerged as an innocuous alternative that does not hold many of the limitations of x-ray imaging. However, True-FISP MRI is very sensitive to turbulent blood flow, generating artifacts that may resemble fake clots in the pulmonary vasculature. These misinterpretations reduce its overall diagnostic accuracy to 94%, limiting a wider use in clinical environments. A new segmentation algorithm is proposed to confirm the presence of real pulmonary clots in True-FISP MR images by quantitative means, measuring the shape, intensity, and solidity of the formation. The algorithm was evaluated in 37 patients. The developed method increased the diagnostic accuracy of expert observers assessing Pulmonary True-FISP MRI sequences by 6% without the use of ionizing radiation, achieving a diagnostic accuracy comparable to standard CT angiography.