Evaluation of deep learning-based myocardial infarction quantification using Segment CMR software

TL;DR

This paper assesses the accuracy of deep learning methods for quantifying myocardial infarction using Segment CMR software, comparing automated results with expert assessments to validate the approach.

Contribution

It introduces a U-net based semantic segmentation algorithm to fully automate MI quantification within Segment CMR software, enhancing previous methods.

Findings

Deep learning-based segmentation correlates well with expert assessments.

Automated MI quantification improves efficiency and consistency.

The method accurately estimates infarct volume and microvascular obstruction.

Abstract

This work evaluates deep learning-based myocardial infarction (MI) quantification using Segment cardiovascular magnetic resonance (CMR) software. Segment CMR software incorporates the expectation-maximization, weighted intensity, a priori information (EWA) algorithm used to generate the infarct scar volume, infarct scar percentage, and microvascular obstruction percentage. Here, Segment CMR software segmentation algorithm is updated with semantic segmentation with U-net to achieve and evaluate fully automated or deep learning-based MI quantification. The direct observation of graphs and the number of infarcted and contoured myocardium are two options used to estimate the relationship between deep learning-based MI quantification and medical expert-based results.