Early Myocardial Infarction Detection over Multi-view Echocardiography

TL;DR

This work tackles early myocardial infarction detection by leveraging multi-view echocardiography (A4C and A2C) to capture RWMA across 12 LV segments. It introduces Active Polynomials (APs) to robustly extract the LV endocardial boundary, derives per-segment displacement features, and applies ML classifiers to detect MI, with a new public HMC-QU dataset containing 260 recordings. Results show ML-based APs outperform threshold-based APs in single-view, and multi-view fusion yields high sensitivity (up to 90.91%) and competitive precision, demonstrating the value of combining views for reliable MI diagnosis. The approach offers a practical, interpretable CAD tool and provides a benchmark dataset to spur further research in automated MI localization and multi-view echocardiography analysis.

Abstract

Myocardial infarction (MI) is the leading cause of mortality in the world that occurs due to a blockage of the coronary arteries feeding the myocardium. An early diagnosis of MI and its localization can mitigate the extent of myocardial damage by facilitating early therapeutic interventions. Following the blockage of a coronary artery, the regional wall motion abnormality (RWMA) of the ischemic myocardial segments is the earliest change to set in. Echocardiography is the fundamental tool to assess any RWMA. Assessing the motion of the left ventricle (LV) wall only from a single echocardiography view may lead to missing the diagnosis of MI as the RWMA may not be visible on that specific view. Therefore, in this study, we propose to fuse apical 4-chamber (A4C) and apical 2-chamber (A2C) views in which a total of 12 myocardial segments can be analyzed for MI detection. The proposed method first estimates the motion of the LV wall by Active Polynomials (APs), which extract and track the endocardial boundary to compute myocardial segment displacements. The features are extracted from the A4C and A2C view displacements, which are concatenated and fed into the classifiers to detect MI. The main contributions of this study are 1) creation of a new benchmark dataset by including both A4C and A2C views in a total of 260 echocardiography recordings, which is publicly shared with the research community, 2) improving the performance of the prior work of threshold-based APs by a Machine Learning based approach, and 3) a pioneer MI detection approach via multi-view echocardiography by fusing the information of A4C and A2C views. Experimental results show that the proposed method achieves 90.91% sensitivity and 86.36% precision for MI detection over multi-view echocardiography. The software implementation is shared at https://github.com/degerliaysen/MultiEchoAI.

Figures (10)

• Figure 1: The chambers of the heart in A2C and A4C view echocardiography.
• Figure 2: The diagram of the proposed MI detection approach using multi-view echocardiography. The endocardial boundary is first extracted by the APs method. Then, the defined myocardial segments are tracked through one-cardiac cycle to form the displacement curves. The maximum displacements are generated from each segment to define the features that are then concatenated and fed into the classifier to detect MI.
• Figure 3: The comparison of the original and constrained active contours. In both A4C and A2C views, the constrained active contours can extract the endocardial boundary more accurately.
• Figure 4: The APs method for the endocardial boundary of the LV wall extraction consists of three stages: 1) the RPs on the LV wall are formed in input echocardiography, 2) the active contour is evolved from inside of the LV and constrained by the RPs, and 3) the APs are formed by fitting $4^{\text{th}}-$order polynomials on the evolved active contour.
• Figure 5: The myocardial segments of A4C and A2C views echocardiography based on the $17-$segment model.