Parametric Methods for the Regional Assessment of Cardiac Wall Motion Abnormalities: Comparison Study

Abstract

Left ventricular (LV) dysfunction is mainly assessed by global contractile indices such as ejection fraction and LV Volumes in cardiac MRI. While these indices give information about the presence or not of LV alteration, they are not able to identify the location and the size of such alteration. The aim of this study is to compare the performance of three parametric imaging techniques used in cardiac MRI for the regional quantification of cardiac dysfunction. The proposed approaches were evaluated on 20 patients with myocardial infarction and 20 subjects with normal function. Three parametric images approaches: covariance analysis, parametric images based on Hilbert transform and those based on the monogenic signal were evaluated using cine-MRI frames acquired in three planes of views. The results show that parametric images generated from the monogenic signal were superior in term of sensitivity (89.69%), specificity (86.51%) and accuracy (89.06%) to those based on covariance analysis and Hilbert transform in the detection of contractile dysfunction related to myocardial infarction. Therefore, the parametric image based on the monogenic signal is likely to provide additional regional indices about LV dysfunction and it may be used in clinical practice as a tool for the analysis of the myocardial alterations.

Stroke Risk Assessment Decision-Making Using a Machine Learning Model: Logistic-AdaBoost

“…This model has high prediction accuracy among the Chinese population, but it mainly focuses on the prediction of cardiovascular diseases. Benameur et al [25] compared the performance of three parametric imaging techniques (covariance analysis and parametric imaging based on Hilbert transform and that based on the monogenic signal) used in cardiac MRI for the regional quantification of cardiac dysfunction, and the three approaches were evaluated using cine-MRI frames acquired from three planes of view.…”

Ventricular segmentation and modeling using topological watershed transformation and harmonic state model

“…In cardiac imaging, the segmentation of the contours of the ventricles is an essential step in detecting pathologies [12]- [14] such as ischemic, cardiomyopathies, and arrhythmias. Moreover, the monitoring of ventricular motion allows an in-depth analysis of these cardiovascular pathologies [15]. Although medical imaging provides essential support for the diagnosis of ventricle functions, their direct interpretation is still impeded by some constraints such as low resolution and the presence of strong noise that influence not only the reliability of 2D segmentation but also the quality of 3D reconstruction.…”

“…Moreover, the monitoring of ventricular motion allows an in-depth analysis of these cardiovascular pathologies. 15 Although medical imaging provides essential support for the diagnosis of ventricle functions, their direct interpretation is still impeded by some constraints such as low resolution and the presence of strong noise that influence not only the reliability of 2D segmentation but also the quality of 3D reconstruction. Thus, the use of spatio-temporal modeling techniques represents a notable alternative.…”

Clustering Ensemble Technology Based on Granular Computing to Extract Cervical Cancer Predictors

“…In recent years, with the rapid development of highthroughput sequencing technology and the gradual reduction of costs, massive amounts of data have been accumulated in the eld of biomedicine. Using machine learning, neural network, and other data analysis methods to apply biological data to disease research has become a research hotspot in recent years [1][2][3][4]. However, the rapid growth of data volume and data dimension makes it di cult for traditional tools and experimental methods to solve problems in complex biological systems.…”