Detecting Regional Abnormal Cardiac Contraction in Short-Axis MR Images Using Independent Component Analysis
نویسندگان
چکیده
Regional myocardial motion analysis is used in clinical routine to inspect cardiac contraction in myocardial diseases such as infarction or hypertrophy. Physicians/radiologists can recognize abnormal cardiac motion because they have knowledge about normal heart contraction. This paper explores the potential of Independent Component Analysis (ICA) to extract local myocardial contractility patterns and to use them for the automatic detection of regional abnormalities. A qualitative evaluation was performed using 42 healthy volunteers to train the ICA model and 6 infarct patients to test the detection and localization. This experiment shows that the evaluation results correlate very well to the clinical gold standard: delayed-enhancement MR images.
منابع مشابه
Extraction of Myocardial Contractility Patterns from Short-Axes MR Images Using Independent Component Analysis
Regional myocardial wall motion analysis has been used in clinical routine to assess myocardial disease, such as infarction and hypertrophy. These diseases can be distinguished from normals by looking at the local abnormality of cardiac motion. In this paper, we present a first result of a feature extraction experiment using the Independent Component Analysis (ICA), where abnormal patterns of m...
متن کاملMeasurement of Left Ventricular Myocardium Wall Instantaneous Motions with Echocardiographic Sequence Images
Background & Aims: One of the important aims of quantitative cardiac image processing is the clarification of myocardial motions in order to derive biomechanical behavior of the heart in the disease condition. In this study we presented a computerized analysis method for detecting the instantaneous myocardial changes by using 2D echocardiography images. Methods: The analysis was performed on th...
متن کاملRegional Heart Motion Abnormality Detection via Multiview Fusion
This study investigates regional heart motion abnormality detection via multiview fusion in cine cardiac MR images. In contrast to previous methods which rely only on short-axis image sequences, the proposed approach exploits the information from several other long-axis image sequences, namely, 2-chamber, 3-chamber and 4-chamber MR images. Our analysis follows the standard issued by American He...
متن کاملMethodology for rapid Cardiac Axis generation from non gated cardiac MR images
Introduction: Cardiac Magnetic Resonance Imaging (MRI) is an excellent tool in analysis of left ventricular (LV) functioning[3]. Short axis cardiac MR images are most suitable to study the LV function [4], but preparation for generating these images is time consuming and requires sound understanding of the cardiac anatomy. Accurate and reproducible determination of short axis to study the LV fu...
متن کاملAutomatic, observer independent acquisition planning of cardiac MR short-axis views
Multi-slice, multi-phase Short-Axis (SA) cardiac MR-imaging has proven to be highly suitable to assess Left-Ventricular (LV) function, and is now considered to be the ‘gold standard’ for analysis of global and regional cardiac function. However, the acquisition planning of these scans is a timely process and requires substantial insight in cardiac anatomy, and planning of SA views in a reproduc...
متن کامل