Automatic Left Ventricular Boundary Detection from Echocardiographic Images Using Wavelet Analysis

A new fully automatic Wavelet and Multiresolution-Based algorithm for left ventricular (LV) endocardial and epicardial boundary detection and tracking in Short Axis (SA) echocardiographic images is presented in this paper. The proposed algorithm is a Center-Based approach in which the LV center point (LVCP) is estimated using a fuzzy-Based technique and then epicardial and endocardial edge points are searched on radial lines emanating from LVCP. The algorithm consist of five steps: preprocessing , LVCP estimation , wavelet based edge detection , radial search and finally uniform cubic BSpline approximation is used to define closed and smoothed LV Boundaries. Sample experimental results are shown for endocardial and epicardial border identification in 2D short axis (SA) echocardiograms.

Automatic Left Ventricular Boundary Detection from Echocardiographic Images Using Wavelet Analysis Keywords:

Edge detection , wavelet transform , boundary detection , echocardiography , multiresolution