Fully automatic echocardiographical feature extraction applied to left ventricular wall motion and volume changes visualisation

A fully automatic system for extraction of the cardiac left ventricular (LV) boundaries from echocardiographic images is presented. Fuzzy set theory is used to estimate the centre of the LV cavity using knowledge of the standard echo views and the heart morphology. A multiresolution edge detection technique based on the `global maximum´ in wavelet transform domain is used in conjunction with a radial search algorithm, to define a candidate single boundary point on each radial intensity profile. Both spatial and temporal median post filtering and cubic B-spline approximation methods are employed to refine the estimated boundary points and to construct the final closed boundaries. Experiments and results with real short axis and long axis images are presented which include boundary extraction and visualisation of the wall motion and volume change dynamics