Automatic detection of end systole and end diastole within a sequence of 2-D echocardiographic images using modified Isomap algorithm

The first step for automatic calculation of the ejection fraction, stroke volume and some other features related to heart motion abnormalities in echocardiographic images is automatic detection of the end-systole and end-diastole frames. In this paper, modified Isomap algorithm is applied on two dimensional (2-D) echocardiographic images to reveal the relationship between the frames of one cycle of heart motion. By this approach, the image sequences are represented in a 2-D manifold and each image is characterized by a point on reconstructed manifold. By considering the fact that end-diastolic and the end-systolic frames have the highest volume difference and consequently highest image difference comparing to the other two frames, the maximum distance between the two points in manifold is used to find these frames. The results obtained with our method were validated to those obtained with the reference experienced echo-cardiologist on six healthy volunteers and depicted the usefulness of presented method.