Cardiac Motion Estimation from Echocardiographic Image Sequence using Unsupervised Active Contour Tracker
U. Bharali, Debashis Ghosh · 2006
The study and analysis of cardiac function, in particular the left-ventricular function, from echocardiographic image sequence is one important topic of research in the field of medical image processing. In this paper, we develop a technique for segmentation and simultaneous tracking of the left-ventricular wall using active contour model, thereby estimating the motion of the left ventricle. Unlike the existing active contour tracker, we propose an unsupervised active contour tracking algorithm thereby making our scheme fully automatic without the need for any user input. The initial approximate contour in the first frame of the sequence is obtained via multiresolution image segmentation while the initial contours in all subsequent frames are obtained from the final contours in the previous frames. Another advantage of the method is that the computational cost is significantly reduced by accomplishing multiple tasks through single operations. In our experiments, we observe that our proposed method is capable of tracking the heart wall with high precision and accuracy