Cardiac Motion Estimation from Echocardiographic Image Sequence using Unsupervised Active Contour Tracker

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

[1]  Xiaorong Gao,et al.  A novel multiscale nonlinear thresholding method for ultrasonic speckle suppressing , 1999, IEEE Transactions on Medical Imaging.

[2]  Demetri Terzopoulos,et al.  Snakes: Active contour models , 2004, International Journal of Computer Vision.

[3]  Debashis Ghosh,et al.  Unsupervised active contour model for biological image segmentation and analysis , 2003, TENCON 2003. Conference on Convergent Technologies for Asia-Pacific Region.

[4]  James D. Thomas,et al.  Segmentation and tracking in echocardiographic sequences: active contours guided by optical flow estimates , 1998, IEEE Transactions on Medical Imaging.

[5]  Baba C. Vemuri,et al.  Shape Modeling with Front Propagation: A Level Set Approach , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Michael G. Strintzis,et al.  Tracking the left ventricle in echocardiographic images by learning heart dynamics , 1999, IEEE Transactions on Medical Imaging.

[7]  T. Loupas,et al.  An adaptive weighted median filter for speckle suppression in medical ultrasonic images , 1989 .

[8]  J. Alison Noble,et al.  A shape-space-based approach to tracking myocardial borders and quantifying regional left-ventricular function applied in echocardiography , 2002, IEEE Transactions on Medical Imaging.

[9]  S. Osher,et al.  Algorithms Based on Hamilton-Jacobi Formulations , 1988 .

[10]  Jerry L Prince,et al.  Image Segmentation Using Deformable Models , 2000 .

[11]  N. Paragios A level set approach for shape-driven segmentation and tracking of the left ventricle , 2003, IEEE Transactions on Medical Imaging.

[12]  Xiaorong Gao,et al.  Multi-Scale Nonlinear Thresholding for Ultrasonic Speckle Suppression , 1999, IEEE Trans. Medical Imaging.

[14]  J. Sethian,et al.  Fronts propagating with curvature-dependent speed: algorithms based on Hamilton-Jacobi formulations , 1988 .

[15]  Mubarak Shah,et al.  A fast algorithm for active contours , 1990, [1990] Proceedings Third International Conference on Computer Vision.

[16]  Yongmin Kim,et al.  A multiple active contour model for cardiac boundary detection on echocardiographic sequences , 1996, IEEE Trans. Medical Imaging.

[17]  Andrew F. Laine,et al.  Speckle reduction and contrast enhancement of echocardiograms via multiscale nonlinear processing , 1998, IEEE Transactions on Medical Imaging.