A Framework for real-time left ventricular tracking in 3D+T echocardiography, using nonlinear deformable contours and kalman filter based tracking

This paper presents a new framework for automatic real-time left ventricular (TV) tracking in 3D+T echocardiography. The framework enables usage of existing biomechanical deformation models for the heart, with nonlinear modes of deformation, combined with edge models for the endocardial boundary. Tracking is performed in a sequential state estimation fashion, using an extended Kalman filter to recursively predict and update contour deformations in realtime. Contours are detected using normal-displacement measurements from points on the predicted contour, and are processed efficiently using an information-filter formulation of the Kalman filter. Promising results are shown for TV-tracking using a truncated ellipsoid contour model, with deformation parameters for translation, orientation, scaling and bending in all three dimensions. The tracking framework automatically detects TV position initially, even in situations where it is partially outside the volume. It also successfully tracks the dominant motion and shape changes throughout the heart cycle in real-time. A collection of 21 3D echocardiography recordings of good quality demonstrates that the framework is capable of automatically identifying and tracking the left ventricle in 90% of the recordings without any user input.