Tracking the left ventricle in echocardiographic images by learning heart dynamics

In this paper a temporal learning-filtering procedure is applied to refine the left ventricle (LV) boundary detected by an active-contour model. Inste ad of making prior assumptions about the LV shape or its motion, this infor mation is incrementally gathered directly from the images and is exploited to achieve more coherent segmentation, A Hough transform technique is used to find an initial approximation of the object boundary at the first frame of the sequence, Then, an active-contour model is used in a coarse-to-fine framework, for the estimation of a noisy LV boundary, The PCA transform is applied to form a reduced ordered orthonormal basis of the LV deformations based on a sequence of noisy boundary observations. Then this basis is used to constrain the motion of the active contour in subsequent frames, and th us provide more coherent identification. Results of epicardial boundary ide ntification in E-mode images are presented.