CT volumetric data-based left ventricle motion estimation: an integrated approach.

This paper describes a novel approach to left ventricle motion analysis via the integration of image segmentation with shape deformation analysis using computerized tomography (CT) volumetric image data. This approach is different from traditional image analysis scenario in which the image segmentation and shape analysis were considered separately. The advantage of integrating the image segmentation with the shape analysis lies in the fact that the shape characteristics of the object can be used as effective constraints in the process of segmentation while original image data can be made useful along with the segmentation results in the process of shape analysis. In the case of left ventricle motion estimation, such an integration can be applied to obtain the estimation results that are consistent with both given image data and a priori shape knowledge. The initial segmentation of the images is obtained through adaptive K-mean classification and the region-of-interest is then identified based on the initial segmentation. The shape analysis is accomplished through fitting the boundary points of the region-of-interest to the surface modeling primitives. These two processes are integrated through the feedforward and feedback channels so that the surface fitting is constrained by the confidence measures of the boundary points and segmentation refinement is guided by the result of surface modeling. Global motion parameters are obtained by comparing the parameters of the fitted surface model at consecutive time instances. The segmentation and shape analysis results obtained show that the integrated approach is capable of providing promising improvement over traditional approaches.