SEGMENTATION OF MULTIDIMENSIONAL CARDIAC IMAGES

One of the initial steps in the analysis of three-dimensional (3D)/fou r-dimensional (4D) images is Segmentation, which entails partitioning the images into relevant subsets such as object and background. In thi s paper, we present a multidimensional segmentation algorithm to extra ct object surfaces from Multidimensional Cardiac Computed Tomography ( CT) scans. We propose the Generalized Morphological operators for segm entation in multidimensions. A prior knowledge of the approximate loca tion of the object surface is communicated to the algorithm via the de finition of the Search Space. The algorithm uses this definition of th e Search Space to obtain the Surface Candidate elements. The search sp ace specification reduces the computational cost and increases the rel iability of the detected features.