Segmenting the External Surface of a Human Skull in MR Data

Abstract

A method is presented to extract the outline of the skull region in coronal Magnetic Resonance (MR) images from the Visible Human Project. The starting point is the formulation of a Gradient Vector Flow (GVF) snake extended to include statistical shape information. This method exploits the diffusion process used by the GVF snake and improves its capacity to deal with occlusion problems by adding a shape term to the traditional scheme. The results of the segmentation of the MR data are compared with the results of the segmentation of CT scans of the same individual. For the MR data, the addition of a shape term improves on the results obtained by using a GVF snake alone.