Vessel detection by mean shift based ray propagation

A robust and efficient method for the segmentation of vessel cross-sections in contrast enhanced CT and MR images is presented. The primary innovation of the technique is the boundary propagation by mean shift analysis combined with a smoothness constraint. Consequently, the robustness of the mean shift to noise is enhanced by the use of a priori information on boundary smoothness. This processing is integrated into our computationally efficient framework based on ray propagation. The new algorithm allows real time segmentation of medical structures found in multi-modality images (CT, MR) and various examples are shown to illustrate its effectiveness.