It requires skill, effort, and time to visualize desired anatomic structures from radiological data in three-dimensions. There have been many attempts at automating this process and making it less labor intensive. The technique we have developed is based on mutual information for automatic multi-modality image fusion (MIAMI Fuse, University of Michigan). The initial development of our technique has focused on the autocolorization of the liver, portal vein, and hepatic vein. A standard dataset in which these structures had been segmented and assigned colors was created from the full color Visible Human Female (VHF) and then optimally fused to the fresh CT Visible Human Female. This semi-automatic segmentation and coloring of the CT dataset was subjectively evaluated to be reasonably accurate. The transformation could be viewed interactively on the ImmersaDesk, in an immersive Virtual Reality (VR) environment. This 3D segmentation and visualization method marks the first step to a broader, standardized automatic structure visualization method for radiological data. Such a method, would permit segmentation of radiological data by canonical structure information and not just from the data’s intrinsic dynamic range.