Automatic region growing algorithm for the visible human dataset

The National Library of Medicine's Visible Human Project is a digital image library containing full color anatomical, CT and MR images representing a complete, normal, adult male and female. Segmentation of the Visible Human datasets offer many additions to the original goal of a three-dimensional representation of a computer generated anatomical model of the human body. This paper presents an automatic segmentation algorithm based on seeded region growing. The technique repeatedly extracts anatomical regions of interest from two-dimensional (2D) cross section images to create three-dimensional (3D) visualizations of these anatomical areas. Results of this technique are also presented.