Abstract: Semi-automatic tissue segmentation for medical visualization and virtual endoscopy was implemented by boundary model and local character structure techniques. We found out inner voxels and outer voxels by pre-appointing a specific voxel on boundary model. And then, boundary voxels were correctly classified into different tissues by their eigenvalues of Hessian matrix based on the local character structure. Only eigenvalues of the boundary voxels are computed, so little time is used compared with other algorithms based on local character structure. It can quickly and effectively realize the segmentation of single tissue.