Vector-based Medical Image Segmentation using Adaptive Delaunay Triangulation

M. Španĕl and P. Kršek (Czech Republic)


CT/MR data, image segmentation, 3D geometrical model, vector-based segmentation, Delaunay tringulation.


The image segmentation plays an important role in medi cal image processing. Many segmentation algorithms ex ist. Most of them produce raster data which is not suitable for further 3D geometrical modeling of tissues. In this pa per, a vector segmentation algorithm based on an adaptive Delaunay triangulation is proposed. Triangular meshes are used to divide an image into several non-overlapping re gions whose characteristics are similar. Novel methods for improving quality of the mesh and its adaptation to the im age structure are also presented.

Important Links:

Go Back