In this chapter we introduced the semi-implicit co-volume level set method for solving the segmentation equation given by the Riemannian mean curvature flow of graphs. We discussed basic properties of the model and the role of model parameters and gave all details for computer implementation of the numerical algorithm. We also showed unconditional stability of our method and its high efficiency for this type of problems. The computational results related to

Figure 11.28: Segmentation level line and graph of the segmentation function for extraction of tumor in mammography (color slide).

medical image segmentation with partly missing boundaries and subjective contour extraction were discussed. The method was presented for 2D image segmentation. However, as is common in level set methods, the extension to 3D case is straightforward and can be done easily using ideas of this chapter.

0 0

Post a comment