Multilayer Image Segmentation Based On Gaussian Weighted Euclidean Distance And Nonlinear Interpolation

Multilayer image segmentation is commonly used in computer aided diagnosis and therapy planning. However, manual multilayer image segmentation is time-consuming and tedious. In this paper, an efficient and accurate semi-automatic method, which is based on Gaussian weighted Euclidean distance and nonlinear interpolation, is presented. The first and the last layers are segmented using improved live wire method. Then the prior knowledge, which is from the Gaussian weighted Euclidean distance transformation of the first and last layers, is combined with nonlinear interpolation to realize automatic segmentation of the intermediate layers. Experiments were conducted over magnetic resonance (MR) images of human leg. The results show that proposed method can not only reduce the time consumption, but also improve the accuracy of the segmentation.