Peng Yanjun

3D medical image segmentation based on active contour model

Contour initialization is a big problem of the active contours. Using the continuous features of the three-dimensional medical image, this paper proposes an initial contour prediction model. There are some changes in the boundary contours in the adjacent images of the same object and we attribute these changes to continuous translation and similar deformation, and quantify into the displacement of the centroid and displacement of the point in the direction of Normal. The curve fitting method is used to predict the centroid displacement and the displacement of the points of the contours, which can provide more accurate prediction of changes in the contour. By predicting the initial contour, we have solved the contour initialization problem of the parametric active contour with external force using vector field convolution.

Research on medical images segmentation algorithm

A segmentation algorithm in 3d medical data is proposed based on boundary model and local character structure in this paper. We found out inner voexls and outer voexls by pre-appointed voxel based on boundary model. And then, boundary voexls are 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.