Segmentation of Medical Serial Images Based on K-means and GVF Model

The medical CT images are irregular and have deep boundary concavities. So how to get the organ picture from serial images quickly and accurately is a difficult process. The paper discusses the shortcoming of GVF model being susceptible to structures with slender topology. For the better convergence we improve GVF model by setting the initial contour as the actual contour. The new algorithm combines k-means cluster with GVF model. Firstly, the target organ is extracted from a CT slice through k-means cluster and morphological reconstruction, and then its edge is set as an initial contour of the adjacent CT sequence, finally, the organ is segmented from a sequence of images with GVF algorithm. The process is repeated until all slices from entire CT sequences are obtained. The new algorithm has higher segmentation accuracy and lower complexity.