Segmentation of Hippocampus in MRI Images Based on the Improved Level Set

For hippocampus of MRI demonstrating the low contrast, low signal to noise ratio(SNR), boundary discrete, intensity in homogeneities features, this paper proposed an improved level set model that based on regional and edge information. Refer to the intensity in homogeneities image, the global image information of external energy item is joined, to optimize the segmentation result, adopt edge information that is extracted by wavelet, which is used as an edge constraint stop item. Experimental results of many times segmentation of the hippocampus of MRI image show that this algorithm can precisely segment intensity in homogeneities image and improve the segmentation speed, so this algorithm can be applied to the complex structure segmentation, such as the hippocampus.