A skull-stripping method based on modified morphological processing

摘要

The method of skull-stripping is based on edge detection. The method can extract the brain tissue from a normal MRI (magnetic resonance image) quickly and accurately. But if there are tumors at the boundary of the brain tissues whose intensity is different with normal tissues, some unwanted edge will appear while detecting the boundary of the brain tissue. So, a modified method to solve this issue by anisotropic diffusion and morphological processing has been proposed. But there were issues based on clarity with this method. Our procedure consists of three steps. First, the MRI is processed with a wiener filter. And then find the region between the skull and the brain tissue using thresholding methods. It is difficult to remove the unwanted edges directly, but we found that when we processed it using a skeletonization algorithm, the unwanted edges became the branches on the skeleton of the region. Finally, use a sequence of morphological and connected component operator to make sure the region is closed. The closed region is that we wish for. Results on 2-D MR images are provided.