Medical image segmentation based on level set with new local fitting energy

In this paper, we define the fitting energy by a new kernel function, which is to do in the range of an image what traditional filters do a small neighborhood of the same location. We combine the advantages of the LBF model and our model by taking domain and range kernel functions into account. The new level set method with domain and range kernel functions has been tested and assessed on different modalities of medical images. Experiments prove our simulation results demonstrate that our model has better segmentation results compared with the LBF model.