A novel ACM for segmentation of medical image with intensity inhomogeneity

This paper presents a scheme of improvement on the Li's model in terms of intensity inhomogeneous images. By introducing local entropy to Li's model, our method is able to segment medical images with intensity inhomogeneity and estimate the bias field simultaneously. The level set energy function is redefined as a weighted energy integral, where the weight is local entropy deriving from a grey level distribution of image. The total energy functional is then incorporated into a level set formulation. Experimental results on test images show that our approach outperforms the existing locally statistical active contour model (LSACM) and Li's model in terms of accuracy and efficiency with less central processing unit (CPU) time.