Medical image segmentation based on Mumford-Shah model

Segmentation of medical images has become an indispensable process to quantitative analysis of images of human organs and their functions. In this paper, we discuss a novel approach to the segmentation of medical images. The Mumford-Shah model segmentation problem can be solved using the level set method. The new model can detect objects whose boundaries are not necessarily defined by gradient, as well as interior contours automatically. The model algorithm can be simultaneously used to denoise, segment, detect-extract edges. The approach is fast and accurate. The experimental results on various cases demonstrate the accuracy of the approach.