Segmentation for CT Image Based on Improved Level-Set Approach

Liver segmentation on computed tomography (CT) images is a challenging task due to the anatomic complexity and the imaging system noise. In this paper, we develop an improved level set segmentation method. Our region-based level-set approach has many advantages over the conventional active contour models. First, the improved model can get much smoother contour by adding a signed distance preserving term to evolution PDE. In addition, this modified level set function speeds up the segmentation process significantly. Second, we can obtain accurate extracted liver image by morphological filters. Therefore, our algorithm can be applied to detect the internal malignant structure of liver image. Third, it has good robustness to the presence of weak boundaries and strong noise. Experimental results show that the proposed method gives automatic and accurate liver structure segmentation.