Organ segmentation from medical images is still an open problem and liver segmentation is a much more challenging task among other organ segmentations. This paper presents a liver egmentation method from a sequence of computer tomography images.We propose a novel balloon force that controls the direction of the evolution process and slows down the evolving contour in regions with weak or without edges and discourages the evolving contour from going far away from the liver boundary or from leaking at a region that has a weak edge, or does not have an edge. The model is implemented using a modified Distance Regularized Level Set (DRLS) model. The experimental results show that the method can achieve a satisfactory result. Comparing with the original DRLS model, our model is more effective in dealing with over segmentation problems.
展开▼
