Abstract: For the sake of high accuracy and efficiency of liver segmentation, we propose an improved Fast Marching method based on self-adaptive parameter adjustment. The arrival time parameter T is adjusted according to the intensity statistics of the liver region on set of abdominal CT images, which can used to estimate the size of liver region on the corresponding CT slices. This method is efficient for elimination the influence of traditional same parameter values on the efficiency and accuracy of liver segmentation. When tested on 10 sets of abdominal CT images, experimental results show that the proposed approach can segment liver automatically, quickly and accurately. The average time for processing a slice of CT image resulted to be 0.3s, and the average accuracy is up to 97%. It is accurate and efficient enough for the use in clinical diagnosis and surgical navigation.