Abstract
This paper presents a high-speed liver segmentation method applied on abdominal CT image. Firstly, based on the morphological feature of the liver region under various window-level settings, we apply the region-growing algorithm to remove other tissues such as skeleton, skin, kidney and stomach, and hence the discrete points of the liver region can be acquired. Secondly, we recover the liver region from the original image by calculating the coordinates of the discrete points. Finally, in order to get more accurate segmentation results, the gradient information based edge correction and three-dimensional restoration are adopted to optimize the recovered liver image. Compared with other liver segmentation methods, our method has lower time complexity, which can satisfy the demands of realtime processing.
