Abstract: Three-dimensional liver segmentation is a hot issue in medical image processing study. Accurate and fast liver segmentation from abdominal CT sequences is basis for liver lesions diagnose. The traditional active contour model is sensitive to contour and has large amount of computation, new method improves traditional contour set, and extends the algorithm to three-dimensional. In an abdominal CT image, using improved watershed algorithm to grow a liver from a seed block by the principle of the similarity between gray scale and texture, then using its edge as the start contour of the adjacent CT sequence, with GVF algorithm split a liver from a sequence of images, the process is repeated until getting all slices of the entire abdomen, then 3-D reconstructed.

Key words: watershed, GVF algorithm, 3-D liver segmentation

摘要： 三维肝脏分割是当前医学图像处理的热点问题，如何准确快速地从腹部CT序列中分割出肝脏是肝部病变诊断的基础。针对传统活动轮廓模型对轮廓线敏感、运算量大的问题，改进了传统轮廓线设置方法，并把算法扩展到三维。首先，在一幅腹部CT图片中采用改进的分水岭算法，按照灰度和纹理的相似性原则从一个种子块开始生长出整个肝脏，再用其边缘作为相邻CT序列的起始轮廓，用GVF算法从序列图片中分割出肝脏，重复该过程，直至分割出整个腹部序列图像的切片，进行三维重建。

关键词: 分水岭, GVF算法, 三维肝脏分割