Image segmentation is the keystone of medical image processing quantitative analysis and the basis of registration, 3D reconstruction. It is very difficult for quantitative analysis of medical CT images because of their complex texture and fuzzy edge This paper takes medicine chest CT images for experimental object, presents a method of CT image segmentation based on region growing method, and the application of effective segmentation of the lung tissue to chest CT images. Compared with any other segmentation methods, the results show that the segmentation method which is proposed in this paper does better in CT image segmentation. The results obtained in this paper have the significance in clinical applications and auxiliary diagnosis.