Liver Segmentation Based on Snakes Model and Improved GrowCut Algorithm in Abdominal CT Image. (26th August 2013)

• Record Type: Journal Article
• Authors: Jiang, Huiyan; He, Baochun; Ma, Zhiyuan; Zong, Mao; Zhou, Xiangrong; Fujita, Hiroshi
• Other Names: Najarian Kayvan Academic Editor.
• Is Part Of: Computational and mathematical methods in medicine. Volume 2013(2013)
• Publication Date: 2013-08-26
• Subjects: Medicine -- Computer simulation -- Periodicals; Medicine -- Mathematical models -- Periodicals; 610.11
• DOI: 10.1155/2013/958398
• Languages: English
• ISSNs: 1748-670X

Abstract

Abstract : A novel method based on Snakes Model and GrowCut algorithm is proposed to segment liver region in abdominal CT images. First, according to the traditional GrowCut method, a pretreatment process using K-means algorithm is conducted to reduce the running time. Then, the segmentation result of our improved GrowCut approach is used as an initial contour for the future precise segmentation based on Snakes model. At last, several experiments are carried out to demonstrate the performance of our proposed approach and some comparisons are conducted between the traditional GrowCut algorithm. Experimental results show that the improved approach not only has a better robustness and precision but also is more efficient than the traditional GrowCut method.