Computer Engineering and Applications ›› 2009, Vol. 45 ›› Issue (31): 215-217.DOI: 10.3778/j.issn.1002-8331.2009.31.064

• 工程与应用 • Previous Articles     Next Articles

Study on spines and ribs segmentation from liver CTA images

ZHOU Jie,ZHAO Yu-qian,TANG Jian,YAO Ai-ping   

  1. School of Info-Physics and Geomatics Engineering,Central South University,Changsha 410083,China
  • Received:2009-05-08 Revised:2009-06-22 Online:2009-11-01 Published:2009-11-01
  • Contact: ZHOU Jie

肝脏CTA图像肋骨和脊椎骨分割方法研究

周 洁,赵于前,唐 建,姚爱萍   

  1. 中南大学 信息物理工程学院,长沙 410083
  • 通讯作者: 周 洁

Abstract: The segmentation of the spines and ribs is an important preprocessing work in the segmentation of liver from liver CTA images.Usually thresholding is chosen,but this method will result in integrant or over-segmentation.To solve this problem,the paper proposes a method combining regional anatomy with threshold to remove the spine and ribs.Based on the basic theory of regional anatomy,the method first builds four border characteristics lines,and then removes the spine and ribs through binary morphological reconstruction.The proposed method not only adapts to different images of the spine and ribs with different gray values,but also eliminates the impact of adjacent tissues with the similar gray scale.The experimental results show that the proposed method can segment the spines and ribs from liver CTA images efficiently and accurately.

Key words: thresholding, morphological reconstruction, Computed Tomography Angiography(CTA), spines and ribs segmentation

摘要: 肋骨和脊椎骨的分割是从肝脏CTA(即肝脏CT血管造影)图像中准确分割出肝脏的重要预处理工作,一般考虑阈值分割方法,但该方法常常导致分割不全或过分割。提出了一种将形态学方法和阈值法结合起来的肋骨和脊椎骨分割方法。利用局部解剖学知识,构建四种图像边界特征线,然后通过二值形态学处理方法实现肋骨和脊椎骨的分割。这样既适应了由于不同图像的肋骨和脊椎骨灰度值不同的复杂性,也消除了由于其他器官灰度值相近的影响。实验结果表明,该方法能够高效准确地分割出肝脏CTA图像中的肋骨和脊椎骨。

关键词: 阈值处理, 形态学重构, CT血管造影(CTA), 肋骨和脊椎骨分割

CLC Number: