作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2007, Vol. 33 ›› Issue (16): 14-16. doi: 10.3969/j.issn.1000-3428.2007.16.005

• 博士论文 • 上一篇    下一篇

基于椭圆约束分割心脏MRI图像的水平集模型

段先华1,夏德深2   

  1. (1. 江苏科技大学电子信息学院,镇江 212003;2. 南京理工大学计算机科学与技术系,南京 210094)
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-08-20 发布日期:2007-08-20

Level Set Model for Segmentation of Cardiac MRI Image Based on Ellipse Shape Restriction

DUAN Xian-hua1, XIA De-shen2   

  1. (1. School of Electronics and Information, Jiangsu University of Science and Technology, Zhenjiang 212003; 2. Department of Computer Science and Technology, Nanjing University of Science and Technology, Nanjing 210094)
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-08-20 Published:2007-08-20

摘要: 针对左心室外轮廓类似椭圆的特点,提出了基于椭圆约束的水平集模型,该模型在Chan and Vese模型的基础上增加椭圆形状约束项,来控制曲线的演化,将水平集的演化曲线作为对轮廓新的位置预测,并用椭圆对预测结果进行修正,把预测结果和修正结果分别作为新的水平集曲线和椭圆信息,直到曲线停止演化。实验表明,该方法能够有效地分割心脏外轮廓。

关键词: 椭圆, 水平集模型, 心脏MRI图像, 分割

Abstract: In respect of the ellipse-like outline of the left ventricle, a new model for segmenting cardiac MRI image is presented, which is based on ellipse shape restriction level set model. Ellipse shape restriction is adopted based on Chan and Vese model to control evolvement of curve. The evolvement curve of level set is regarded as the new forecast of contour location, ellipse restriction is introduced to modify the forecast result. Accordingly, the results of the forecast and modification are taken respectively as new curve of the level set and shape information, till curve ceases evolvement. The results of the experiments prove its effectiveness for segmenting tagged cardiac MRI images.

Key words: ellipse, level set model, cardiac MRI image, segmentation

中图分类号: