基于统计方法和主动轮廓模型相结合的医学图像轮廓提取

应用科学学报 ›› 2005, Vol. 23 ›› Issue (1): 41-44.

基于统计方法和主动轮廓模型相结合的医学图像轮廓提取

陈曾胜, 周康源, 李传富, 胡跃辉, 黄丹, 王庆临

中国科学技术大学电子工程与信息科学系, 安徽合肥 230027

收稿日期:2003-10-28 修回日期:2004-02-05 出版日期:2005-01-31 发布日期:2005-01-31
作者简介:陈曾胜(1976-),男,安徽怀宁人,博士生;周康源(1941-),男,上海人,教授,博导,E-mail:kyzhou@ustc.edu.cn

Contour Extraction for Medical Images Based on the Combination of the Statistical Method and Active Contour Models

CHEN Zeng-sheng, ZHOU Kang-yuan, LI Chuan-fu, HU Yao-hui, HUANG Dan, WANG Qing-lin

Depertment of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei 230027, China

Received:2003-10-28 Revised:2004-02-05 Online:2005-01-31 Published:2005-01-31

摘要/Abstract

摘要： 采用最小描述长度作为目标函数实现点分布模型上轮廓点的自动选取,提出了一种结合统计方法与主动轮廓模型提取图像轮廓曲线的方法.对一系列图像训练得到该训练集的典型轮廓曲线,初始化新图像的主动轮廓模型曲线后,再用训练集得到的轮廓线约束其变形,提取图像最佳的轮廓曲线.实验表明,与传统主动轮廓模型比较,该方法具有更好的轮廓提取效果.

关键词: Snakes模型, 医学图像轮廓提取, 主动轮廓模型, 点分布模型, 最小描述长度

Abstract: The paper proposes a method of images contour extraction which combines the statistical method and active contour models(ACM).To choose the contour points of points distribution models automatically, the minimum description length was chosen as the object function.A typical contour model is obtained from an image training set.After the initialization of a new image's ACM contour, the typical contour mentioned above is used as the deformation constraint to extract the nearly optimum contour.The experiments with the real images show the effectiveness of this method in comparison with the traditional active contour models method.

Key words: contour extraction for medical images, active contour models, Snakes models, points distribution models, minimum description length

中图分类号:

TP391.41

陈曾胜, 周康源, 李传富, 胡跃辉, 黄丹, 王庆临. 基于统计方法和主动轮廓模型相结合的医学图像轮廓提取[J]. 应用科学学报, 2005, 23(1): 41-44.

CHEN Zeng-sheng, ZHOU Kang-yuan, LI Chuan-fu, HU Yao-hui, HUANG Dan, WANG Qing-lin. Contour Extraction for Medical Images Based on the Combination of the Statistical Method and Active Contour Models[J]. Journal of Applied Sciences, 2005, 23(1): 41-44.