结合Hough变换与测地线轮廓模型的MR图像左心室自动分割  

Automatic Segmentation of the Epicardium and Endocardium from MR Image Based on Hough Transform and Geodesic Active Contour Model

作　　者：刘复昌[1] 尤建洁[1] 郭亮[2] 王平安[3] 韦志辉[1] 夏德深[1] 

机构地区：[1]南京理工大学计算机科学与技术学院,南京210094 [2]苏州大学附属第一医院放射科,苏州215006 [3]香港中文大学计算机科学与工程学系

出　　处：《计算机辅助设计与图形学学报》2007年第10期1292-1297,共6页Journal of Computer-Aided Design & Computer Graphics

基　　金：江苏省自然科学基金(BK2006704-2);香港特区政府研究资助局资助项目(CUHK/4180/01E;CUHK1/00C)

摘　　要：通过对MR图像左心室分割中各种主流方法的分析,提出一种自动分割MR图像左心室内外轮廓的算法.利用短轴图像上左心室心肌内外轮廓近似圆形的先验形状知识,先用Hough变换自动定位左心室的初始轮廓,然后在测地线轮廓模型基础上,结合K均值聚类提供的区域信息及心肌的生理结构约束对左心室的内外轮廓同时进行自动分割.实验结果表明,该算法能够有效地分割左心室内外轮廓.We propose an approach to segment the epicardium and endocardium in cardiac image automatically. Based on the knowledge on the circle-like shape of epicardium and endocardium, we first use Hough transform to detect circles for initial contours of the left ventricle. Based on the geodesic active contour model by integrating K-means clustering to provide regional information and the anatomical constraints, we then segment both the epicardium and endocardium automatically, from the initial contour detected by Hough transform. Experimental results demonstrate the effectiveness of our approach.

关 键 词：MR图像分割 K均值 HOUGH变换 测地线轮廓模型 左心室 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]