基于活动轮廓模型的超声心脏图像轮廓的自动检测  

Auto-detection of Contour in Echocardiographic Images Based on Active Contour Model

作　　者：何爱军[1] 汪天富[1] 郑昌琼[1] 郑翊 李德玉[1] 赵树魁[1] 

机构地区：[1]四川大学生物医学工程中心,373信箱成都610065 [2]Department of Electrical Engineering

出　　处：《生物医学工程学杂志》2001年第2期242-246,253,共6页Journal of Biomedical Engineering

基　　金：国家自然科学基金资助课题 (6 96 310 2 0 ;6 9972 0 2 9)

摘　　要：轮廓的提取是超声医图像学多维重建中最困难的问题之一。本文提出了一种超声心脏图像轮廓的自动检测方法。首先 ,根据超声图像的特点 ,对超声图像进行自适应加权中值滤波以消除斑点噪声。然后利用数学形态学的方法提取出心脏的初始轮廓。最后 ,运用活动轮廓模型 ,对初始轮廓进行逼近 ,得到精确的心脏轮廓。实验结果显示了方法的有效性。本方法在心脏超声图像的多维重建过程中 。Contour detection is one of the most difficult problems in the multi-dimensional reconstruction of e-chocardiographic images. A method based on active contour model is presented in the present paper to solve this problem. First, according to the characteristic of the ultrasonic medical images, an adaptive weighted median filter is used to suppress speckle noise and an adaptive threshold value is selected to get binary image. Then, mathematical morphological treatment is utilized to get the initial contour. At last, active contour model is employed to revise the initial contour and get the accurate final contour. Experiments with real and interpolated ultrasonic images are presented. The results show the effectiveness of this method. This method has practical use in the multi-dimensional reconstruction of ultrasonic medical images.

关 键 词：超声医学图像 活动轮廓模型 数学形态学 边缘检测 

分 类 号：R540.45[医药卫生—心血管疾病]