摘要
为有效准确地提取人体肝脏CT图像的轮廓特征,实现人体腹部软组织三维可视化重构,提出一种基于Splines小波仿射调幅的肝脏CT图像提取算法。利用Splines双正交小波对CT图像进行增强处理,对增强处理后的边缘先验知识进行套索模型初始化,利用仿射变换调幅技术对传统的Snake算法进行改进,增强图像的边缘幅度,有效提取肝脏CT图像的边缘特征。仿真实验表明,该算法能有效实现CT图像边缘轮廓提取,边缘轮廓点更加接近于真实的肝脏边缘。该方法也可以用于其它医学图像器官轮廓线的分割与提取。
For extracting the contour the human liver CT image accurately, realization of human abdominal soft tissue visual-ization of three-dimensional reconstruction, an extraction algorithm of liver CT image based on Splines wavelet affine am-plitude modulation was proposed. Using the Splines biorthogonal wavelet for enhancement on CT images, the lasso model initialization of the enhanced edge prior knowledge was obtained. Affine transform amplitude modulation technology was taken for improve the traditional Snake algorithm. The liver CT batch was realized. Simulation results show that the method can realize the CT image edge detection effectively. The contour points are closer to the edge of real liver. This method can also be used for medical image segmentation and extraction of other organ contour.
出处
《科技通报》
北大核心
2014年第8期62-64,共3页
Bulletin of Science and Technology
