摘要
基于CT图像的肺实质分割不仅仅是后续图像处理最基础和最重要的技术，而且是一个典型的亟待解决的问题。本文利用水平集方法能初步获取较好的目标轮廓的特点和分水岭算法准确的边缘检测能力，提出一种基于水平集和分水岭相结合的改进轮廓检测算法。该算法采用由粗糙到准确的方式，在运用水平集演化初步检测目标轮廓的基础上，进一步运用标记分水岭算法检测准确的轮廓边界。结果表明，该方法能实现肺实质分割，解决了肺结节检测的预处理问题。
The lung parenchyma segmentation based on CT images is not only the most basic and important technology for the foUowing processing, but also a typically difficult problem. This paper gets an improved contour detection method based on level set and watershed transform. The manner from coarse to fine is adopted in the method. The level set is primarily employed to segment the image and then watershed is employed to obtain accurate contours without oversegmentation. The experimental results indicate that the method can effectively segment the pulmonary parenchyma, and solves the problem of preprocessing issue when detecting pulmonary nodules.
出处
《电子测试》
2013年第4期27-29,60,共4页
Electronic Test
关键词
图像分割
肺实质
肺部CT图像
水平集
分水岭变
image segmentation
lung parenchyma
lung fields CT image
level set
watershed transform
