基于肺部CT序列图像的肺实质三维分割

目的:肺实质分割是基于CT图像的肺结节计算机辅助检测技术必不可少的步骤。结合阈值技术、连通区域标记以及形态学技术,提出了一种简单有效的从CT图像中分割三维肺实质的方法,以期能为后续肺结节计算机辅助检测技术的研究奠定基础。方法:首先,将原图像二值化,并应用三维连通域标记去除背景及细小空洞;然后,经三维区域生长法去除气管;最后,经形态学滤波平滑肺边界得到肺部精确的三维模板,并采用该模板从CT序列图像中分割出肺实质。结果:根据对20组层厚2.0mm、每组约250个切片的肺部CT临床数据实验验证,其肺实质分割的平均正确度为91.55%,处理单组数据平均耗时167.4563s。结论:实验结果表明,本文方法能自动快速地从CT序列图像中分割出肺实质。

The Three-dimensional Lung Segmentation from CT Images

Objective： 3D （Three-dimensional） lung segmentation is an indispensable step in pulmonary nodules computer-aided detection based CT images. In this paper, we proposed a simple and effective 3D segmentation method, which combined the threshold, connected regional mark and morphological techniques. And we hope this can be the basis for the follow-up pulmonary nodules computer-aided detection technology study. Method： This method has four main steps. Firstly, binarized the CT images. Secondly, the lung region is extracted from the CT images by 3D connected component labeling. And then, the airway is removed by 3D region growing. Finally, a sequence of morphological operations is used to smooth the boundaries and fill the holes caused by small vessels and airways. Result： Using our method to segment 20 group lung CT clinical data, the segmentation average accuracy is 91.55%, and the average time-consuming to deal with a single group data is 167.4563s. Conclusion： The experimental results showed that this method can automatically and quickly segment the lung parenchyma.