摘要
精确的肺实质三维分割是对肺部病变进行计算机辅助检测或诊断的必要步骤,但复杂的胸部组织结构使得肺实质的精确分割变得较为困难。提出了一种结合阈值分割、区域增长、改进波阵面法等多种方法的全自动的三维肺实质分割方法。该方法使用计算机视觉及图像分析小组/国际肺癌早期行动计划(Computer Vision and Image Analysis Group/International EarlyLung Cancer Action Program,VIA/I-ELCAP)和肺部图像数据库联盟(Lung Image Database Consortium,LIDC)提供的数据进行实验,结果证明这个方法能快速、精确地得到肺实质。
The precise three-dimensiona(l3-D) segmentation of pulmonary parenchyma from thorax X-ray computed tomography(CT)images is essential for the detection of pulmonary diseases.The complex 3-D structure of breast tissues in CT images makes precise segmentation difficult.A fully automatic 3-D segmentation algorithm is presented,which based on threshold,region growing and improved wavefront simulation model for extracting the 3-D pulmonary parenchyma from a X-ray CT dataset.The new algorithm is applied on the Computer Vision and Image Analysis Group/International Early Lung Cancer Action Program(VIA/I-ELCA) and Lung Image Database Consortium(LIDC) database.The results indicate that the algorithm is fast and precise for pulmonary parenchyma segmentation.
出处
《计算机工程与应用》
CSCD
北大核心
2011年第22期137-140,共4页
Computer Engineering and Applications
基金
广东省科技计划项目(No.2009B010800019)
广州市科技计划项目(No.2010J-E471)
广东省产学研项目(No.2010B090400543)
关键词
全自动
三维分割
肺实质
fully automatic
3D segmentation
pulmonary parenchyma