宋佳,李翠芳,孙希文,聂生东.一种非实质性肺结节分割的新方法[J].中国医学影像技术,2011,27(12):2531~2535
一种非实质性肺结节分割的新方法
A new method for segmenting nonsolid nodules on CT images
投稿时间:2011-04-25  修订日期:2011-08-01
DOI:
中文关键词:  非实质性肺结节  三维分割  模糊隶属度模型  Hessian矩阵特征值
英文关键词:Nonsolid pulmonary nodule  Three-dimensional segmentation  Fuzzy membership model  Hessian matrix eigenvalue
基金项目:国家自然科学基金(60972122)、上海市教委科研创新项目(09YZ216)。
作者单位E-mail
宋佳 上海理工大学医学影像工程研究所,上海 200093  
李翠芳 上海理工大学医学影像工程研究所,上海 200093  
孙希文 上海市肺科医院影像科,上海 200433  
聂生东 上海理工大学医学影像工程研究所,上海 200093 nsd4647@sohu.com 
摘要点击次数: 3554
全文下载次数: 978
中文摘要:
       本文提出一种分割非实质性肺结节的新方法。首先通过阈值操作去除高亮的实质部分;其次根据模糊数学建立非实质性肺结节的模糊隶属度模型,并根据该模型计算各体素对非实质性肺结节的隶属度,以此为特征向量进行体素分类;然后基于Hessian矩阵的特征值进行血管增强,通过阈值去除血管;最后通过三维连通域标记获取非实质性肺结节。实验结果表明,应用本文方法能够比较准确地将非实质性肺结节分割出来,分割效果优于目前文献报道的其他方法。本文方法可作为分割非实质性肺结节的工具。
英文摘要:
      To solve the current segmenting problems in nonsolid pulmonary nodules, a new three-dimensional segmentation method based on a fuzzy membership model was developed. Firstly, a single intensity threshold was used to separate the solid voxels. Secondly, a fuzzy membership model of nonsolid nodule was built and combining with linear discriminant a voxel classifier is produced. Then blood vessels were enhanced using hessian matrix eigenvalue and deleted by a simple threshold. Finally, the nonsolid nodule was gotten through 3D connected component labeling. This method was experimented on clinical CT data, and achieved good results, showing that the proposed method can be used as a good tool to segment nonsolid nodules in CAD systems.
查看全文  查看/发表评论  下载PDF阅读器