摘要
为了能够在肺癌早期或者例行体检时及时发现肺部结节灶,临床上要求能够对肺结节进行全面迅速的检测。提出了一种新的肺结节检测算法——TMH(引入了Hessian矩阵的模版匹配)算法。该算法首先获取肺实质;然后在二维层面上采用模版匹配方法(Template-Matching,TM)对结节进行检测;最后引入Hessian矩阵,有效降低了原TM算法的假阳率,实验证明该算法能够快速检测出肺结节,且假阳率较小。
In order to find the pulmonary nodules at the early monary nodules quickly and completely,especially to the small stage of lung cancer or in duty check,we must detect the pulnodules which are always omitted by doctors.A new TMH（Template-Matching with Hessian matrix） method is proposed in this paper.Firstly lung lobes are gained.Then TM （Template-Matching method） is used to detect the pulmonary nodules.At last the Hessian matrix is imported to the method.TMH method has been proved to be quick,complete and low true positive rate.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第23期198-199,共2页
Computer Engineering and Applications
基金
国家重点基础研究发展规划(the National Grand Fundamental Research Program of China under Grant No.2003CB716101)
广东省自然科学基金(the Natural Science Foundation of Guangdong Province of China under Grant No.06024419)
关键词
肺结节
模版匹配
HESSIAN矩阵
TMH算法
pulmonary nodule
Template-Matching （TM）
Hessian matrix
Template-Matching with Hessian matrix （TMH）
