|
|||||
|
|
| 基于遗传算法和支持向量机的肺结节检测 | |
| 引用本文： | 孙申申,任会之,康雁,赵宏.基于遗传算法和支持向量机的肺结节检测[J].系统仿真学报,2011,23(3):497-501,566. |
| 作者姓名： | 孙申申 任会之 康雁 赵宏 |
| 作者单位： | 1. 沈阳大学信息工程学院,沈阳,110044 2. 东北大学信息工程学院,沈阳,110004 3. 东北大学中荷生物医学工程学院,沈阳,110004 |
| 摘 要： | 针对圆点滤波器不能区分粘连血管型结节、血管端点和血管交叉结构,造成假阳率高的问题,提出基于改进遗传算法封装模型的特征选择算法,并把最优特征组合输入到支持向量机分类器,该分离器能做到检测肺结节时漏检率低同时降低假阳率。选出七个特征(其中包含两种新提出的特征)作为最优特征组合。用含有肺结节的CT影像数据库(50个结节和961个假阳)测试分类器的性能,得到敏感性100%和特异性95.5%的效果。实验结果表明,该框架和算法能应用到临床中来提高影像科医生的阅片效率。改进的遗传算法比传统的遗传算法能搜索到更优的特征组合。 |
| 关 键 词： | 肺结节检测 遗传算法 支持向量机 特征选择 粘连血管型结节 |
Lung Nodule Detection by GA and SVM |
|
| SUN Shen-shen,REN Hui-zhi,KANG Yan,ZHAO Hong.Lung Nodule Detection by GA and SVM[J].Journal of System Simulation,2011,23(3):497-501,566. | |
| Authors: | SUN Shen-shen REN Hui-zhi KANG Yan ZHAO Hong |
| Institution: | SUN Shen-shen1,REN Hui-zhi2,KANG Yan3,ZHAO Hong2(1.Information Engineering College,Shenyang University,Shenyang 110044,China,2.Information Engineering College,Northeastern University,Shenyang 110004,3.Sino-Dutch Biomedical and Information Engineering School,China) |
| Abstract: | To solve the problem that the vascular adhesion nodule and vascular-crossing could not be distinguished by dot filter and make high rate of false positive,a feature subset selection method based on improved genetic algorithms in wrapper model was proposed,and the best feature subset was used to establish a classifier based on support vector machines to improve the performance by reducing false positive and retaining true nodule.From 22 features(including three newly proposed features) which were calculated ... |
| Keywords: | lung nodule detection genetic algorithms support vector machines feature selection vascular adhesion nodule |
| 本文献已被 CNKI 万方数据 等数据库收录！ | |