| 面向肺癌CAD系统的感兴趣区域特征选择与分类算法 |
| |
| 引用本文： | 魏颖,郭薇,孙月芳,赵大哲,季策.面向肺癌CAD系统的感兴趣区域特征选择与分类算法[J].信息与控制,2008,37(4):1-1. |
| |
| 作者姓名： | 魏颖 郭薇 孙月芳 赵大哲 季策 |
| |
| 作者单位： | 东北大学信息科学与工程学院,辽宁,沈阳,110004 |
| |
| 基金项目： | 国家自然科学基金，辽宁省自然科学基金 |
| |
| 摘 要： | 本文重点研究ROI 的特征提取与分类方法．首先，根据医学征象对ROI 进行特征提取；为了提高
分类的准确性，采用概率分布可分性对原始提取的特征进行特征选择．然后，利用SVM 对选择的特征进行定
量描述；采用特征量化参数对Mahalanobis 距离进行加权改进，加权的Mahalanobis 距离使类间差别明显增大．
最后采用加权改进后的Mahalanobis 距离将ROI 分类为结节或非结节．利用所提ROI 特征选择和分类算法进
行肺结节检测实验；肺结节检测灵敏度为94.6%，漏诊率为5.4%，可以为医生进行肺癌早期诊断提供帮助信
息．
|
| 关 键 词： | 肺癌计算机辅助诊断CAD 感兴趣区域ROI 特征提取 概率可分性 特征选择 加权 |
Feature Selection and Classification Algorithm for Region of Interest in Lung Cancer CAD System |
| |
| WEI Ying,GUO Wei,SUN Yue-fang,ZHAO Da-zhe,JI Ce.Feature Selection and Classification Algorithm for Region of Interest in Lung Cancer CAD System[J].Information and Control,2008,37(4):1-1. |
| |
| Authors: | WEI Ying GUO Wei SUN Yue-fang ZHAO Da-zhe JI Ce |
| |
| Affiliation: | WEI Ying,GUO Wei,SUN Yue-fang,ZHAO Da-zhe,JI Ce(College of Information Science , Engineering,Northeastern University,Shenyang 110004,China) |
| |
| Abstract: | Feature selection and classification of region of interest(ROI) is investigated in this paper.Firstly,several features of ROI are extracted according to medical symptoms,and in order to improve the classification accuracy,these features are selected by their separability of probability distribution.Secondly,the selected features are described quantita-tively by SVM.Quantitative feature parameters are used to improve Mahalanobis distance with weight,and the improved Mahalanobis distance can enlarge the diffe... |
| |
| Keywords: | lung cancer computer-aided diagnosis(CAD) region of interest(ROI) feature extracting separability of probability feature selection weighted Mahalanobis distance classification of ROI |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《信息与控制》浏览原始摘要信息 |
|
点击此处可从《信息与控制》下载全文 |
|
