| 基于局部灰度最大和改进Mahalanobis距离分类的肺结节检测算法 |
| |
| 引用本文： | 魏颖,郭薇,孙月芳,季策.基于局部灰度最大和改进Mahalanobis距离分类的肺结节检测算法[J].中国图象图形学报,2008,13(9). |
| |
| 作者姓名： | 魏颖 郭薇 孙月芳 季策 |
| |
| 作者单位： | 东北大学信息科学与工程学院 |
| |
| 基金项目： | 国家自然科学基金，辽宁省自然科学基金 |
| |
| 摘 要： | CT图像中肺结节检测一直是肺癌CAD系统的关键和难点。提出了一种孤立性肺结节自动检测算法,首先对原始CT图像进行有效、准确的肺实质分割;采用寻找局部灰度最大值方法对ROI进行初始分割;再对分割出的各ROI进行特征提取,利用SVM方法对每个特征进行定量描述,根据SVM单特征分类准确率对Mahalanobis距离进行加权改进,最后采用基于改进的Mahalanobis距离进行肺结节分类。实验结果表明,该算法可以较好地提取出CT图像中的孤立性肺结节,具有较高的灵敏度和较低的漏诊率,可以为医生诊断早期肺癌病灶提供帮助信息。
|
| 关 键 词： | 肺癌CAD 孤立性肺结节 局部灰度最大 加权的Mahalanobis距离 分类 |
A Lung Nodule Detection Algorithm Based on Local Maximum Gray Segmenting and Improved Mahalanobis Distance Classifying |
| |
| WEI Ying,GUO Wei,SUN Yue-fang,JI Ce.A Lung Nodule Detection Algorithm Based on Local Maximum Gray Segmenting and Improved Mahalanobis Distance Classifying[J].Journal of Image and Graphics,2008,13(9). |
| |
| Authors: | WEI Ying GUO Wei SUN Yue-fang JI Ce |
| |
| Abstract: | It is hard to detect lung nodules automatically from CT images for lung CAD system.A detection algorithm is proposed for solitary pulmonary nodules(SPNs) in thoracic CT images in this paper.Firstly,lung field is segmented from original CT image effectively and accurately.Secondly,areas of local maximum gray are found,to segment regions of interest(ROIs) roughly.Then,features of each ROI are extracted,each feature is described quantitatively by the accuracy of SVM classification with each single feature separately,and Mahalanobis distance is weighted by the quantitative parameters.Finally,ROIs are classified to nodule or non-nodule with the improved Mahalanobis distance.Experiment results indicated that the algorithm can detect SPNs effectively,it is with relatively high sensitivity and low false neglected rate,and it can provide doctors helpful information to diagnose lesions in early stage of lung cancer. |
| |
| Keywords: | lung cancer CAD solitary pulmonary nodule local gray maximum weighted Mahalanobis distance classification |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《中国图象图形学报》浏览原始摘要信息 |
|
点击此处可从《中国图象图形学报》下载免费的PDF全文 |
|
