| 基于局部闭值和聚类中心迭代的肺结节检测算法 |
| |
| 引用本文： | 陈侃,李彬,田联房.基于局部闭值和聚类中心迭代的肺结节检测算法[J].计算机科学,2012,39(2):302-304. |
| |
| 作者姓名： | 陈侃 李彬 田联房 |
| |
| 作者单位： | 华南理工大学自动化科学与工程学院 广州510640 |
| |
| 基金项目： | 广东省教育部产学研结合项目，教育部博士点基金资助项目，广州市番禺区科技攻关项目，华南理工大学中央高校基本科研业务费 |
| |
| 摘 要： | 肺部疾病通常以肺结节的形式表现出来。为了对肺部疾病进行诊断治疗,需要对肺结节进行准确的检测。提出了基于局部阈值和聚类中心迭代的肺结节检测算法。首先,对肺实质图像采用局部阈值算法,提取感兴趣区域(ROIs),并且计算ROIs的形态特征、灰度特征和纹理特征;其次,结合规则、聚类中心迭代和欧式距离,对ROIs进行分类。实验结果表明,所提算法能够较好地检测出孤立性结节、低对比度结节和粘连肺壁结节。
|
| 关 键 词： | 肺结节 局部阈值 聚类中心迭代 欧式距离 |
Pulmonary Nodules Detection Algorithm Based on Local Threshold and Iterative of Clustering Center |
| |
| CHEN Kan
,
LI Bin
,
TIAN Lian-fang.Pulmonary Nodules Detection Algorithm Based on Local Threshold and Iterative of Clustering Center[J].Computer Science,2012,39(2):302-304. |
| |
| Authors: | CHEN Kan LI Bin TIAN Lian-fang |
| |
| Affiliation: | CHEN Kan LI Bin TIAN Lian-fang(School of Automation Science and Engineering,South China University of Technology,Guangzhou 510640,China) |
| |
| Abstract: | Lung disease is usually showed in the form of pulmonary nodules.In order to diagnose lung disease,pulmonary nodules must be detected accuratly.This paper proposed pulmonary nodules detection algorithm based on local threshold and iterative of clustering center.First,local algorithm was proposed for extracting interested region(ROIs) in lung parenchyma image.Morphological features,gray features and texture features were calculated in interested region(ROIs).Second,rule,iterative algorithm of clustering center and Euclidean distance were used to classing ROIs.Experiment results show that the proposed algorithm can better detect isolation nodules,low contrast nodules and nodules which adhere to lung wall. |
| |
| Keywords: | Pulmonary nodules Local threshold Iterative of clustering center Euclidcan distance |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
点击此处可从《计算机科学》下载全文 |
|
