期刊文献+

结合规则和SVM方法的肺结节识别 被引量:9

Lung Nodule Recognition Combining Rule-Based Method and SVM
下载PDF
导出
摘要 为识别CT图像中的肺结节,提出了一种结合规则和支持向量机(SVM)的识别方法,来对分割出来的感兴趣区域(ROI)进行分类.该方法首先计算候选ROI的形态特征,利用基于规则的方法筛去非结节的区域;然后把筛选之后剩余的候选ROI作为测试样本和训练样本,计算它们的灰度和纹理等特征;最后把灰度、形态和纹理特征值作为SVM的输入,对经过基于规则筛选之后剩余的ROI进行分类.实验结果表明:基于规则的方法虽然没有漏检,但误判的可能性最大;结合规则和SVM的方法漏检的可能性要比SVM方法漏检的大,但误判的可能性小. In order to effectively recognize lung nodules in CT images,a recognition method combining the rule-based method and the support vector machine(SVM) is proposed to classify the regions of interest(ROIs).In this method,first,shape features of candidate ROIs are calculated,and some non-nodule regions are filtered out by using the rule-based method.Then,the remaining candidate ROIs are taken as testing and training samples,whose grayscale and texture features are calculated and used as the inputs of SVM to classify the remaining candidate ROIs.Experimental results show that the rule-based method may result in high possibility of misdiagnosis although there is no nodule omission,while the proposed method combining the rule-based method and the SVM is of low possibility of misdiagnosis but of obvious nodule omission.
出处 《华南理工大学学报(自然科学版)》 EI CAS CSCD 北大核心 2011年第2期125-129,147,共6页 Journal of South China University of Technology(Natural Science Edition)
基金 中国博士后科学基金资助项目(20090450866) 广东省教育部产学研结合项目(2009B090300057) 教育部高等学校博士学科点专项科研基金资助项目(200805610018) 广东省自然科学基金资助项目(8451064101000631) 广州市番禺区科技攻关项目(2009-Z-108-1) 华南理工大学中央高校基本科研业务费资助项目(2009ZM0077)
关键词 图像识别 肺结节 分类器 支持向量机 规则 image recognition lung nodule classifier support vector machine rule
  • 引文网络
  • 相关文献

参考文献16

  • 1Lin Daw-yung, Yan Chung-ren, Chen Wen-tai. Autonomous detection of pulmonary nodules on CT images with a neural network-based fuzzy system [ J ]. Computerized Medical Imageing and Graphics,2005,29:447-458.
  • 2Xu X W, Doi K, Kobayashi T, et al. Development of an improved CAD scheme for automated detection of lung nodules in digital chest images [ J ]. Medical Physics, 1997,24(9) :1395-1403.
  • 3Kanazawa K, Kawata Y, Niki N, et al. Computer-aided diagnosis for pulmonary nodules based on helical CT images[J]. Computerized Medical Imaging and Graphics, 1998, 22 : 157-167.
  • 4Satoh H, Ohmatsu H, Kakinuma R,et al. Lung cancer detection based on helical CT images using curves surface morphology analysis [ J ]. Proceeding of SPIE, 1999, 3661 : 1307-1314.
  • 5Vapnik V. The nature of statistical learning theory [ M ]. New York : Springer-Verlag, 1995:91-188.
  • 6Cristianini N,Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods [ M ]. Cambridge : Cambridge University Press, 2000 : 47-98.
  • 7Dehmeshki Jamshid, Chen Jun, Casique M V, et al. Classification of lung data by sampling and support vector machine [C]//Proceedings of the 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. San Francisco : IEEE,2004 : 3194-3197.
  • 8Lilla B, Zhao Luyin, Lee K P. Feature subset selection for improving the performance of false positive reduction in lung nodule CAD [ J ]. IEEE Transactions on Information Technology in Biomedicine ,2006,10( 3 ) :504-511.
  • 9Ganeshan B, Miles K A,Young R C, et al. Texture analysis in non-contrast enhanced CT:impact of malignancy on texture in apparently disease-free areas of the liver [ J ]. European Journal of Radiology,2009,70( 1 ) : 101-110.
  • 10Gurcan Metin N, Sahiner Berkman, Petrick Nicholas, et al. Lung nodule detection on thoracic computed tomo- graphy images: preliminary evaluation of a computeraided diagnosis system [ J ]. Medical Physics, 2002, 29 ( 11 ) :2552-2558.

同被引文献42

  • 1李阳,史东承,王珂,王燕,魏艳芳.基于图像模式的肺结节识别[J].吉林大学学报(工学版),2013,43(S1):463-467. 被引量:3
  • 2聂生东,郑斌,李雯.CT图像肺结节计算机辅助检测与分类系统设计(英文)[J].系统仿真学报,2007,19(5):935-944. 被引量:14
  • 3Corinna Cortes,Vladimir Vapnik.Support-Vector Networks[J]Machine Learning,1995(3).
  • 4Farag A, Ayman E B , Gimel F G , et al. Detection and recognition of lung nodules in spiral CT images using deformable templates and Bayesian post-classi- fication[C]//International Conference on Image Pro- cessing(ICIP 2004), Singapore, 2004.
  • 5Kenji S, Li F, Sone S, et al. Computer-aided diag- nostic scheme for distinction between benign and malignant nodules in thoracic low-dose CT by use of massive training artificialneural network[J]. IEEE Transactions on Medical Imaging, 2005, 24 (9) : 1138-1150.
  • 6Suzuki K, Armato S G, Li F, et al. Massive train- ing artificial neural network (MTANN) for reduc- tion of false positives in computerized detection of lung nodules in low-dose computed tomography[J]. Med Phys, 2003, 30(6): 1602-1617.
  • 7Wang Z, Chen S C. New least squares support vec- tor machines based on matrix patterns[J]. Neural Processing Letters, 2007, 26(1): 41-56.
  • 8Wang Q Z,Kang W W, Wu C M, et al. Computer- aided detection of lung nodules by SVM based on 3D matrix patterns[J]. Clinical Imaging, 2013, 37(1) 62-69.
  • 9Chih-Chung Chang,Chih-Jen Lin.LIBSVM[J]ACM Transactions on Intelligent Systems and Technology (TIST),2011(3).
  • 10J. R. Quinlan.Induction of decision trees[J]. Machine Learning . 1986 (1)

引证文献9

二级引证文献48

;
使用帮助 返回顶部