动态多分类器集成在肺结节辅助检测中的应用-计算机工程与应用.PDFVIP

218 2012 ，48 （2 ） Computer Engineering and Applications 计算机工程与应用 动态多分类器集成在肺结节辅助检测中的应用 1 1 1 2 韩妍妍 ，冯 筠 ，崔 鑫 ，王秋萍 1 1 1 2 HAN Yanyan , FENG Jun , CUI Xin , WANG Qiuping 1.西北大学 信息科学与技术学院，西安 710127 2.西安交通大学第一附属医院 放射科，西安 710061 1.School of Information Science and Technology, Northwest University, Xi ’an 710127, China 2.Department of Radiology, First Affiliated Hospital of Medical College of Xi ’an Jiaotong University, Xi ’an 710061, China HAN Yanyan, FENG Jun, CUI Xin, et al. Lung nodule detection based on Dynamic Multiple Classifiers Selection ensemble algo- rithm. Computer Engineering and Applications, 2012, 48 （2 ）：218-221. Abstract ：A novel approach based on Dynamic Multiple Classifiers Selection （DMCS ）ensemble algorithm is proposed based on the characteristics of diversity and inhomogeneity of the nodule lesions. The feature space is randomly divided into a number of feature sub- sets. Specifically, for different kinds of subset, more appropriate base classifier is selected based on their distributions. Then the results of the classifiers are ensembled for final decision. The experimental results demonstrate that the proposed algorithm achieves better per- formance than the typical and traditional nodule detection approaches. Key words ：lung nodule; dynamic multiple classifiers selection; integration algorithm; computer aided detection 摘 要：针对肺结节病灶数据具有多样性及异质性特点，提出了动态多分类器选择集成算法（Dynamic Multiple Classifiers Se- lection ，DMCS ），将特征空间随机划分为若干特征子集，针对每个特征子集样本分布不同，对不同的特征子集选择适合的基分类 器，最后进行集成学习。实验表明，该算法比目前有代表性的肺结节检测病灶分类算法具有更好的稳定性和检测性能。 关键词：肺结节；动态多分类器选择；集成算法；计算机辅助检测 DOI ：10.3778/j.issn. 1002-8331.2012.02.063 文章编号：1002-8331（2012 ）02-0218-04 文献标识码：A 中图分类号：TP391.4 1 引言 除肺结核，减少假阳，正确率达到95.21%[2] 。Temesguen Messay 近年来，随着空气污染的