计算机工程与应用 ›› 2007, Vol. 43 ›› Issue (36): 211-213.

• 工程与应用 • 上一篇    下一篇

基于Cascade组合分类器的医学图像分类方法研究

张春芬1,朱玉全1,陈 耿2,王 敏1   

  1. 1.江苏大学 计算机科学与通信工程学院,江苏 镇江 212013
    2.南京审计学院,南京270029
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2007-12-21 发布日期:2007-12-21
  • 通讯作者: 张春芬

Research on medical image classification based on Cascade combined classifiers

ZHANG Chun-fen1,ZHU Yu-quan1,CHEN Geng2,WANG Min1   

  1. 1.School of Computer Science and Telecommunications Engineering,Jiangsu University,Zhenjiang,Jiangsu 212013,China
    2.Nanjing Audit University,Nanjing 270029,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2007-12-21 Published:2007-12-21
  • Contact: ZHANG Chun-fen

摘要: 提出了利用Cascade组合方法生成基于贝叶斯、神经网络与决策树的组合分类器,并将之应用到肝脏图像的分类中。实验结果表明,与现有医学图像分类方法相比,该组合方法可以有效地提高医学图像分类的准确性和稳定性。

关键词: 多分类器组合, 朴素贝叶斯, 神经网络, 决策树

Abstract: Based on Cascade combination algorithm,two combined classifiers constructed by naive bayes,BP neural network and decision tree are developed and applied to lung images classification.Compared with existing medical image classifications,experiment results indicate that this method can obviously improve the accuracy and stability of medical image classification.

Key words: multiple classifiers combination, Naive bayes, BP neural network, decision tree