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。
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.
出处
《计算机工程与应用》
CSCD
北大核心
2007年第36期211-213,共3页
Computer Engineering and Applications
基金
国家自然科学基金(the National Natural Science Foundation of China under Grant No.60572112)
关键词
多分类器组合
朴素贝叶斯
神经网络
决策树
multiple classifiers combination
Naive hayes
BP neural network
decision tree