Abstract: The function of medical image mining in computer-aided diagnoses is discussed. The idea of using luminance grade as the features of CT image and the method of extracting and storing the luminance grade are proposed. The results of classification based on decision tree and clustering based on density to some brain and breast CT images and the analysis to them are introduced. Moreover, the conclusion and future work are given.

Key words: Image mining, Computer-aided diagnoses, Luminance grade, Classification, Clustering

摘要： 论述了医学图像挖掘在计算机辅助诊断中的作用，提出了采用灰度级作为CT图像特征的思想、灰度级的提取和存储方法，介绍了采用决策树分类算法和基于密度的聚类算法对胸部和头部CT图像进行分类和聚类的结果及其分析，给出了分析的结论和进一步的研究方向。

关键词: 图像挖掘, 计算机辅助诊断, 灰度级, 分类, 聚类