计算机应用 ›› 2013, Vol. 33 ›› Issue (04): 1108-1111.DOI: 10.3724/SP.J.1087.2013.01108

• 多媒体处理技术 • 上一篇    下一篇

基于尺度空间中多特征融合的医学影像分类

李博1,2,曹鹏1,2,栗伟1,2,赵大哲1,2   

  1. 1. 东北大学 信息科学与工程学院,沈阳 110004
    2. 医学影像计算教育部重点实验室(东北大学),沈阳 110179
  • 收稿日期:2012-10-23 修回日期:2012-11-22 出版日期:2013-04-01 发布日期:2013-04-23
  • 通讯作者: 李博
  • 作者简介:李博(1985-),男,辽宁沈阳人,博士研究生,主要研究方向:医学影像挖掘、医学影像检索;曹鹏(1982-),男,辽宁沈阳人,博士研究生,主要研究方向:机器学习、医学影像挖掘;栗伟(1980-),男,辽宁沈阳人,博士研究生,主要研究方向:医学文本挖掘;赵大哲(1960-),女,辽宁沈阳人,教授,博士生导师,主要研究方向:软件工程、数据挖掘、医学影像处理。
  • 基金资助:

    国家自然科学基金资助项目(51005237);中央高校基本科研业务费专项资金资助项目(N110618001)

Medical image classification based on scale space multi-feature fusion

LI Bo1,2,CAO Peng2,3,LI Wei2,3,ZHAO Dazhe2,3   

  1. 1. College of Information Science and Engineering, Northeastern University, Shenyang Liaoning 110004, China
    2. Key Laboratory of Medical Image Computing, Ministry of Education (Northeastern University), Shenyang Liaoning 110179, China
    3. College of Information Science and Engineering, Northeastern University, Shenyang Liaoning 110004, China
  • Received:2012-10-23 Revised:2012-11-22 Online:2013-04-01 Published:2013-04-23
  • Contact: LI Bo

摘要: 针对现有医学影像分类方法对临床不同类别影像特征描述效果不一致,且尺度变化敏感的问题,提出一种基于尺度空间提取多特征进行融合的分类方法。首先构建高斯差分尺度空间,然后在尺度空间中分别从灰度、纹理、形状、频域四种互补的角度描述医学影像,最后基于最大似然估计理论构建决策级特征融合模型,实现医学影像分类。严格依照IRMA医学影像类别编码标准选择实验数据,结果表明所提方法相对已有方法分类的平均F1值得到了5%~20%不同程度的提高, 更全面描述医学影像信息, 避免了特征降维造成的信息损失,有效提高了分类的准确率,具有临床应用价值。

关键词: 图像分类, 决策级融合, 多特征, 尺度空间, 最大似然估计

Abstract: In order to describe different kinds of medical image more consistently and reduce the scale sensitivity, a classification model based on scale space multi-feature fusion was proposed according to the characteristics of medical image. First, scale space was built by difference of Gaussian, and then complementary features were extracted, such as gray-scale features, texture features, shape features, and features extracted in the frequency domain. In addition, maximum likelihood estimation was considered to realize decision level fusion. The scale space multi-feature fusion classification model was applied to medical image classification task following IRMA code. The experimental results show that compared with traditional methods, F1 value increased 5%-20%. Fusion classification model describes medical image more comprehensively, avoids the information loss from feature dimension reduction, improves classification accuracy, and has clinical value.

Key words: image classification, decision level fusion, multi-feature, scale space, maximum likelihood estimation

中图分类号: