计算机工程与应用 ›› 2011, Vol. 47 ›› Issue (9): 236-239.

• 工程与应用 • 上一篇    下一篇

活体肝细胞磷31磁共振波谱数据分类

桑 君1,刘毅慧1,王韶卿2,刘 强2,成金勇1   

  1. 1.山东轻工业学院 信息科学与技术学院 智能信息处理研究所,济南 250353
    2.山东省医学影像学研究所,济南 250021
  • 收稿日期:1900-01-01 修回日期:1900-01-01 出版日期:2011-03-21 发布日期:2011-03-21

Classification of 31phosphorus magnetic resonance spectroscopy data for liver cell in vivo

SANG Jun1,LIU Yihui1,WANG Shaoqing2,LIU Qiang2,CHENG Jinyong1   

  1. 1.Institute of Intelligence Information Processing,School of Information Science and Technology,Shandong Institute of Light Industry,Jinan 250353,China
    2.Shandong Medical Imaging Research Institute,Jinan 250021,China
  • Received:1900-01-01 Revised:1900-01-01 Online:2011-03-21 Published:2011-03-21

摘要: 基于活体肝细胞的31P磁共振波谱图(31Phosphorus Magnetic Resonance Spectroscopy,31P-MRS)对肝细胞数据进行诊断,分为3种类型:肝癌、肝硬化和正常肝。分别运用线性分类器和二次分类器对数据分类,并在分类前进行了特征抽取。线性分类器和二次分类器在“留一法”中对上述3种类型的分类准确率分别约为81.37%、77.75%、92.30%和95.27%、99.89%、99.70%。实验证明二次分类器相对于线性分类器,明显地提高了分类准确率。

关键词: 31P, 磁共振波谱, 线性判别分析, 二次分类器

Abstract: Data based on 31phosphorus magnetic resonance spectroscopy map of liver cells in vivo are divided into three diagnostic types of hepatocellular carcinoma,hepatic cirrhosis and normal hepatic tissue.The data are classified using linear classifier and quadratic classifier separately,and main features are selected before classification.Classification accuracy rate of the data in leave-one-out method when linear classifier and quadratic classifier are used are about 81.37%、77.75%、92.30% and 95.27%、99.89%、99.70% separately.Experiments prove that the classification accuracy rate of the data when quadratic polynomial classifier is used is obviously improved,compared to linear classifier.

Key words: 31phosphorus, magnetic resonance spectroscopy, linear discriminant analysis, quadratic classifier