活体肝细胞磷31磁共振波谱数据分类

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

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。

Data based on ^31 phosphorus 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.