线性辨别分析与人工神经网络用于血清光谱对于肝癌、肝硬化的诊断  

Linear Discriminant Analysis and Artificial Neural Network Applied to the Serum Spectroscopy for the Diagnosis of Liver Cancer and Liver Cirrhosis

作　　者：李晓舟[1,2] 杨天月[1] 孙宝明 

机构地区：[1]沈阳理工大学理学院光电子与激光生物医学研究中心,沈阳110168 [2]大连理工大学物理与光电工程学院光电信息工程与技术实验室,大连116024 [3]沈阳永源科技开发有限公司,沈阳110006

出　　处：《光散射学报》2010年第4期377-381,共5页The Journal of Light Scattering

摘　　要：本文探测了人体血清的自体荧光-拉曼光谱,采用多元统计方法中的主元分析法(PCA)对光谱进行分析,并利用线性辨别分析(LDA)作为诊断算法,与此同时,用人工神经网络进行交叉认证。PCA-LDA的灵敏度和特异性分别为88.00%和79.14%,PCA-ANN的为89.29%和94.74%。In this paper,laser-induced fluorescence（LIF） and Raman spectra of human serum were measured simultaneously using our fluorescence-Raman spectroscopy system,then the spectra was analyzed the multivariate statistical methods of principle component analysis（PCA）.Then linear discriminant analysis（LDA） was utilized to differentiate the loading score plot of different diseases as the diagnosing algorithm.Artificial neural network（ANN） was used for cross-validation.The diagnosis sensitivity and specificity by PCA-LDA are 88.00% and 79.14%,while that of the PCA-ANN are 89.29% and 94.74%.

关 键 词：荧光 拉曼光谱 PCA-LDA PCA-ANN 肝癌 肝硬化 

分 类 号：O433.1[机械工程—光学工程] O433.4[理学—光学]