利用自体荧光光谱法对正常组织和发育异常组织进行鉴别时线性多变量分析方法的性能比较。

Comparison of the performance of linear multivariate analysis methods for normal and dyplasia tissues differentiation using autofluorescence spectroscopy.

作者信息

Chu Shou Chia, Hsiao Tzu-Chien Ryan, Lin Jen K, Wang Chih-Yu, Chiang Huihua Kenny

机构信息

Institute of Biomedical Engineering, National Yang-Ming University, Taipei, Taiwan ROC.

出版信息

IEEE Trans Biomed Eng. 2006 Nov;53(11):2265-73. doi: 10.1109/TBME.2006.883643.

DOI:10.1109/TBME.2006.883643

PMID:17073332

Abstract

We compared the performance of three widely used linear multivariate methods for autofluorescence spectroscopic tissues differentiation. Principal component analysis (PCA), partial least squares (PLS), and multivariate linear regression (MVLR) were compared for differentiating at normal, tubular adenoma/epithelial dysplasia and cancer in colorectal and oral tissues. The methods' performances were evaluated by cross-validation analysis. The group-averaged predictive diagnostic accuracies were 85% (PCA), 90% (PLS), and 89% (MVLR) for colorectal tissues; 89% (PCA), 90% (PLS), and 90% (MVLR) for oral tissues. This study found that both PLS and MVLR achieved higher diagnostic results than did PCA.

摘要

我们比较了三种广泛使用的线性多变量方法在自体荧光光谱组织鉴别中的性能。对主成分分析（PCA）、偏最小二乘法（PLS）和多元线性回归（MVLR）在结直肠和口腔组织的正常组织、管状腺瘤/上皮发育异常和癌症鉴别中的性能进行了比较。通过交叉验证分析评估了这些方法的性能。结直肠组织的组平均预测诊断准确率分别为85%（PCA）、90%（PLS）和89%（MVLR）；口腔组织的组平均预测诊断准确率分别为89%（PCA）、90%（PLS）和90%（MVLR）。本研究发现，PLS和MVLR均比PCA取得了更高的诊断结果。