標題: Comparison of the performance of linear multivariate analysis methods for normal and dyplasia tissues differentiation using autofluorescence spectroscopy
作者: Chu, Shou Chia
Hsiao, Tzu-Chien Ryan
Lin, Jen K.
Wang, Chih-Yu
Chiang, Huihua Kenny
資訊工程學系
Department of Computer Science
關鍵字: colorectal tissue;light-induced autofluorescence;multivariate linear regression;oral tissue;partial least squares;principal component analysis
公開日期: 1-十一月-2006
摘要: 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.
URI: http://dx.doi.org/10.1109/TBME.2006.883643
http://hdl.handle.net/11536/11573
ISSN: 0018-9294
DOI: 10.1109/TBME.2006.883643
期刊: IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
Volume: 53
Issue: 11
起始頁: 2265
結束頁: 2273
顯示於類別:期刊論文


文件中的檔案:

  1. 000241536900016.pdf