TY - JOUR
T1 - Comparison of the performance of linear multivariate analysis methods for normal and dyplasia tissues differentiation using autofluorescence spectroscopy
AU - Shou, Chia Chu
AU - Hsiao, Tzu Chien Ryan
AU - Lin, Jen K.
AU - Wang, Chih Yu
AU - Huihua, Kenny Chiang
PY - 2006/11/1
Y1 - 2006/11/1
N2 - 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.
AB - 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.
KW - Colorectal tissue
KW - Light-induced autofluorescence
KW - Multivariate linear regression
KW - Oral tissue
KW - Partial least squares
KW - Principal component analysis
UR - http://www.scopus.com/inward/record.url?scp=33750305316&partnerID=8YFLogxK
U2 - 10.1109/TBME.2006.883643
DO - 10.1109/TBME.2006.883643
M3 - Article
C2 - 17073332
AN - SCOPUS:33750305316
SN - 0018-9294
VL - 53
SP - 2265
EP - 2273
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 11
ER -