9 June 2015 Discrimination of healthy and osteoarthritic articular cartilages by Fourier transform infrared imaging and partial least squares-discriminant analysis
Author Affiliations +
Abstract
Fourier transform infrared imaging (FTIRI) combined with chemometrics algorithm has strong potential to obtain complex chemical information from biology tissues. FTIRI and partial least squares-discriminant analysis (PLS-DA) were used to differentiate healthy and osteoarthritic (OA) cartilages for the first time. A PLS model was built on the calibration matrix of spectra that was randomly selected from the FTIRI spectral datasets of healthy and lesioned cartilage. Leave-one-out cross-validation was performed in the PLS model, and the fitting coefficient between actual and predicted categorical values of the calibration matrix reached 0.95. In the calibration and prediction matrices, the successful identifying percentages of healthy and lesioned cartilage spectra were 100% and 90.24%, respectively. These results demonstrated that FTIRI combined with PLS-DA could provide a promising approach for the categorical identification of healthy and OA cartilage specimens.
© 2015 Society of Photo-Optical Instrumentation Engineers (SPIE)
Xue-Xi Zhang, Xue-Xi Zhang, Jian-Hua Yin, Jian-Hua Yin, Zhi-Hua Mao, Zhi-Hua Mao, Yang Xia, Yang Xia, } "Discrimination of healthy and osteoarthritic articular cartilages by Fourier transform infrared imaging and partial least squares-discriminant analysis," Journal of Biomedical Optics 20(6), 060501 (9 June 2015). https://doi.org/10.1117/1.JBO.20.6.060501 . Submission:
JOURNAL ARTICLE
3 PAGES


SHARE
Back to Top