Open AccessDiscrimination of healthy and osteoarthritic articular cartilage by Fourier transform infrared imaging and Fisher’s discriminant analysis
Author(s) -
Zhihua Mao,
Jianhua Yin,
Xuexi Zhang,
Xiao Wang,
Yang Xia
Publication year - 2016
Publication title -
biomedical optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.362
H-Index - 86
ISSN - 2156-7085
DOI - 10.1364/boe.7.000448
Subject(s) - principal component analysis , chemometrics , linear discriminant analysis , articular cartilage , cartilage , fourier transform , fourier transform infrared spectroscopy , osteoarthritis , biomedical engineering , pattern recognition (psychology) , artificial intelligence , materials science , mathematics , medicine , chemistry , pathology , computer science , anatomy , chromatography , optics , physics , mathematical analysis , alternative medicine
Fourier transform infrared spectroscopic imaging (FTIRI) technique can be used to obtain the quantitative information of content and spatial distribution of principal components in cartilage by combining with chemometrics methods. In this study, FTIRI combining with principal component analysis (PCA) and Fisher's discriminant analysis (FDA) was applied to identify the healthy and osteoarthritic (OA) articular cartilage samples. Ten 10-μm thick sections of canine cartilages were imaged at 6.25μm/pixel in FTIRI. The infrared spectra extracted from the FTIR images were imported into SPSS software for PCA and FDA. Based on the PCA result of 2 principal components, the healthy and OA cartilage samples were effectively discriminated by the FDA with high accuracy of 94% for the initial samples (training set) and cross validation, as well as 86.67% for the prediction group. The study showed that cartilage degeneration became gradually weak with the increase of the depth. FTIRI combined with chemometrics may become an effective method for distinguishing healthy and OA cartilages in future.