Comparative study on identification of healthy and osteoarthritic articular cartilages by fourier transform infrared imaging and chemometrics methods

Abstract

Two discriminant methods, partial least squares-discriminant analysis (PLS-DA) and Fisher's discriminant analysis (FDA), were combined with Fourier transform infrared imaging (FTIRI) to di®erentiate healthy and osteoarthritic articular cartilage in a canine model. Osteoarthritic cartilage had been developed for up to two years after the anterior cruciate ligament (ACL) transection in one knee. Cartilage specimens were sectioned into 10 m thickness for FTIRI. A PLS-DA model was developed after spectral pre-processing. All IR spectra extracted from FTIR images were calculated by PLS-DA with the discriminant accuracy of 90%. Prior to FDA, principal component analysis (PCA) was performed to decompose the IR spectral matrix into informative principal component matrices. Based on the di®erent discriminant mechanism, the discriminant accuracy (96%) of PCA-FDA with high convenience was higher than that of PLS-DA. No healthy cartilage sample was mis-assigned by these two methods. The above mentioned suggested that both integrated technologies of FTIRI-PLS-DA and, especially, FTIRI-PCA-FDA could become a promising tool for the discrimination of healthy and osteoarthritic cartilage specimen as well as the diagnosis of cartilage lesion at microscopic level. The results of the study would be helpful for better understanding the pathology of osteoarthritics.

Spatial analysis of the osteoarthritis microenvironment: techniques, insights, and applications

“…Mao et al further compared the results using FTIR imaging with PLS-DA and FTIR imaging with PCA–FDA in the normal and ACLT cartilage of dogs to validate which discriminant method was better and found that FDA methods were superior for a better understanding of OA pathophysiology. 46 Using the combination of K-means clustering and PLSR, Oinas et al also found that the collagen integrity and carbohydrates were closely related to disease classification. 43 They further used the PLSR model to predict the OARSI grade and achieved high accuracy from cartilage superficial (94%) and deep zone (77%) structures.…”

Vibrational Spectroscopy in Assessment of Early Osteoarthritis—A Narrative Review

“…In the calibration and prediction matrix, the recognition rates of healthy cartilage and injured cartilage were 100% and 90.24%, respectively. Mao et al [ 88 ] predicted that both FTIRI–PLS–DA and FTIRI–PCA–FDA integration technologies would become tools for the microscopic identification of healthy cartilage and OA cartilage specimens and the diagnosis of cartilage lesions. Oinas et al [ 78 ] used cluster analysis to investigate human articular cartilage samples with different histological levels of OA.…”

Fourier Transform Infrared Microspectroscopy Combined with Principal Component Analysis and Artificial Neural Networks for the Study of the Effect of β-Hydroxy-β-Methylbutyrate (HMB) Supplementation on Articular Cartilage

“…So far, FTIR spectroscopy and its combination with microscopic visualization of the AC tissue have been successfully applied both to evaluate the relative changes in its composition and the spatial distribution of main AC components [23][24][25][26]. The development of FTIR spectroscopy in the AC research to provide a new strategy for rapid diagnosis of degenerative disease was reported elsewhere [27][28][29][30] and demonstrated by the changes in the spatial distribution of various components of AC mapped by FTIR microspectroscopy [31]. Using advanced multivariate data analysis methods, FTIR microspectroscopy can reveal hidden structures within spectral data concerning the tissue composition and structure, thereby helping improve medical diagnostics of cartilage diseases or monitor therapeutic progress [31].…”