Abstract
This study aimed to extract the paraffin component from paraffin-embedded oral cancer tissue spectra using three multivariate analysis (MVA) methods; Independent Component Analysis (ICA), Partial Least Squares (PLS) and Independent Component - Partial Least Square (IC-PLS). The estimated paraffin components were used for removing the contribution of paraffin from the tissue spectra. These three methods were compared in terms of the efficiency of paraffin removal and the ability to retain the tissue information. It was found that ICA, PLS and IC-PLS could remove the paraffin component from the spectra at almost the same level while Principal Component Analysis (PCA) was incapable. In terms of retaining cancer tissue spectral integrity, effects of PLS and IC-PLS on the non-paraffin region were significantly less than that of ICA where cancer tissue spectral areas were deteriorated. The paraffin-removed spectra were used for constructing Raman images of oral cancer tissue and compared with Hematoxylin and Eosin (H&E) stained tissues for verification. This study has demonstrated the capability of Raman spectroscopy together with multivariate analysis methods as a diagnostic tool for the paraffin-embedded tissue section.
Highlights
This study aimed to extract the paraffin component from paraffin-embedded oral cancer tissue spectra using three multivariate analysis (MVA) methods; Independent Component Analysis (ICA), Partial Least Squares (PLS) and Independent Component - Partial Least Square (IC-PLS)
We found that the Principal Component Analysis (PCA) was unable to extract the paraffin component due to its distribution
PLS with Non-Linear Iterative Partial Least Squares (NIPALS) algorithm was used for determining the paraffin corresponding variables and the regression coefficients obtained were used as a paraffin estimator
Summary
This study aimed to extract the paraffin component from paraffin-embedded oral cancer tissue spectra using three multivariate analysis (MVA) methods; Independent Component Analysis (ICA), Partial Least Squares (PLS) and Independent Component - Partial Least Square (IC-PLS). In the studies of embryonic chick cornea and prostrate gland using Raman spectroscopy, the paraffin regions were removed prior to the multivariate analysis to prevent the results from the contribution of paraffin[11,12]. Raman spectra of a paraffin-embedded skin tissue were investigated by Gobinet et al and Vrabie et al.[13,14] They reported the possibility of ICA to provide the estimator of the paraffin while PCA was unable to do due to the non-Gaussianity of paraffin. The present study investigates the performance of ICA, PLS and IC-PLS for the paraffin estimation and develops Raman images of oral cancer tissues. IC-PLS is implemented and developed for higher performance for paraffin estimation These methods are compared in terms of the paraffin removal capability and the effect on non-paraffin region for proteins, collagen, keratin. The Raman images and a H&E stained tissue are compared to verify the correctness of the removal of paraffin component
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
