Multivariate Curve Resolution Alternating Least Squares Analysis of In Vivo Skin Raman Spectra

Abstract

In recent years, Raman spectroscopy has been used to study biological tissues. However, the analysis of experimental Raman spectra is still challenging, since the Raman spectra of most biological tissue components overlap significantly and it is difficult to separate individual components. New methods of analysis are needed that would allow for the decomposition of Raman spectra into components and the evaluation of their contribution. The aim of our work is to study the possibilities of the multivariate curve resolution alternating least squares (MCR-ALS) method for the analysis of skin tissues in vivo. We investigated the Raman spectra of human skin recorded using a portable conventional Raman spectroscopy setup. The MCR-ALS analysis was performed for the Raman spectra of normal skin, keratosis, basal cell carcinoma, malignant melanoma, and pigmented nevus. We obtained spectral profiles corresponding to the contribution of the optical system and skin components: melanin, proteins, lipids, water, etc. The obtained results show that the multivariate curve resolution alternating least squares analysis can provide new information on the biochemical profiles of skin tissues. Such information may be used in medical diagnostics to analyze Raman spectra with a low signal-to-noise ratio, as well as in various fields of science and industry for preprocessing Raman spectra to remove parasitic components.

Neural Network-Based Filter Design for Compressive Raman Classification of Cells

“…For the results shown in Figures S3 and S5 , spectra were preprocessed by baseline removal and normalization prior to classification with the support vector machine and neural network model A (see below). A slowly varying baseline was estimated by asymmetric least-squares smoothing, which was introduced by EIlers et al 45 and applied and further developed in the context of Raman spectra by He et al 46 For each spectrum we ran the smoothing algorithm for 10 iterations with parameters reported in the literature 47 (smoothness penalty parameter λ of 10, 6 asymmetry parameter p of 0.1) and subtracted the resulting baseline from the raw spectrum. Baseline-corrected spectra were subsequently normalized by dividing by the sum of all intensities.…”

From Vibrations to Visions: Raman Spectroscopy’s Impact on Skin Cancer Diagnostics

“…When distinguishing between malignant neoplasms and benign neoplasms, the highest ROC AUC obtained was 0.653 (95% CI: 0.602-0.705). The ROC AUC for the discrimination models between MM and pigmented nevus was 0.656 (95% CI: 0.574-0.738) [52]. In another study, 44 biopsy specimens encompassing MM, dysplastic nevi, and compound nevus tumors were examined using Raman spectroscopy imaging in conjunction with the MCR-ALS algorithm.…”

Multispectral Raman Differentiation of Malignant Skin Neoplasms In Vitro: Search for Specific Biomarkers and Optimal Wavelengths

“…We compared the results obtained by the method using the proposed spectral criteria with the results of multivariate curve resolution (MCR) analysis based on a non-negative matrix factorization (NNMF) algorithm [20,[50][51][52][53][54]. Here, we used a MATLAB implementation of the algorithm, which uses an alternating least squares (ALS) method.…”