Discrimination of Basal Cell Carcinoma and Melanoma from Normal Skin Biopsies in Vitro Through Raman Spectroscopy and Principal Component Analysis

Abstract

Objective: Raman spectroscopy has been employed to discriminate between malignant (basal cell carcinoma [BCC] and melanoma [MEL]) and normal (N) skin tissues in vitro, aimed at developing a method for cancer diagnosis. Background data: Raman spectroscopy is an analytical tool that could be used to diagnose skin cancer rapidly and noninvasively. Methods: Skin biopsy fragments of *2 mm 2 from excisional surgeries were scanned through a Raman spectrometer (830 nm excitation wavelength, 50 to 200 mW of power, and 20 sec exposure time) coupled to a fiber optic Raman probe. Principal component analysis (PCA) and Euclidean distance were employed to develop a discrimination model to classify samples according to histopathology. In this model, we used a set of 145 spectra from N (30 spectra), BCC (96 spectra), and MEL (19 spectra) skin tissues. Results: We demonstrated that principal components (PCs) 1 to 4 accounted for 95.4% of all spectral variation. These PCs have been spectrally correlated to the biochemicals present in tissues, such as proteins, lipids, and melanin. The scores of PC2 and PC3 revealed statistically significant differences among N, BCC, and MEL (ANOVA, p < 0.05) and were used in the discrimination model. A total of 28 out of 30 spectra were correctly diagnosed as N, 93 out of 96 as BCC, and 13 out of 19 as MEL, with an overall accuracy of 92.4%. Conclusions: This discrimination model based on PCA and Euclidean distance could differentiate N from malignant (BCC and MEL) with high sensitivity and specificity.

The Clinical Application of Raman Spectroscopy for Breast Cancer Detection

“…Many spectral unmixing algorithms are applied currently, including principal component analysis (PCA), vertex component analysis (VCA), hierarchical cluster analysis (HCA), support vector machine (SVM), and SVM-recursive feature elimination (SVM-RFE) [7]. PCA is more commonly used for quantitative analysis in detecting cancers such as melanoma, breast cancer, and cervical cancer [8][9][10]. As for HCA, it is used for cancer diagnosis such as esophageal cancer [11] and some cancer cells [12][13][14].…”

Effect of Low-Level Laser Therapy in an Experimental Model of Osteoarthritis in Rats Evaluated Through Raman Spectroscopy

“…PCA has been used as a tool to discriminate differences in the spectra of several biological materials, such as skin cells, bacteria, and body fluids. 29,42 In addition to the reduction in the number of variables, decomposition through PCA has also the ability to detect differences in the spectra caused by changes in the chemical constitution, using a suitable discrimination technique. 29 Results of the present study have pointed out that PC1 vector reveals especially the mineral content from subchondral bone and general features of protein from bone and cartilage, whereas PC2 and PC3 vectors indicate the organic content, mainly collagens II and III, respectively.…”

“…27 In addition, PCA has been used to characterize biological tissues with the aims of identification of biochemical composition and diagnosis. 28,29 The aim of this study was to investigate the biochemical and biomolecular changes associated with LLLT on a wellestablished experimental model of OA (collagenase of the knee) in rats, in an attempt to elucidate the effects of LLLT on damaged cartilage using the spectral information provided by Raman spectroscopy, as this protocol had not been used before. With the characterization of the Raman features on the damaged cartilage after laser treatment by PCA, the framework for the analysis of cartilaginous tissue could be improved.…”

Biological and Medical Applications of Multivariate Curve Resolution Assisted Raman Spectroscopy

“…Though it is helpful for deducing the number of different sources of variation present in the data set and partially decomposes molecular information, the results are only abstract solutions with no physical meaning. [21][22][23][24] Cluster analysis, another widely used spectral decomposition method, partitions a dataset into a pre-determined number of subgroups of similar spectra by statistically analyzing the variations. It has been successfully applied to identify intracellular structures and discriminate tissue environments.…”