In Vivo Raman Spectroscopy for Chronic Diseases Detection

Abstract

In this study we performed in vivo diagnosis of skin cancer and kidney failure based on the estimation of biochemical changes in skin tissues employing a portable spectroscopy setup combining analysis of Raman and autofluorescence spectra in the near infrared region [1]. We studied 617 cases of skin cancer (70 melanomas, 122 basal cell carcinomas, 12 squamous cell carcinomas and 413 benign tumors) and 90 adult patients with kidney failure (90 spectra) and 40 healthy adult volunteers (80 spectra) in vivo with a portable setup. The studies considered the patients examined by GPs in local clinics and directed to specialized clinics with suspected skin cancer and kidney failure patients that undergo hemodialysis. The spectra were classified with a projection on latent structures and discriminant analysis (PLS-DA) [2]. To check the classification models stability, a 10-fold cross-validation was performed. We obtained ROC AUCs of 0.75 (0.71 – 0.79; 95% CI), 0.69 (0.63-0.76; 95% CI), and 0.81 (0.74 – 0.87; 95% CI) for classification of a) malignant and benign tumors, b) melanomas and pigmented tumors and c) melanomas and seborrheic keratosis respectively. The positive and negative predictive values ranged from 20% to 52% and from 73% to 99% respectively. The biopsy ratio varied from 0.92:1 to 4.08:1 (at sensitivity levels from 90% to 99%). Application of Raman spectroscopy to investigate the forearm skin in patients with kidney failure and healthy adult volunteers has yielded the accuracy of 0.96, sensitivity of 0.94 and specificity of 0.99 in terms of identifying the target subjects with kidney failure. The autofluorescence analysis in the near infrared region identified patients with kidney failure among healthy volunteers of the same age group with specificity, sensitivity, and accuracy of 0.91, 0.84, and 0.88, respectively. The most informative Raman spectral bands when classifying subjects by the presence of kidney failure using the PLS-DA method are 1315-1330 cm-1, 1450-1460 cm-1, 1700-1800 cm-1. Figure 1 demonstrates variable importance in the projection (VIP) for discrimination of kidney failure. VIP makes it possible to assess the impact of individual variables of the predicate matrix array on the model [3].
In general, the performed study demonstrates that for in vivo skin analysis, the conventional Raman spectroscopy can provide the basis for cost-effective and accurate detection of kidney failure and associated metabolic changes in the skin. The accuracy of automatic analysis with the proposed portable system is higher than the accuracy of GPs and trainees, and is comparable to the accuracy of trained dermatologists. The proposed approach may be combined with other optical techniques of skin lesion analysis, such as dermoscopy- and spectroscopy-based computer-assisted diagnosis systems to increase accuracy of neoplasms classification.
[1] Y.A. Khristoforova, I.A. Bratchenko, O.O. Myakinin, et al. Portable spectroscopic system for in vivo skin neoplasms diagnostics by Raman and autofluorescence analysis. J Biophotonics. 12. e201800400, 2019.
[2] D.M. Haaland, E.V. Thomas: Partial least-squares methods for spectral analyses. 1. Relation to other quantitative calibration methods and the extraction of qualitative information. Anal Chem. 60. 1193–1202, 1988.
[3] I.G. Chong, C.H. Jun. Performance of some variable selection methods when multicollinearity is present. Chemometr Intell Lab Syst. 78. 103–112, 2005.

Speaker

Ivan Bratchenko
Samara University
Россия

Discussion

Ask question