© 2022 All Rights Reserved

Raman spectroscopy and autofluorescence analysis with patient’s demographics for skin cancer detection

Yulia A. Khristoforova1, Ivan A. Bratchenko1, Lyudmila A. Bratchenko1, Alexander A. Moryatov2, Sergey V. Kozlov2, Valery P. Zakharov1,
1 Samara University, Samara, Russia
2 Samara State Medical University, Samara, Russia


In vivo study of skin cancer was performed in Samara Clinical Oncology Center using optical biopsy method. Today, optical biopsy is one of the promising methods to detect tumors based on their spectral features caused by the contribution of the different chemical components. Over the past years, a number of methods have been proposed that are capable to increase the efficiency of skin cancer diagnosis, especially melanoma, among which Raman spectroscopy is one of the successfully developing method. The Raman spectroscopy is based on the change in the photon’s frequency after interaction with the molecules of the studied sample, allows one to determine the presence of chemical compounds and their change as a result of various processes in the sample, in particular, during the malignancy of biological tissue. Therefore, optical biopsy in this study was based on combined application of the Raman spectroscopy and near-infrared region autofluorescence with regression analysis. The projection of the latent structure with linear discriminant analysis was used to classify the different skin tumors. The risk for developing skin cancer depends on demographic factors, therefore, each analyzed tumor in regression models was specified using spectral features in combination with demographic features (gender, age, localization, size, family history, harmfulness by profession). Incorporating of the patient’s demographics with spectral data allows us to improve quality indicators of the regression model by the 3-7%.

File with abstract


Yulia Khristoforova
Samara National Research University
Russian Federation


File with report


Ask question