SARATOV FALL MEETING SFM 

© 2024 All Rights Reserved

Analysis of mouse blood serum in the dynamics of U87 glioblastoma by Terahertz spectroscopy and Machine learning

Denis Vrazhnov,1,2, Anastasia Knyazkova,1,2, Maria Konnikova,3,4, Yury Kistenev,1,2, Alexander Shkurinov,3,4, Olga Cherkasova,4,5,6 1 Laboratory of Biophotonics, Tomsk State University, Tomsk, Russia 2 V.E. Zuev Institute of Atmospheric Optics SB RAS, Tomsk, Russia 3 Faculty of Physics, Lomonosov Moscow State University, Moscow, Russia 4 Institute on Laser and Information Technologies, Branch of the Federal Scientific Research Centre “Crystallography and Photonics” of RAS, Shatura, Russia 5 Institute of Laser Physics, Siberian Branch of the RAS, Novosibirsk, Russia

Abstract

Glioblastoma is one of the most rapidly progressing oncological diseases with the most unfavorable survival prognosis because of a late diagnostic. Early and noninvasive diagnosis of oncological diseases can be achieved by body fluids analysis via terahertz time-domain spectroscopy. In this work we use THz-TDS to study the blood serum of mice in the dynamics of the development of experimental U87 glioblastoma. The THz absorption spectra of blood serum do not have any specific spectral features. To identify differences between the control and experimental groups and estimate informative THz frequencies, we proposed machine learning (ML) pipeline, which includes Savitzky-Golay filter for smoothing, isolation forest for outlier removal, principal component analysis together with linear kernel support vector machine for informative feature selection and data separability investigation. ML models were verified by k-fold cross validation. Additional study included regression analysis of THz spectra and tumor size by the LASSO method. Specific THz frequencies were determined to be prominent for the glioma development.
The study was carried out with the support of the Russian Foundation for Basic Research (RFBR) grant (No. 19–52-55004). This work was supported by the Ministry of Science and Higher Education of the Russian Federation within the State assignment FSRC "Crystallography and Photonics" RAS, within the State assignment of ILP SB RAS (project # 0307-2019-0007), grant under the Decree of the Government of the Russian Federation No. 220 of April 09 2010 (Agreement No. 075-15-2021-615 of June 04 2021), This work has been supported by the Interdisciplinary Scientific and Educational School of Moscow University «Photonic and Quantum Technologies. Digital Medicine» and the Tomsk State University Development Program (Priority-2030).


File with abstract

Speaker

Denis Vrazhnov
Tomsk State University
Russia

Discussion

Ask question