Precise cancer detection via the combination of functionalized SERS surfaces and convolutional neural network with independent inputs

M. Erzina, A. Trelin, O. Guselnikova, B. Dvorankova, K. Strnadova, A. Perminova, P. Ulbrich, D. Mares, V. Jerabek, R. Elashnikov, V. Svorcik, O. Lyutakov

Research output: Contribution to journalArticle

Abstract

Combining the advanced approaches of surface functionalization and chemistry, plasmonics, surface enhanced Raman spectroscopy (SERS), and machine learning, we propose the advanced route for express and precise recognition of normal and cancer cells. Our interdisciplinary approach uses plasmonic coupling between the specific nanoparticles and underlying periodical plasmonic surface and achieves high SERS enhancement factor. The surface of gold multibranched nanoparticles (AuMs) was functionalized with different chemical groups to achieve partially selective entrapping of biomolecules from cells cultivation media and generate information-rich inputs for machine learning methods and SERS-based cells recognition. Evaluation of convolutional neural networks (CNN) training results, performed with ad hoc feature selection method, suggests that the grafted functional groups provide specificity to proteins, nucleic acids and lipids, responsible for cancer line identification. The dataset of SERS control spectra of normal and cancer cell's metabolites were classified by the trained CNN and perfectly distinguished with 100 % prediction accuracy.

Original languageEnglish
Article number127660
JournalSensors and Actuators, B: Chemical
Volume308
DOIs
Publication statusPublished - 1 Apr 2020

Fingerprint

Raman spectroscopy
cancer
Neural networks
machine learning
Learning systems
Cells
Nanoparticles
Nucleic acids
Biomolecules
nanoparticles
Metabolites
Surface chemistry
metabolites
Gold
Nucleic Acids
Lipids
Functional groups
nucleic acids
Feature extraction
cells

Keywords

  • Cancer detection
  • Convolutional neural network
  • SERS
  • Surface functionalization

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Instrumentation
  • Condensed Matter Physics
  • Surfaces, Coatings and Films
  • Metals and Alloys
  • Electrical and Electronic Engineering
  • Materials Chemistry

Cite this

Precise cancer detection via the combination of functionalized SERS surfaces and convolutional neural network with independent inputs. / Erzina, M.; Trelin, A.; Guselnikova, O.; Dvorankova, B.; Strnadova, K.; Perminova, A.; Ulbrich, P.; Mares, D.; Jerabek, V.; Elashnikov, R.; Svorcik, V.; Lyutakov, O.

In: Sensors and Actuators, B: Chemical, Vol. 308, 127660, 01.04.2020.

Research output: Contribution to journalArticle

Erzina, M. ; Trelin, A. ; Guselnikova, O. ; Dvorankova, B. ; Strnadova, K. ; Perminova, A. ; Ulbrich, P. ; Mares, D. ; Jerabek, V. ; Elashnikov, R. ; Svorcik, V. ; Lyutakov, O. / Precise cancer detection via the combination of functionalized SERS surfaces and convolutional neural network with independent inputs. In: Sensors and Actuators, B: Chemical. 2020 ; Vol. 308.
@article{fba756f977424d77a4c3cdfb48586104,
title = "Precise cancer detection via the combination of functionalized SERS surfaces and convolutional neural network with independent inputs",
abstract = "Combining the advanced approaches of surface functionalization and chemistry, plasmonics, surface enhanced Raman spectroscopy (SERS), and machine learning, we propose the advanced route for express and precise recognition of normal and cancer cells. Our interdisciplinary approach uses plasmonic coupling between the specific nanoparticles and underlying periodical plasmonic surface and achieves high SERS enhancement factor. The surface of gold multibranched nanoparticles (AuMs) was functionalized with different chemical groups to achieve partially selective entrapping of biomolecules from cells cultivation media and generate information-rich inputs for machine learning methods and SERS-based cells recognition. Evaluation of convolutional neural networks (CNN) training results, performed with ad hoc feature selection method, suggests that the grafted functional groups provide specificity to proteins, nucleic acids and lipids, responsible for cancer line identification. The dataset of SERS control spectra of normal and cancer cell's metabolites were classified by the trained CNN and perfectly distinguished with 100 {\%} prediction accuracy.",
keywords = "Cancer detection, Convolutional neural network, SERS, Surface functionalization",
author = "M. Erzina and A. Trelin and O. Guselnikova and B. Dvorankova and K. Strnadova and A. Perminova and P. Ulbrich and D. Mares and V. Jerabek and R. Elashnikov and V. Svorcik and O. Lyutakov",
year = "2020",
month = "4",
day = "1",
doi = "10.1016/j.snb.2020.127660",
language = "English",
volume = "308",
journal = "Sensors and Actuators, B: Chemical",
issn = "0925-4005",
publisher = "Elsevier",

}

TY - JOUR

T1 - Precise cancer detection via the combination of functionalized SERS surfaces and convolutional neural network with independent inputs

AU - Erzina, M.

AU - Trelin, A.

AU - Guselnikova, O.

AU - Dvorankova, B.

AU - Strnadova, K.

AU - Perminova, A.

AU - Ulbrich, P.

AU - Mares, D.

AU - Jerabek, V.

AU - Elashnikov, R.

AU - Svorcik, V.

AU - Lyutakov, O.

PY - 2020/4/1

Y1 - 2020/4/1

N2 - Combining the advanced approaches of surface functionalization and chemistry, plasmonics, surface enhanced Raman spectroscopy (SERS), and machine learning, we propose the advanced route for express and precise recognition of normal and cancer cells. Our interdisciplinary approach uses plasmonic coupling between the specific nanoparticles and underlying periodical plasmonic surface and achieves high SERS enhancement factor. The surface of gold multibranched nanoparticles (AuMs) was functionalized with different chemical groups to achieve partially selective entrapping of biomolecules from cells cultivation media and generate information-rich inputs for machine learning methods and SERS-based cells recognition. Evaluation of convolutional neural networks (CNN) training results, performed with ad hoc feature selection method, suggests that the grafted functional groups provide specificity to proteins, nucleic acids and lipids, responsible for cancer line identification. The dataset of SERS control spectra of normal and cancer cell's metabolites were classified by the trained CNN and perfectly distinguished with 100 % prediction accuracy.

AB - Combining the advanced approaches of surface functionalization and chemistry, plasmonics, surface enhanced Raman spectroscopy (SERS), and machine learning, we propose the advanced route for express and precise recognition of normal and cancer cells. Our interdisciplinary approach uses plasmonic coupling between the specific nanoparticles and underlying periodical plasmonic surface and achieves high SERS enhancement factor. The surface of gold multibranched nanoparticles (AuMs) was functionalized with different chemical groups to achieve partially selective entrapping of biomolecules from cells cultivation media and generate information-rich inputs for machine learning methods and SERS-based cells recognition. Evaluation of convolutional neural networks (CNN) training results, performed with ad hoc feature selection method, suggests that the grafted functional groups provide specificity to proteins, nucleic acids and lipids, responsible for cancer line identification. The dataset of SERS control spectra of normal and cancer cell's metabolites were classified by the trained CNN and perfectly distinguished with 100 % prediction accuracy.

KW - Cancer detection

KW - Convolutional neural network

KW - SERS

KW - Surface functionalization

UR - http://www.scopus.com/inward/record.url?scp=85077692131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077692131&partnerID=8YFLogxK

U2 - 10.1016/j.snb.2020.127660

DO - 10.1016/j.snb.2020.127660

M3 - Article

AN - SCOPUS:85077692131

VL - 308

JO - Sensors and Actuators, B: Chemical

JF - Sensors and Actuators, B: Chemical

SN - 0925-4005

M1 - 127660

ER -