Classifying Raman Spectra of Extracellular Vesicles based on Convolutional Neural Networks for Prostate Cancer Detection

Research output: Contribution to journalArticleAcademicpeer-review

1 Downloads (Pure)

Abstract

Since early 2000s, machine learning algorithms have been widely used in many research and industrial fields, most prominently in computer vison. Lately, many fields of study have tried to use these automated methods, and there are several reports from the field of spectroscopy. In this study, we demonstrate a classification model based on machine learning to classify Raman spectra. We obtained Raman spectra from extracellular vesicles (EVs) to find tumor derived EVs. The convolutional neural network (CNN) was trained on preprocessed Raman data and raw Raman data. We compare the result from CNN with results from principal component analysis that is widely used among in spectroscopy. The new model classifies EVs with an accuracy of >90%. Moreover, the new model based on CNN is also suitable for classifying the raw Raman data directly without preprocessing with a minimum accuracy of 93%.
Original languageEnglish
JournalJournal of raman spectroscopy
DOIs
Publication statusE-pub ahead of print/First online - 7 Nov 2019

Fingerprint

Raman scattering
Neural networks
Learning systems
Spectroscopy
Principal component analysis
Learning algorithms
Tumors

Keywords

  • UT-Hybrid-D
  • Convolutional Neural Network
  • Extracellular vesicles
  • Machine Learning
  • Raman Spectroscopy
  • Cancer Biomarker
  • Cancer biomarker
  • extracellular vesicles
  • convolutional neural network
  • Raman spectroscopy
  • machine learning

Cite this

@article{c32ed004a0314b6c9bc905e2e1843641,
title = "Classifying Raman Spectra of Extracellular Vesicles based on Convolutional Neural Networks for Prostate Cancer Detection",
abstract = "Since early 2000s, machine learning algorithms have been widely used in many research and industrial fields, most prominently in computer vison. Lately, many fields of study have tried to use these automated methods, and there are several reports from the field of spectroscopy. In this study, we demonstrate a classification model based on machine learning to classify Raman spectra. We obtained Raman spectra from extracellular vesicles (EVs) to find tumor derived EVs. The convolutional neural network (CNN) was trained on preprocessed Raman data and raw Raman data. We compare the result from CNN with results from principal component analysis that is widely used among in spectroscopy. The new model classifies EVs with an accuracy of >90{\%}. Moreover, the new model based on CNN is also suitable for classifying the raw Raman data directly without preprocessing with a minimum accuracy of 93{\%}.",
keywords = "UT-Hybrid-D, Convolutional Neural Network, Extracellular vesicles, Machine Learning, Raman Spectroscopy, Cancer Biomarker, Cancer biomarker, extracellular vesicles, convolutional neural network, Raman spectroscopy, machine learning",
author = "Wooje Lee and Lenferink, {Aufried T.M.} and Cornelis Otto and H.L. Offerhaus",
note = "Wiley deal",
year = "2019",
month = "11",
day = "7",
doi = "10.1002/jrs.5770",
language = "English",
journal = "Journal of raman spectroscopy",
issn = "0377-0486",
publisher = "Wiley",

}

TY - JOUR

T1 - Classifying Raman Spectra of Extracellular Vesicles based on Convolutional Neural Networks for Prostate Cancer Detection

AU - Lee, Wooje

AU - Lenferink, Aufried T.M.

AU - Otto, Cornelis

AU - Offerhaus, H.L.

N1 - Wiley deal

PY - 2019/11/7

Y1 - 2019/11/7

N2 - Since early 2000s, machine learning algorithms have been widely used in many research and industrial fields, most prominently in computer vison. Lately, many fields of study have tried to use these automated methods, and there are several reports from the field of spectroscopy. In this study, we demonstrate a classification model based on machine learning to classify Raman spectra. We obtained Raman spectra from extracellular vesicles (EVs) to find tumor derived EVs. The convolutional neural network (CNN) was trained on preprocessed Raman data and raw Raman data. We compare the result from CNN with results from principal component analysis that is widely used among in spectroscopy. The new model classifies EVs with an accuracy of >90%. Moreover, the new model based on CNN is also suitable for classifying the raw Raman data directly without preprocessing with a minimum accuracy of 93%.

AB - Since early 2000s, machine learning algorithms have been widely used in many research and industrial fields, most prominently in computer vison. Lately, many fields of study have tried to use these automated methods, and there are several reports from the field of spectroscopy. In this study, we demonstrate a classification model based on machine learning to classify Raman spectra. We obtained Raman spectra from extracellular vesicles (EVs) to find tumor derived EVs. The convolutional neural network (CNN) was trained on preprocessed Raman data and raw Raman data. We compare the result from CNN with results from principal component analysis that is widely used among in spectroscopy. The new model classifies EVs with an accuracy of >90%. Moreover, the new model based on CNN is also suitable for classifying the raw Raman data directly without preprocessing with a minimum accuracy of 93%.

KW - UT-Hybrid-D

KW - Convolutional Neural Network

KW - Extracellular vesicles

KW - Machine Learning

KW - Raman Spectroscopy

KW - Cancer Biomarker

KW - Cancer biomarker

KW - extracellular vesicles

KW - convolutional neural network

KW - Raman spectroscopy

KW - machine learning

UR - http://www.scopus.com/inward/record.url?scp=85074925137&partnerID=8YFLogxK

U2 - 10.1002/jrs.5770

DO - 10.1002/jrs.5770

M3 - Article

JO - Journal of raman spectroscopy

JF - Journal of raman spectroscopy

SN - 0377-0486

ER -