Discrimination of skin cancer cells using Fourier transform infrared spectroscopy.

2.50
Hdl Handle:
http://hdl.handle.net/11287/620850
Title:
Discrimination of skin cancer cells using Fourier transform infrared spectroscopy.
Authors:
Peñaranda, F.; Naranjo, V.; Lloyd, G. R.; Kastl, L.; Kemper, B.; Schnekenburger, J.; Nallala, J.; Stone, Nick
Abstract:
Fourier transform infrared (FTIR) spectroscopy is a highly versatile tool for cell and tissue analysis. Modern commercial FTIR microspectroscopes allow the acquisition of good-quality hyperspectral images from cytopathological samples within relatively short times. This study aims at assessing the abilities of FTIR spectra to discriminate different types of cultured skin cell lines by different computer analysis technologies. In particular, 22700 single skin cells, belonging to two non-tumoral and two tumoral cell lines, were analysed. These cells were prepared in three different batches that included each cell type. Different spectral preprocessing and classification strategies were considered, including the current standard approaches to reduce Mie scattering artefacts. Special care was taken for the optimisation, training and evaluation of the learning models in order to avoid possible overfitting. Excellent classification performance (balanced accuracy between 0.85 and 0.95) was achieved when the algorithms were trained and tested with the cells from the same batch. When cells from different batches were used for training and testing the balanced accuracy reached values between 0.35 and 0.6, demonstrating the strong influence of sample preparation on the results and comparability of cell FTIR spectra. A deep study of the most optimistic results was performed in order to identify perturbations that influenced the final classification.
Citation:
Discrimination of skin cancer cells using Fourier transform infrared spectroscopy. 2018, 100:50-61 Comput. Biol. Med.
Publisher:
Elsevier
Journal:
Computers in biology and medicine
Issue Date:
1-Sep-2018
URI:
http://hdl.handle.net/11287/620850
DOI:
10.1016/j.compbiomed.2018.06.023
PubMed ID:
29975855
Additional Links:
https://linkinghub.elsevier.com/retrieve/pii/S0010-4825(18)30171-9
Type:
Journal Article
Language:
en
ISSN:
1879-0534
Appears in Collections:
Honorary contracts publications; 2018 RD&E publications

Full metadata record

DC FieldValue Language
dc.contributor.authorPeñaranda, F.en
dc.contributor.authorNaranjo, V.en
dc.contributor.authorLloyd, G. R.en
dc.contributor.authorKastl, L.en
dc.contributor.authorKemper, B.en
dc.contributor.authorSchnekenburger, J.en
dc.contributor.authorNallala, J.en
dc.contributor.authorStone, Nicken
dc.date.accessioned2018-10-04T10:06:03Z-
dc.date.available2018-10-04T10:06:03Z-
dc.date.issued2018-09-01-
dc.identifier.citationDiscrimination of skin cancer cells using Fourier transform infrared spectroscopy. 2018, 100:50-61 Comput. Biol. Med.en
dc.identifier.issn1879-0534-
dc.identifier.pmid29975855-
dc.identifier.doi10.1016/j.compbiomed.2018.06.023-
dc.identifier.urihttp://hdl.handle.net/11287/620850-
dc.description.abstractFourier transform infrared (FTIR) spectroscopy is a highly versatile tool for cell and tissue analysis. Modern commercial FTIR microspectroscopes allow the acquisition of good-quality hyperspectral images from cytopathological samples within relatively short times. This study aims at assessing the abilities of FTIR spectra to discriminate different types of cultured skin cell lines by different computer analysis technologies. In particular, 22700 single skin cells, belonging to two non-tumoral and two tumoral cell lines, were analysed. These cells were prepared in three different batches that included each cell type. Different spectral preprocessing and classification strategies were considered, including the current standard approaches to reduce Mie scattering artefacts. Special care was taken for the optimisation, training and evaluation of the learning models in order to avoid possible overfitting. Excellent classification performance (balanced accuracy between 0.85 and 0.95) was achieved when the algorithms were trained and tested with the cells from the same batch. When cells from different batches were used for training and testing the balanced accuracy reached values between 0.35 and 0.6, demonstrating the strong influence of sample preparation on the results and comparability of cell FTIR spectra. A deep study of the most optimistic results was performed in order to identify perturbations that influenced the final classification.en
dc.language.isoenen
dc.publisherElsevieren
dc.relation.urlhttps://linkinghub.elsevier.com/retrieve/pii/S0010-4825(18)30171-9en
dc.rightsArchived with thanks to Computers in biology and medicineen
dc.subjectWessex Classification Subject Headings::Biochemistryen
dc.titleDiscrimination of skin cancer cells using Fourier transform infrared spectroscopy.en
dc.typeJournal Articleen
dc.identifier.journalComputers in biology and medicineen
dc.type.versionIn press (epub ahead of print)en

Related articles on PubMed

All Items in RD&E Research Repository are protected by copyright, with all rights reserved, unless otherwise indicated.