Machine learning utilising spectral derivative data improves cellular health classification through hyperspectral infra-red spectroscopy.
Journal
PloS one
ISSN: 1932-6203
Titre abrégé: PLoS One
Pays: United States
ID NLM: 101285081
Informations de publication
Date de publication:
2020
2020
Historique:
received:
23
03
2020
accepted:
20
08
2020
entrez:
15
9
2020
pubmed:
16
9
2020
medline:
28
10
2020
Statut:
epublish
Résumé
The objective differentiation of facets of cellular metabolism is important for several clinical applications, including accurate definition of tumour boundaries and targeted wound debridement. To this end, spectral biomarkers to differentiate live and necrotic/apoptotic cells have been defined using in vitro methods. The delineation of different cellular states using spectroscopic methods is difficult due to the complex nature of these biological processes. Sophisticated, objective classification methods will therefore be important for such differentiation. In this study, spectral data from healthy/traumatised cell samples using hyperspectral imaging between 2500-3500 nm were collected using a portable prototype device. Machine learning algorithms, in the form of clustering, have been performed on a variety of pre-processing data types including 'raw' unprocessed, smoothed resampling, background subtracted and spectral derivative. The resulting clusters were utilised as a diagnostic tool for the assessment of cellular health and quantified using both sensitivity and specificity to compare the different analysis methods. The raw data exhibited differences for one of the three different trauma types applied, although unable to accurately cluster all the traumatised samples due to signal contamination from the chemical insult. The background subtracted and smoothed data sets reduced the accuracy further, due to the apparent removal of key spectral features which exhibit cellular health. However, the spectral derivative data-types significantly improved the accuracy of clustering compared to other data types, with both sensitivity and specificity for the background subtracted data set being >94% highlighting its utility to account for unknown signal contamination while maintaining important cellular spectral features.
Identifiants
pubmed: 32931514
doi: 10.1371/journal.pone.0238647
pii: PONE-D-20-08309
pmc: PMC7491715
doi:
Substances chimiques
Contrast Media
0
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
e0238647Déclaration de conflit d'intérêts
The authors have declared that no competing interests exist.
Références
Biomed Opt Express. 2018 Aug 09;9(9):4163-4174
pubmed: 30615705
Circulation. 2015 Nov 17;132(20):1920-30
pubmed: 26572668
Jpn J Pharmacol. 1999 Jan;79(1):33-40
pubmed: 10082315
Methods Cell Biol. 2008;89:275-308
pubmed: 19118679
Anal Chem. 2018 Feb 6;90(3):1444-1463
pubmed: 29281255
Burns. 2008 Sep;34(6):761-9
pubmed: 18511202
J Biomed Opt. 2013 Jun;18(6):061204
pubmed: 23111601
J Biophotonics. 2012 Mar;5(3):255-62
pubmed: 22232073
PLoS One. 2017 Dec 7;12(12):e0186425
pubmed: 29216188
FEBS Lett. 1994 Oct 17;353(2):129-32
pubmed: 7926036
Lab Chip. 2016 Apr 26;16(9):1644-1651
pubmed: 27040369
Biophys J. 2009 Oct 7;97(7):2107-14
pubmed: 19804743
Annu Int Conf IEEE Eng Med Biol Soc. 2013;2013:4442-5
pubmed: 24110719
J Biomed Opt. 2019 Jul;24(7):1-9
pubmed: 31313538
Curr Med Imaging. 2021;17(9):1059-1077
pubmed: 33504314
J Biomed Opt. 2015 Mar;20(3):030901
pubmed: 25803186
Philos Trans A Math Phys Eng Sci. 2016 Apr 13;374(2065):20150202
pubmed: 26953178
IEEE Trans Biomed Eng. 2007 Feb;54(2):303-12
pubmed: 17278587
Nurs Stand. 2016 Mar 2;30(27):40-7
pubmed: 26932649
Phys Med Biol. 2010 Jun 21;55(12):3381-99
pubmed: 20505221
Science. 2006 Jul 28;313(5786):504-7
pubmed: 16873662
Analyst. 2012 Jan 21;137(2):322-32
pubmed: 22114757
Methods Mol Biol. 2017;1618:95-123
pubmed: 28523503