Discrimination of different cancer types clustering Raman spectra by a super paramagnetic stochastic network approach

González-Solís Jl

PLOS ONE, 2019, vol. 14, issue 3, 1-15

Abstract: Based in high sensitivity and specificity reported recently in detection of the cancer, the technique of Raman spectroscopy is proposed to discriminate between breast cancer, leukemia and cervical cancer using blood serum samples from patients officially diagnosed. In order to classify Raman spectra, clustering method known as Super Paramagnetic Clustering based on statistical physics concepts with a stochastic approach was implemented. Comparing firstly average Raman spectra of the three cancers, some peaks that allowed differentiating one cancer from other were identified, however, other peaks allowed concluding that there are biochemical similarities among them. According to these spectra, the band associated with amide I (1654 cm−1) and one of two shoulders assigned to amide III (1230-1282 cm−1) allowed discriminating leukemia from breast and cervical cancer, whereas band 714 cm−1 (polysaccharides) achieves to differentiate cervical cancer from leukemia and breast cancer, and bulged region, 1040 − 1100 cm−1 (phenylalanine, phospholipid) discriminated breast cancer from leukemia and cervical cancer. Subsequently, Super Paramagnetic Clustering method was applied to Raman spectra to study similarity relationships between cancers based on the biochemical composition of serum samples. Finally, as a cross check method, the standard method to classify Raman spectra of breast cancer, leukemia and cervical cancer, known as principal components analysis, was used showing excellent agreement with results of Super Paramagnetic Clustering method. Preliminary results demonstrated that Raman spectroscopy and Super Paramagnetic Clustering method can be used to discriminate between breast cancer, leukemia and cervical cancer samples using blood serum samples.

Date: 2019
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0213621 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 13621&type=printable (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:plo:pone00:0213621

DOI: 10.1371/journal.pone.0213621

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().