Repository logo
 
Publication

Diffuse reflectance and machine learning techniques to differentiate colorectal cancer ex vivo

2021Journal article Open access
Simple item page
dc.contributor.authorFernandes, Luís
dc.contributor.authorCarvalho, Sónia
dc.contributor.authorCarneiro, Isa
dc.contributor.authorHenrique, Rui
dc.contributor.authorTuchin, Valery V.
dc.contributor.authorOliveira, Hélder P.
dc.contributor.authorOliveira, Luís
dc.date.accessioned2022-02-11T10:59:37Z
dc.date.available2022-02-11T10:59:37Z
dc.date.issued2021
dc.description.abstractIn this study, we used machine learning techniques to reconstruct the wavelength dependence of the absorption coefficient of human normal and pathological colorectal mucosa tissues. Using only diffuse reflectance spectra from the ex vivo mucosa tissues as input to algorithms, several approaches were tried before obtaining good matching between the generated absorption coefficients and the ones previously calculated for the mucosa tissues from invasive experimental spectral measurements. Considering the optimized match for the results generated with the multilayer perceptron regression method, we were able to identify differentiated accumulation of lipofuscin in the absorption coefficient spectra of both mucosa tissues as we have done before with the corresponding results calculated directly from invasive measurements. Considering the random forest regressor algorithm, the estimated absorption coefficient spectra almost matched the ones previously calculated. By subtracting the absorption of lipofuscin from these spectra, we obtained similar hemoglobin ratios at 410/550 nm: 18.9-fold/9.3-fold for the healthy mucosa and 46.6-fold/24.2-fold for the pathological mucosa, while from direct calculations, those ratios were 19.7-fold/10.1-fold for the healthy mucosa and 33.1-fold/17.3-fold for the pathological mucosa. The higher values obtained in this study indicate a higher blood content in the pathological samples used to measure the diffuse reflectance spectra. In light of such accuracy and sensibility to the presence of hidden absorbers, with a different accumulation between healthy and pathological tissues, good perspectives become available to develop minimally invasive spectroscopy methods for in vivo early detection and monitoring of colorectal cancer.The application of machine learning methods to noninvasivelike diffuse reflectance spectra allowed us to reconstruct the absorption coefficient spectra of human healthy and pathological mucosa tissues from the colorectal wall. Consequently, we were able to obtain differentiated blood and pigment content in both tissues, which can be used for the development of new noninvasive diagnostic methods for colorectal cancer.pt_PT
dc.description.sponsorshipThe work of L. M. Oliveira was supported by the Portuguese Science Foundation (Grant No. FCT-UIDB/04730/2020). The work of V. V. Tuchin was supported by a grant of the Government of the Russian Federation (Registration No. 2020-220-08-2389).pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationFernandes, L., Carvalho, S., Carneiro, I., Henrique, R., Tuchin, V.V., Oliveira, H.P., Oliveira, L.M. Diffuse reflectance and machine learning techniques to differentiate colorectal cancer ex vivo. Chaos, vol. 31, 053118.pt_PT
dc.identifier.doi10.1063/5.0052088pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.22/19917
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherAIP Publishingpt_PT
dc.relationFCT-UIDB/04730/2020pt_PT
dc.relation2020-220-08-2389pt_PT
dc.relation.publisherversionhttps://aip.scitation.org/doi/10.1063/5.0052088pt_PT
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/pt_PT
dc.subjectDiseases and conditionspt_PT
dc.subjectBloodpt_PT
dc.subjectArtificial neural networkspt_PT
dc.subjectOptical propertiespt_PT
dc.subjectMachine learningpt_PT
dc.subjectPathologypt_PT
dc.subjectOptical absorptionpt_PT
dc.subjectSpectroscopypt_PT
dc.titleDiffuse reflectance and machine learning techniques to differentiate colorectal cancer ex vivopt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.issue5pt_PT
oaire.citation.startPage053118pt_PT
oaire.citation.titleChaos: An Interdisciplinary Journal of Nonlinear Sciencept_PT
oaire.citation.volume31pt_PT
person.familyNameEmanuel Pereira Pinto Fernandes
person.familyNameOliveira
person.givenNameLuís
person.givenNameLuís
person.identifier414820
person.identifier.ciencia-id5A17-BE21-CF8C
person.identifier.ciencia-idC312-F342-BD23
person.identifier.orcid0000-0001-8306-3362
person.identifier.orcid0000-0003-0667-3428
person.identifier.ridB-7198-2017
person.identifier.scopus-author-id55853723900
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT
relation.isAuthorOfPublicationc2a74f78-fbc6-4449-bf63-a5cfc963eac9
relation.isAuthorOfPublication4e2de4d7-142a-400f-8dbf-cd0ff9551093
relation.isAuthorOfPublication.latestForDiscoveryc2a74f78-fbc6-4449-bf63-a5cfc963eac9

Files

Original bundle
Now showing 1 - 2 of 2
No Thumbnail Available
Name:
ART_CIETI_LuisFernandes-Chaos_2021.pdf
Size:
3.57 MB
Format:
Adobe Portable Document Format
Download
No Thumbnail Available
Name:
license.txt
Size:
1.74 KB
Format:
Item-specific license agreed upon to submission
Download

Collections

ISEP – CIETI – Artigos