LDA vs QDA for FT-MIR prostate cancer tissue classification
Autor(a) principal: | |
---|---|
Data de Publicação: | 2017 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UFRN |
Texto Completo: | https://repositorio.ufrn.br/handle/123456789/49621 https://doi.org/10.1016/j.chemolab.2017.01.021 |
Resumo: | Discrimination/classification of biological material a ta molecular level is one of the key aims of chemometrics applied to biospectroscopic data. Two discriminant functions, namely Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), were considered in this study for prostate cancer classification based on FT-MIR data, and illustrated graphically as boundary methods. Principal Component Analysis (PCA) was applied as a variable/dimensionality reduction method and Genetic Algorithm (GA) as variable selection method, followed by LDA and QDA. The performance of each method was determined using 40–100 MIR spectra per tissue sample (n=45), previously classified according to Gleason traditional grading by pathologists. The methods were used to separate the two-category of prostate cancer: Low grade (Gleason grade 2) vs. High grade (Gleason grade 3 and 4). The models were optimized using a training set and their performance was evaluated using a test set. Classification rates and quality metrics (Sensitivity, Specificity, Positive (or Precision) and Negative Predictive Values, Youden's index, and Positive and Negative Likelihood Ratios) were computed for each model. QDA-based models obtained higher classification rates and quality performance than LDA-based models. The models studied identify that secondary protein structure variations and DNA/RNA alterations are the main biomolecular ‘difference markers’ for prostate cancer grades. |
id |
UFRN_2c08bc7ccad190cf57e1f8ef5b50e6dd |
---|---|
oai_identifier_str |
oai:https://repositorio.ufrn.br:123456789/49621 |
network_acronym_str |
UFRN |
network_name_str |
Repositório Institucional da UFRN |
repository_id_str |
|
spelling |
Araújo, Aurigena Antunes deSiqueira, Laurinda F.S.Araújo Júnior, Raimundo F.Morais, Camilo L.M.Lima, Kássio M.G.2022-10-24T21:42:59Z2022-10-24T21:42:59Z2017-03-15ARAÚJO, Aurigena Antunes de et al.LDA vs QDA for FT-MIR prostate cancer tissue classification. Chemometrics and Intelligent Laboratory Systems (Print), v. 162, p. 123-129, 2017. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0169743916303318?via%3Dihub>. Acesso em: 21 mar. 2018.0169-7439https://repositorio.ufrn.br/handle/123456789/49621https://doi.org/10.1016/j.chemolab.2017.01.021ElsevierFT-MIRLDAQDATissueProstate cancerLDA vs QDA for FT-MIR prostate cancer tissue classificationinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleDiscrimination/classification of biological material a ta molecular level is one of the key aims of chemometrics applied to biospectroscopic data. Two discriminant functions, namely Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), were considered in this study for prostate cancer classification based on FT-MIR data, and illustrated graphically as boundary methods. Principal Component Analysis (PCA) was applied as a variable/dimensionality reduction method and Genetic Algorithm (GA) as variable selection method, followed by LDA and QDA. The performance of each method was determined using 40–100 MIR spectra per tissue sample (n=45), previously classified according to Gleason traditional grading by pathologists. The methods were used to separate the two-category of prostate cancer: Low grade (Gleason grade 2) vs. High grade (Gleason grade 3 and 4). The models were optimized using a training set and their performance was evaluated using a test set. Classification rates and quality metrics (Sensitivity, Specificity, Positive (or Precision) and Negative Predictive Values, Youden's index, and Positive and Negative Likelihood Ratios) were computed for each model. QDA-based models obtained higher classification rates and quality performance than LDA-based models. The models studied identify that secondary protein structure variations and DNA/RNA alterations are the main biomolecular ‘difference markers’ for prostate cancer grades.info:eu-repo/semantics/openAccessengreponame:Repositório Institucional da UFRNinstname:Universidade Federal do Rio Grande do Norte (UFRN)instacron:UFRNLICENSElicense.txtlicense.txttext/plain; charset=utf-81748https://repositorio.ufrn.br/bitstream/123456789/49621/2/license.txt8a4605be74aa9ea9d79846c1fba20a33MD52123456789/496212022-10-24 18:45:47.797oai:https://repositorio.ufrn.br:123456789/49621Tk9URTogUExBQ0UgWU9VUiBPV04gTElDRU5TRSBIRVJFClRoaXMgc2FtcGxlIGxpY2Vuc2UgaXMgcHJvdmlkZWQgZm9yIGluZm9ybWF0aW9uYWwgcHVycG9zZXMgb25seS4KCk5PTi1FWENMVVNJVkUgRElTVFJJQlVUSU9OIExJQ0VOU0UKCkJ5IHNpZ25pbmcgYW5kIHN1Ym1pdHRpbmcgdGhpcyBsaWNlbnNlLCB5b3UgKHRoZSBhdXRob3Iocykgb3IgY29weXJpZ2h0Cm93bmVyKSBncmFudHMgdG8gRFNwYWNlIFVuaXZlcnNpdHkgKERTVSkgdGhlIG5vbi1leGNsdXNpdmUgcmlnaHQgdG8gcmVwcm9kdWNlLAp0cmFuc2xhdGUgKGFzIGRlZmluZWQgYmVsb3cpLCBhbmQvb3IgZGlzdHJpYnV0ZSB5b3VyIHN1Ym1pc3Npb24gKGluY2x1ZGluZwp0aGUgYWJzdHJhY3QpIHdvcmxkd2lkZSBpbiBwcmludCBhbmQgZWxlY3Ryb25pYyBmb3JtYXQgYW5kIGluIGFueSBtZWRpdW0sCmluY2x1ZGluZyBidXQgbm90IGxpbWl0ZWQgdG8gYXVkaW8gb3IgdmlkZW8uCgpZb3UgYWdyZWUgdGhhdCBEU1UgbWF5LCB3aXRob3V0IGNoYW5naW5nIHRoZSBjb250ZW50LCB0cmFuc2xhdGUgdGhlCnN1Ym1pc3Npb24gdG8gYW55IG1lZGl1bSBvciBmb3JtYXQgZm9yIHRoZSBwdXJwb3NlIG9mIHByZXNlcnZhdGlvbi4KCllvdSBhbHNvIGFncmVlIHRoYXQgRFNVIG1heSBrZWVwIG1vcmUgdGhhbiBvbmUgY29weSBvZiB0aGlzIHN1Ym1pc3Npb24gZm9yCnB1cnBvc2VzIG9mIHNlY3VyaXR5LCBiYWNrLXVwIGFuZCBwcmVzZXJ2YXRpb24uCgpZb3UgcmVwcmVzZW50IHRoYXQgdGhlIHN1Ym1pc3Npb24gaXMgeW91ciBvcmlnaW5hbCB3b3JrLCBhbmQgdGhhdCB5b3UgaGF2ZQp0aGUgcmlnaHQgdG8gZ3JhbnQgdGhlIHJpZ2h0cyBjb250YWluZWQgaW4gdGhpcyBsaWNlbnNlLiBZb3UgYWxzbyByZXByZXNlbnQKdGhhdCB5b3VyIHN1Ym1pc3Npb24gZG9lcyBub3QsIHRvIHRoZSBiZXN0IG9mIHlvdXIga25vd2xlZGdlLCBpbmZyaW5nZSB1cG9uCmFueW9uZSdzIGNvcHlyaWdodC4KCklmIHRoZSBzdWJtaXNzaW9uIGNvbnRhaW5zIG1hdGVyaWFsIGZvciB3aGljaCB5b3UgZG8gbm90IGhvbGQgY29weXJpZ2h0LAp5b3UgcmVwcmVzZW50IHRoYXQgeW91IGhhdmUgb2J0YWluZWQgdGhlIHVucmVzdHJpY3RlZCBwZXJtaXNzaW9uIG9mIHRoZQpjb3B5cmlnaHQgb3duZXIgdG8gZ3JhbnQgRFNVIHRoZSByaWdodHMgcmVxdWlyZWQgYnkgdGhpcyBsaWNlbnNlLCBhbmQgdGhhdApzdWNoIHRoaXJkLXBhcnR5IG93bmVkIG1hdGVyaWFsIGlzIGNsZWFybHkgaWRlbnRpZmllZCBhbmQgYWNrbm93bGVkZ2VkCndpdGhpbiB0aGUgdGV4dCBvciBjb250ZW50IG9mIHRoZSBzdWJtaXNzaW9uLgoKSUYgVEhFIFNVQk1JU1NJT04gSVMgQkFTRUQgVVBPTiBXT1JLIFRIQVQgSEFTIEJFRU4gU1BPTlNPUkVEIE9SIFNVUFBPUlRFRApCWSBBTiBBR0VOQ1kgT1IgT1JHQU5JWkFUSU9OIE9USEVSIFRIQU4gRFNVLCBZT1UgUkVQUkVTRU5UIFRIQVQgWU9VIEhBVkUKRlVMRklMTEVEIEFOWSBSSUdIVCBPRiBSRVZJRVcgT1IgT1RIRVIgT0JMSUdBVElPTlMgUkVRVUlSRUQgQlkgU1VDSApDT05UUkFDVCBPUiBBR1JFRU1FTlQuCgpEU1Ugd2lsbCBjbGVhcmx5IGlkZW50aWZ5IHlvdXIgbmFtZShzKSBhcyB0aGUgYXV0aG9yKHMpIG9yIG93bmVyKHMpIG9mIHRoZQpzdWJtaXNzaW9uLCBhbmQgd2lsbCBub3QgbWFrZSBhbnkgYWx0ZXJhdGlvbiwgb3RoZXIgdGhhbiBhcyBhbGxvd2VkIGJ5IHRoaXMKbGljZW5zZSwgdG8geW91ciBzdWJtaXNzaW9uLgo=Repositório de PublicaçõesPUBhttp://repositorio.ufrn.br/oai/opendoar:2022-10-24T21:45:47Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN)false |
dc.title.pt_BR.fl_str_mv |
LDA vs QDA for FT-MIR prostate cancer tissue classification |
title |
LDA vs QDA for FT-MIR prostate cancer tissue classification |
spellingShingle |
LDA vs QDA for FT-MIR prostate cancer tissue classification Araújo, Aurigena Antunes de FT-MIR LDA QDA Tissue Prostate cancer |
title_short |
LDA vs QDA for FT-MIR prostate cancer tissue classification |
title_full |
LDA vs QDA for FT-MIR prostate cancer tissue classification |
title_fullStr |
LDA vs QDA for FT-MIR prostate cancer tissue classification |
title_full_unstemmed |
LDA vs QDA for FT-MIR prostate cancer tissue classification |
title_sort |
LDA vs QDA for FT-MIR prostate cancer tissue classification |
author |
Araújo, Aurigena Antunes de |
author_facet |
Araújo, Aurigena Antunes de Siqueira, Laurinda F.S. Araújo Júnior, Raimundo F. Morais, Camilo L.M. Lima, Kássio M.G. |
author_role |
author |
author2 |
Siqueira, Laurinda F.S. Araújo Júnior, Raimundo F. Morais, Camilo L.M. Lima, Kássio M.G. |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Araújo, Aurigena Antunes de Siqueira, Laurinda F.S. Araújo Júnior, Raimundo F. Morais, Camilo L.M. Lima, Kássio M.G. |
dc.subject.por.fl_str_mv |
FT-MIR LDA QDA Tissue Prostate cancer |
topic |
FT-MIR LDA QDA Tissue Prostate cancer |
description |
Discrimination/classification of biological material a ta molecular level is one of the key aims of chemometrics applied to biospectroscopic data. Two discriminant functions, namely Linear Discriminant Analysis (LDA) and Quadratic Discriminant Analysis (QDA), were considered in this study for prostate cancer classification based on FT-MIR data, and illustrated graphically as boundary methods. Principal Component Analysis (PCA) was applied as a variable/dimensionality reduction method and Genetic Algorithm (GA) as variable selection method, followed by LDA and QDA. The performance of each method was determined using 40–100 MIR spectra per tissue sample (n=45), previously classified according to Gleason traditional grading by pathologists. The methods were used to separate the two-category of prostate cancer: Low grade (Gleason grade 2) vs. High grade (Gleason grade 3 and 4). The models were optimized using a training set and their performance was evaluated using a test set. Classification rates and quality metrics (Sensitivity, Specificity, Positive (or Precision) and Negative Predictive Values, Youden's index, and Positive and Negative Likelihood Ratios) were computed for each model. QDA-based models obtained higher classification rates and quality performance than LDA-based models. The models studied identify that secondary protein structure variations and DNA/RNA alterations are the main biomolecular ‘difference markers’ for prostate cancer grades. |
publishDate |
2017 |
dc.date.issued.fl_str_mv |
2017-03-15 |
dc.date.accessioned.fl_str_mv |
2022-10-24T21:42:59Z |
dc.date.available.fl_str_mv |
2022-10-24T21:42:59Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.citation.fl_str_mv |
ARAÚJO, Aurigena Antunes de et al.LDA vs QDA for FT-MIR prostate cancer tissue classification. Chemometrics and Intelligent Laboratory Systems (Print), v. 162, p. 123-129, 2017. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0169743916303318?via%3Dihub>. Acesso em: 21 mar. 2018. |
dc.identifier.uri.fl_str_mv |
https://repositorio.ufrn.br/handle/123456789/49621 |
dc.identifier.issn.none.fl_str_mv |
0169-7439 |
dc.identifier.doi.none.fl_str_mv |
https://doi.org/10.1016/j.chemolab.2017.01.021 |
identifier_str_mv |
ARAÚJO, Aurigena Antunes de et al.LDA vs QDA for FT-MIR prostate cancer tissue classification. Chemometrics and Intelligent Laboratory Systems (Print), v. 162, p. 123-129, 2017. Disponível em: <https://www.sciencedirect.com/science/article/pii/S0169743916303318?via%3Dihub>. Acesso em: 21 mar. 2018. 0169-7439 |
url |
https://repositorio.ufrn.br/handle/123456789/49621 https://doi.org/10.1016/j.chemolab.2017.01.021 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.publisher.none.fl_str_mv |
Elsevier |
publisher.none.fl_str_mv |
Elsevier |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da UFRN instname:Universidade Federal do Rio Grande do Norte (UFRN) instacron:UFRN |
instname_str |
Universidade Federal do Rio Grande do Norte (UFRN) |
instacron_str |
UFRN |
institution |
UFRN |
reponame_str |
Repositório Institucional da UFRN |
collection |
Repositório Institucional da UFRN |
bitstream.url.fl_str_mv |
https://repositorio.ufrn.br/bitstream/123456789/49621/2/license.txt |
bitstream.checksum.fl_str_mv |
8a4605be74aa9ea9d79846c1fba20a33 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 |
repository.name.fl_str_mv |
Repositório Institucional da UFRN - Universidade Federal do Rio Grande do Norte (UFRN) |
repository.mail.fl_str_mv |
|
_version_ |
1814832870194151424 |