Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica

Detalhes bibliográficos
Autor(a) principal: Carvalho, V. O. [UNESP]
Data de Publicação: 2013
Outros Autores: Neves, L. A. [UNESP], De Godoy, M. F., Moreira, R. D., Moriel, A. R., Murta, L. O.
Tipo de documento: Artigo de conferência
Idioma: por
Título da fonte: Repositório Institucional da UNESP
Texto Completo: http://dx.doi.org/10.1007/978-3-642-21198-0_70
http://hdl.handle.net/11449/74875
Resumo: This work combines symbolic machine learning and multiscale fractal techniques to generate models that characterize cellular rejection in myocardial biopsies and that can base a diagnosis support system. The models express the knowledge by the features threshold, fractal dimension, lacunarity, number of clusters, spatial percolation and percolation probability, all obtained with myocardial biopsies processing. Models were evaluated and the most significant was the one generated by the C4.5 algorithm for the features spatial percolation and number of clusters. The result is relevant and contributes to the specialized literature since it determines a standard diagnosis protocol. © 2013 Springer.
id UNSP_8fccee3516cb155c4e14aa7ec4871a57
oai_identifier_str oai:repositorio.unesp.br:11449/74875
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdicamultiscale fractal techniquesmyocardial biopsies imagessymbolic machine learningC4.5 algorithmDiagnosis support systemsLacunarityMultiscale fractalsNumber of clustersPercolation probabilitySymbolic machine learningBiomedical engineeringFractal dimensionLearning systemsSolventsBiopsyThis work combines symbolic machine learning and multiscale fractal techniques to generate models that characterize cellular rejection in myocardial biopsies and that can base a diagnosis support system. The models express the knowledge by the features threshold, fractal dimension, lacunarity, number of clusters, spatial percolation and percolation probability, all obtained with myocardial biopsies processing. Models were evaluated and the most significant was the one generated by the C4.5 algorithm for the features spatial percolation and number of clusters. The result is relevant and contributes to the specialized literature since it determines a standard diagnosis protocol. © 2013 Springer.Universidade Estadual Paulista DEMAC, Rio ClaroNUTECC Famerp, São José do Rio PretoFaculdade de Medicina de São José Do Rio Preto, São José do Rio PretoInstituto de Anatomia Patológica e Citopatologia, São José do Rio PretoUniversidade de São Paulo FFCLRP Depto. Computação e Matemática, Ribeirão PretoUniversidade Estadual Paulista DEMAC, Rio ClaroUniversidade Estadual Paulista (Unesp)Faculdade de Medicina de São José do Rio Preto (FAMERP)Instituto de Anatomia Patológica e CitopatologiaUniversidade de São Paulo (USP)Carvalho, V. O. [UNESP]Neves, L. A. [UNESP]De Godoy, M. F.Moreira, R. D.Moriel, A. R.Murta, L. O.2014-05-27T11:28:42Z2014-05-27T11:28:42Z2013-03-26info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObject272-275http://dx.doi.org/10.1007/978-3-642-21198-0_705th Latin American Congress on Biomedical Engineering (claib 2011): Sustainable Technologies For the Health of All, Pts 1 and 2. New York: Springer, v. 33, n. 1-2, p. 272-275, 2013.1680-0737http://hdl.handle.net/11449/7487510.1007/978-3-642-21198-0_702-s2.0-848752500241961581092362881Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPporIFMBE Proceedings0,143info:eu-repo/semantics/openAccess2021-10-23T21:44:13Zoai:repositorio.unesp.br:11449/74875Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-05-23T11:36:13.512333Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
title Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
spellingShingle Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
Carvalho, V. O. [UNESP]
multiscale fractal techniques
myocardial biopsies images
symbolic machine learning
C4.5 algorithm
Diagnosis support systems
Lacunarity
Multiscale fractals
Number of clusters
Percolation probability
Symbolic machine learning
Biomedical engineering
Fractal dimension
Learning systems
Solvents
Biopsy
title_short Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
title_full Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
title_fullStr Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
title_full_unstemmed Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
title_sort Aprendizado de máquina simbólico e técnicas fractais para caracterizar rejeição em biópsia miocárdica
author Carvalho, V. O. [UNESP]
author_facet Carvalho, V. O. [UNESP]
Neves, L. A. [UNESP]
De Godoy, M. F.
Moreira, R. D.
Moriel, A. R.
Murta, L. O.
author_role author
author2 Neves, L. A. [UNESP]
De Godoy, M. F.
Moreira, R. D.
Moriel, A. R.
Murta, L. O.
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Universidade Estadual Paulista (Unesp)
Faculdade de Medicina de São José do Rio Preto (FAMERP)
Instituto de Anatomia Patológica e Citopatologia
Universidade de São Paulo (USP)
dc.contributor.author.fl_str_mv Carvalho, V. O. [UNESP]
Neves, L. A. [UNESP]
De Godoy, M. F.
Moreira, R. D.
Moriel, A. R.
Murta, L. O.
dc.subject.por.fl_str_mv multiscale fractal techniques
myocardial biopsies images
symbolic machine learning
C4.5 algorithm
Diagnosis support systems
Lacunarity
Multiscale fractals
Number of clusters
Percolation probability
Symbolic machine learning
Biomedical engineering
Fractal dimension
Learning systems
Solvents
Biopsy
topic multiscale fractal techniques
myocardial biopsies images
symbolic machine learning
C4.5 algorithm
Diagnosis support systems
Lacunarity
Multiscale fractals
Number of clusters
Percolation probability
Symbolic machine learning
Biomedical engineering
Fractal dimension
Learning systems
Solvents
Biopsy
description This work combines symbolic machine learning and multiscale fractal techniques to generate models that characterize cellular rejection in myocardial biopsies and that can base a diagnosis support system. The models express the knowledge by the features threshold, fractal dimension, lacunarity, number of clusters, spatial percolation and percolation probability, all obtained with myocardial biopsies processing. Models were evaluated and the most significant was the one generated by the C4.5 algorithm for the features spatial percolation and number of clusters. The result is relevant and contributes to the specialized literature since it determines a standard diagnosis protocol. © 2013 Springer.
publishDate 2013
dc.date.none.fl_str_mv 2013-03-26
2014-05-27T11:28:42Z
2014-05-27T11:28:42Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv http://dx.doi.org/10.1007/978-3-642-21198-0_70
5th Latin American Congress on Biomedical Engineering (claib 2011): Sustainable Technologies For the Health of All, Pts 1 and 2. New York: Springer, v. 33, n. 1-2, p. 272-275, 2013.
1680-0737
http://hdl.handle.net/11449/74875
10.1007/978-3-642-21198-0_70
2-s2.0-84875250024
1961581092362881
url http://dx.doi.org/10.1007/978-3-642-21198-0_70
http://hdl.handle.net/11449/74875
identifier_str_mv 5th Latin American Congress on Biomedical Engineering (claib 2011): Sustainable Technologies For the Health of All, Pts 1 and 2. New York: Springer, v. 33, n. 1-2, p. 272-275, 2013.
1680-0737
10.1007/978-3-642-21198-0_70
2-s2.0-84875250024
1961581092362881
dc.language.iso.fl_str_mv por
language por
dc.relation.none.fl_str_mv IFMBE Proceedings
0,143
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 272-275
dc.source.none.fl_str_mv Scopus
reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv
_version_ 1803045848885493760

Registros relacionados