Computational diagnosis of skin lesions from dermoscopic images using combined features
Autor(a) principal: | |
---|---|
Data de Publicação: | 2019 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s00521-018-3439-8 http://hdl.handle.net/11449/196252 |
Resumo: | There has been an alarming increase in the number of skin cancer cases worldwide in recent years, which has raised interest in computational systems for automatic diagnosis to assist early diagnosis and prevention. Feature extraction to describe skin lesions is a challenging research area due to the difficulty in selecting meaningful features. The main objective of this work is to find the best combination of features, based on shape properties, colour variation and texture analysis, to be extracted using various feature extraction methods. Several colour spaces are used for the extraction of both colour- and texture-related features. Different categories of classifiers were adopted to evaluate the proposed feature extraction step, and several feature selection algorithms were compared for the classification of skin lesions. The developed skin lesion computational diagnosis system was applied to a set of 1104 dermoscopic images using a cross-validation procedure. The best results were obtained by an optimum-path forest classifier with very promising results. The proposed system achieved an accuracy of 92.3%, sensitivity of 87.5% and specificity of 97.1% when the full set of features was used. Furthermore, it achieved an accuracy of 91.6%, sensitivity of 87% and specificity of 96.2%, when 50 features were selected using a correlation-based feature selection algorithm. |
id |
UNSP_0b6fa0f9540acdc48b02ad9245e9888c |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/196252 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Computational diagnosis of skin lesions from dermoscopic images using combined featuresFeature extraction and selectionFractal dimension analysisDiscrete wavelet transformCo-occurrence matrixThere has been an alarming increase in the number of skin cancer cases worldwide in recent years, which has raised interest in computational systems for automatic diagnosis to assist early diagnosis and prevention. Feature extraction to describe skin lesions is a challenging research area due to the difficulty in selecting meaningful features. The main objective of this work is to find the best combination of features, based on shape properties, colour variation and texture analysis, to be extracted using various feature extraction methods. Several colour spaces are used for the extraction of both colour- and texture-related features. Different categories of classifiers were adopted to evaluate the proposed feature extraction step, and several feature selection algorithms were compared for the classification of skin lesions. The developed skin lesion computational diagnosis system was applied to a set of 1104 dermoscopic images using a cross-validation procedure. The best results were obtained by an optimum-path forest classifier with very promising results. The proposed system achieved an accuracy of 92.3%, sensitivity of 87.5% and specificity of 97.1% when the full set of features was used. Furthermore, it achieved an accuracy of 91.6%, sensitivity of 87% and specificity of 96.2%, when 50 features were selected using a correlation-based feature selection algorithm.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Programa Operacional Regional do Norte (NORTE2020), through Fundo Europeu de Desenvolvimento Regional (FEDER)Univ Porto, Fac Engn, Inst Ciencia & Inovacao Engn Mecan & Engn Ind, Dept Engn Mecan, Rua Dr Roberto Frias, P-4200465 Porto, PortugalUniv Estadual Paulista, Inst Biociencias Letras & Ciencias Exatas, Dept Ciencias Comp & Estat, Rua Cristovao Colombo 2265, BR-15054000 Sao Jose Do Rio Preto, SP, BrazilUniv Estadual Paulista, Inst Biociencias Letras & Ciencias Exatas, Dept Ciencias Comp & Estat, Rua Cristovao Colombo 2265, BR-15054000 Sao Jose Do Rio Preto, SP, BrazilPrograma Operacional Regional do Norte (NORTE2020), through Fundo Europeu de Desenvolvimento Regional (FEDER): NORTE-01-0145-FEDER-000022SpringerUniv PortoUniversidade Estadual Paulista (Unesp)Oliveira, Roberta B.Pereira, Aledir S. [UNESP]Tavares, Joao Manuel R. S.2020-12-10T19:38:38Z2020-12-10T19:38:38Z2019-10-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article6091-6111http://dx.doi.org/10.1007/s00521-018-3439-8Neural Computing & Applications. London: Springer London Ltd, v. 31, n. 10, p. 6091-6111, 2019.0941-0643http://hdl.handle.net/11449/19625210.1007/s00521-018-3439-8WOS:000491131700028Web of Sciencereponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengNeural Computing & Applicationsinfo:eu-repo/semantics/openAccess2021-10-23T05:43:40Zoai:repositorio.unesp.br:11449/196252Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T14:06:01.359689Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Computational diagnosis of skin lesions from dermoscopic images using combined features |
title |
Computational diagnosis of skin lesions from dermoscopic images using combined features |
spellingShingle |
Computational diagnosis of skin lesions from dermoscopic images using combined features Oliveira, Roberta B. Feature extraction and selection Fractal dimension analysis Discrete wavelet transform Co-occurrence matrix |
title_short |
Computational diagnosis of skin lesions from dermoscopic images using combined features |
title_full |
Computational diagnosis of skin lesions from dermoscopic images using combined features |
title_fullStr |
Computational diagnosis of skin lesions from dermoscopic images using combined features |
title_full_unstemmed |
Computational diagnosis of skin lesions from dermoscopic images using combined features |
title_sort |
Computational diagnosis of skin lesions from dermoscopic images using combined features |
author |
Oliveira, Roberta B. |
author_facet |
Oliveira, Roberta B. Pereira, Aledir S. [UNESP] Tavares, Joao Manuel R. S. |
author_role |
author |
author2 |
Pereira, Aledir S. [UNESP] Tavares, Joao Manuel R. S. |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Univ Porto Universidade Estadual Paulista (Unesp) |
dc.contributor.author.fl_str_mv |
Oliveira, Roberta B. Pereira, Aledir S. [UNESP] Tavares, Joao Manuel R. S. |
dc.subject.por.fl_str_mv |
Feature extraction and selection Fractal dimension analysis Discrete wavelet transform Co-occurrence matrix |
topic |
Feature extraction and selection Fractal dimension analysis Discrete wavelet transform Co-occurrence matrix |
description |
There has been an alarming increase in the number of skin cancer cases worldwide in recent years, which has raised interest in computational systems for automatic diagnosis to assist early diagnosis and prevention. Feature extraction to describe skin lesions is a challenging research area due to the difficulty in selecting meaningful features. The main objective of this work is to find the best combination of features, based on shape properties, colour variation and texture analysis, to be extracted using various feature extraction methods. Several colour spaces are used for the extraction of both colour- and texture-related features. Different categories of classifiers were adopted to evaluate the proposed feature extraction step, and several feature selection algorithms were compared for the classification of skin lesions. The developed skin lesion computational diagnosis system was applied to a set of 1104 dermoscopic images using a cross-validation procedure. The best results were obtained by an optimum-path forest classifier with very promising results. The proposed system achieved an accuracy of 92.3%, sensitivity of 87.5% and specificity of 97.1% when the full set of features was used. Furthermore, it achieved an accuracy of 91.6%, sensitivity of 87% and specificity of 96.2%, when 50 features were selected using a correlation-based feature selection algorithm. |
publishDate |
2019 |
dc.date.none.fl_str_mv |
2019-10-01 2020-12-10T19:38:38Z 2020-12-10T19:38:38Z |
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.uri.fl_str_mv |
http://dx.doi.org/10.1007/s00521-018-3439-8 Neural Computing & Applications. London: Springer London Ltd, v. 31, n. 10, p. 6091-6111, 2019. 0941-0643 http://hdl.handle.net/11449/196252 10.1007/s00521-018-3439-8 WOS:000491131700028 |
url |
http://dx.doi.org/10.1007/s00521-018-3439-8 http://hdl.handle.net/11449/196252 |
identifier_str_mv |
Neural Computing & Applications. London: Springer London Ltd, v. 31, n. 10, p. 6091-6111, 2019. 0941-0643 10.1007/s00521-018-3439-8 WOS:000491131700028 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Neural Computing & Applications |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
6091-6111 |
dc.publisher.none.fl_str_mv |
Springer |
publisher.none.fl_str_mv |
Springer |
dc.source.none.fl_str_mv |
Web of Science 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_ |
1808128315291074560 |