A Hermite polynomial algorithm for detection of lesions in lymphoma images
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1007/s10044-020-00927-z http://hdl.handle.net/11449/206832 |
Resumo: | There are different types of lesions that can be investigated with the hematoxylin–eosin staining protocol. Lymphoma is a type of malignant disease which affects one of the highest white blood cell populations responsible for the immunological defence system. There are lymphoma sub-types that can have similar features, which make their diagnoses a difficult task. In this study, we investigated algorithms based on multiscale and multidimensional fractal geometry with colour models for classification of lymphoma images. Fractal features were extracted from the colour models and separate channels from these models. These features were concatenated to form feature vectors. Finally, we investigated the Hermite polynomial classifier and machine learning algorithms in order to evaluate the performance of the proposed approach. We employed the tenfold cross-validation method and evaluated the lesion sub-types with the binary and multiclass classifications. The separated colour channels obtained from histological images achieved relevant values for the binary and multiclass classifications, with an accuracy rating between 91 and 97%. These results can contribute to the detection and classification of the lesions by supporting specialists in clinical practices. |
id |
UNSP_bdc771c72fce949555270ae8ddaa9b79 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/206832 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A Hermite polynomial algorithm for detection of lesions in lymphoma imagesClassificationColour fractalColour spacesHermite polynomialLymphomaThere are different types of lesions that can be investigated with the hematoxylin–eosin staining protocol. Lymphoma is a type of malignant disease which affects one of the highest white blood cell populations responsible for the immunological defence system. There are lymphoma sub-types that can have similar features, which make their diagnoses a difficult task. In this study, we investigated algorithms based on multiscale and multidimensional fractal geometry with colour models for classification of lymphoma images. Fractal features were extracted from the colour models and separate channels from these models. These features were concatenated to form feature vectors. Finally, we investigated the Hermite polynomial classifier and machine learning algorithms in order to evaluate the performance of the proposed approach. We employed the tenfold cross-validation method and evaluated the lesion sub-types with the binary and multiclass classifications. The separated colour channels obtained from histological images achieved relevant values for the binary and multiclass classifications, with an accuracy rating between 91 and 97%. These results can contribute to the detection and classification of the lesions by supporting specialists in clinical practices.Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)Fundação de Amparo à Pesquisa do Estado de Minas Gerais (FAPEMIG)Federal Institute of Triângulo Mineiro (IFTM), Rua Belarmino Vilela Junqueira snDepartment of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265Department of Histology and Morphology Institute of Biomedical Science Federal University of UberlândiaScience and Technology Institute Federal University of São Paulo (UNIFESP), Avenida Cesare Mansueto Giulio Lattes, 1201Faculty of Computer Science (FACOM) Federal University of Uberlândia (UFU), Avenida João Neves de Ávila 2121, Bl.BDepartment of Computer Science and Statistics (DCCE) São Paulo State University (UNESP), Rua Cristóvão Colombo, 2265CNPq: (#304848/2018-2)CNPq: (#313365/2018-0)CNPq: (#427114/2016-0)CNPq: (#430965/2018-4)FAPEMIG: (#APQ-00578-18)Federal Institute of Triângulo Mineiro (IFTM)Universidade Estadual Paulista (Unesp)Universidade Federal de Uberlândia (UFU)Universidade de São Paulo (USP)Martins, Alessandro S.Neves, Leandro A. [UNESP]de Faria, Paulo R.Tosta, Thaína A. A.Longo, Leonardo C. [UNESP]Silva, Adriano B.Roberto, Guilherme Freiredo Nascimento, Marcelo Z.2021-06-25T10:44:33Z2021-06-25T10:44:33Z2021-05-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article523-535http://dx.doi.org/10.1007/s10044-020-00927-zPattern Analysis and Applications, v. 24, n. 2, p. 523-535, 2021.1433-755X1433-7541http://hdl.handle.net/11449/20683210.1007/s10044-020-00927-z2-s2.0-85096065400Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengPattern Analysis and Applicationsinfo:eu-repo/semantics/openAccess2021-10-23T15:16:34Zoai:repositorio.unesp.br:11449/206832Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462021-10-23T15:16:34Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A Hermite polynomial algorithm for detection of lesions in lymphoma images |
title |
A Hermite polynomial algorithm for detection of lesions in lymphoma images |
spellingShingle |
A Hermite polynomial algorithm for detection of lesions in lymphoma images Martins, Alessandro S. Classification Colour fractal Colour spaces Hermite polynomial Lymphoma |
title_short |
A Hermite polynomial algorithm for detection of lesions in lymphoma images |
title_full |
A Hermite polynomial algorithm for detection of lesions in lymphoma images |
title_fullStr |
A Hermite polynomial algorithm for detection of lesions in lymphoma images |
title_full_unstemmed |
A Hermite polynomial algorithm for detection of lesions in lymphoma images |
title_sort |
A Hermite polynomial algorithm for detection of lesions in lymphoma images |
author |
Martins, Alessandro S. |
author_facet |
Martins, Alessandro S. Neves, Leandro A. [UNESP] de Faria, Paulo R. Tosta, Thaína A. A. Longo, Leonardo C. [UNESP] Silva, Adriano B. Roberto, Guilherme Freire do Nascimento, Marcelo Z. |
author_role |
author |
author2 |
Neves, Leandro A. [UNESP] de Faria, Paulo R. Tosta, Thaína A. A. Longo, Leonardo C. [UNESP] Silva, Adriano B. Roberto, Guilherme Freire do Nascimento, Marcelo Z. |
author2_role |
author author author author author author author |
dc.contributor.none.fl_str_mv |
Federal Institute of Triângulo Mineiro (IFTM) Universidade Estadual Paulista (Unesp) Universidade Federal de Uberlândia (UFU) Universidade de São Paulo (USP) |
dc.contributor.author.fl_str_mv |
Martins, Alessandro S. Neves, Leandro A. [UNESP] de Faria, Paulo R. Tosta, Thaína A. A. Longo, Leonardo C. [UNESP] Silva, Adriano B. Roberto, Guilherme Freire do Nascimento, Marcelo Z. |
dc.subject.por.fl_str_mv |
Classification Colour fractal Colour spaces Hermite polynomial Lymphoma |
topic |
Classification Colour fractal Colour spaces Hermite polynomial Lymphoma |
description |
There are different types of lesions that can be investigated with the hematoxylin–eosin staining protocol. Lymphoma is a type of malignant disease which affects one of the highest white blood cell populations responsible for the immunological defence system. There are lymphoma sub-types that can have similar features, which make their diagnoses a difficult task. In this study, we investigated algorithms based on multiscale and multidimensional fractal geometry with colour models for classification of lymphoma images. Fractal features were extracted from the colour models and separate channels from these models. These features were concatenated to form feature vectors. Finally, we investigated the Hermite polynomial classifier and machine learning algorithms in order to evaluate the performance of the proposed approach. We employed the tenfold cross-validation method and evaluated the lesion sub-types with the binary and multiclass classifications. The separated colour channels obtained from histological images achieved relevant values for the binary and multiclass classifications, with an accuracy rating between 91 and 97%. These results can contribute to the detection and classification of the lesions by supporting specialists in clinical practices. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021-06-25T10:44:33Z 2021-06-25T10:44:33Z 2021-05-01 |
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/s10044-020-00927-z Pattern Analysis and Applications, v. 24, n. 2, p. 523-535, 2021. 1433-755X 1433-7541 http://hdl.handle.net/11449/206832 10.1007/s10044-020-00927-z 2-s2.0-85096065400 |
url |
http://dx.doi.org/10.1007/s10044-020-00927-z http://hdl.handle.net/11449/206832 |
identifier_str_mv |
Pattern Analysis and Applications, v. 24, n. 2, p. 523-535, 2021. 1433-755X 1433-7541 10.1007/s10044-020-00927-z 2-s2.0-85096065400 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Pattern Analysis and Applications |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
523-535 |
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_ |
1799964999896006656 |