Classification of glomerular hypercellularity using convolutional features and support vector machine
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da FIOCRUZ (ARCA) |
Texto Completo: | https://www.arca.fiocruz.br/handle/icict/40666 |
Resumo: | Brazilian National Health Council. To preserve confidentiality, the images (including those shown in the paper) were separated from other patient's data. No data presented herein allows patient identification. All the procedures were approved by the Ethics Committee for Research Involving Human subjects of the Gonçalo Moniz Institute from the Oswaldo Cruz Foundation (CPqGM/FIOCRUZ), Protocols No. 188/ 09 and No. 1817574. |
id |
CRUZ_f3770bab2f27350d1b53a9f69f4c9803 |
---|---|
oai_identifier_str |
oai:www.arca.fiocruz.br:icict/40666 |
network_acronym_str |
CRUZ |
network_name_str |
Repositório Institucional da FIOCRUZ (ARCA) |
repository_id_str |
2135 |
spelling |
Chagas, PauloSouza, LuizAraújo, IkaroAldeman, NayzeDuarte, AngeloAngelo, MicheledosSantos, Washington Luis ConradoOliveira, Luciano2020-04-07T14:11:39Z2020-04-07T14:11:39Z2020CHAGAS, Paulo et al. Classification of glomerular hypercellularity using convolutional features and support vector machine. Artificial Intelligence in Medicine, v. 103, 2020.0933-3657https://www.arca.fiocruz.br/handle/icict/4066610.1016/j.artmed.2020.101808Brazilian National Health Council. To preserve confidentiality, the images (including those shown in the paper) were separated from other patient's data. No data presented herein allows patient identification. All the procedures were approved by the Ethics Committee for Research Involving Human subjects of the Gonçalo Moniz Institute from the Oswaldo Cruz Foundation (CPqGM/FIOCRUZ), Protocols No. 188/ 09 and No. 1817574.Universidade Federal da Bahia. Salvador, BA, Brasil.Universidade Federal da Bahia. Salvador, BA, Brasil.Universidade Federal da Bahia. Salvador, BA, Brasil.Universidade Federal do Piauí. Departamento de Medicina Especializada. Terezina, PI, Brasil.Universidade Estadual de Feira de Santana. Salvador, BA, Brasil.Universidade Estadual de Feira de Santana. Salvador, BA, Brasil.Fundação Oswaldo Cruz. Instituto Gonçalo Moniz. Salvador, BA, Brasil.Universidade Federal da Bahia. Salvador, BA, Brasil.Glomeruli are histological structures of the kidney cortex formed by interwoven blood capillaries, and are responsible for blood filtration. Glomerular lesions impair kidney filtration capability, leading to protein loss and metabolic waste retention. An example of lesion is the glomerular hypercellularity, which is characterized by an increase in the number of cell nuclei in different areas of the glomeruli. Glomerular hypercellularity is a frequent lesion present in different kidney diseases. Automatic detection of glomerular hypercellularity would accelerate the screening of scanned histological slides for the lesion, enhancing clinical diagnosis. Having this in mind, we propose a new approach for classification of hypercellularity in human kidney images. Our proposed method introduces a novel architecture of a convolutional neural network (CNN) along with a support vector machine, achieving near perfect average results on FIOCRUZ data set in a binary classification (lesion or normal). Additionally, classification of hypercellularity sub-lesions was also evaluated, considering mesangial, endocapilar and both lesions, reaching an average accuracy of 82%. Either in binary task or in the multi-classification one, our proposed method outperformed Xception, ResNet50 and InceptionV3 networks, as well as a traditional handcrafted-based method. To the best of our knowledge, this is the first study on deep learning over a data set of glomerular hypercellularity images of human kidney.engElsevierHipercelularidadeBiópsia renal humanaRede neural convolucionalHypercellularityHuman kidney biopsyConvolutional neural networkClassification of glomerular hypercellularity using convolutional features and support vector machineinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleinfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da FIOCRUZ (ARCA)instname:Fundação Oswaldo Cruz (FIOCRUZ)instacron:FIOCRUZLICENSElicense.txtlicense.txttext/plain; charset=utf-82991https://www.arca.fiocruz.br/bitstream/icict/40666/1/license.txt5a560609d32a3863062d77ff32785d58MD51ORIGINALChagas P Classification....pdfChagas P Classification....pdfapplication/pdf7803287https://www.arca.fiocruz.br/bitstream/icict/40666/2/Chagas%20P%20Classification....pdf8406d7cf2344ab16df8d3ee7ba290ed8MD52TEXTChagas P Classification....pdf.txtChagas P Classification....pdf.txtExtracted texttext/plain54552https://www.arca.fiocruz.br/bitstream/icict/40666/3/Chagas%20P%20Classification....pdf.txt9c1a8565eab7b9cd834ebd7bddf4cf8aMD53icict/406662023-03-15 14:34:20.5oai:www.arca.fiocruz.br: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ório InstitucionalPUBhttps://www.arca.fiocruz.br/oai/requestrepositorio.arca@fiocruz.bropendoar:21352023-03-15T17:34:20Repositório Institucional da FIOCRUZ (ARCA) - Fundação Oswaldo Cruz (FIOCRUZ)false |
dc.title.pt_BR.fl_str_mv |
Classification of glomerular hypercellularity using convolutional features and support vector machine |
title |
Classification of glomerular hypercellularity using convolutional features and support vector machine |
spellingShingle |
Classification of glomerular hypercellularity using convolutional features and support vector machine Chagas, Paulo Hipercelularidade Biópsia renal humana Rede neural convolucional Hypercellularity Human kidney biopsy Convolutional neural network |
title_short |
Classification of glomerular hypercellularity using convolutional features and support vector machine |
title_full |
Classification of glomerular hypercellularity using convolutional features and support vector machine |
title_fullStr |
Classification of glomerular hypercellularity using convolutional features and support vector machine |
title_full_unstemmed |
Classification of glomerular hypercellularity using convolutional features and support vector machine |
title_sort |
Classification of glomerular hypercellularity using convolutional features and support vector machine |
author |
Chagas, Paulo |
author_facet |
Chagas, Paulo Souza, Luiz Araújo, Ikaro Aldeman, Nayze Duarte, Angelo Angelo, Michele dosSantos, Washington Luis Conrado Oliveira, Luciano |
author_role |
author |
author2 |
Souza, Luiz Araújo, Ikaro Aldeman, Nayze Duarte, Angelo Angelo, Michele dosSantos, Washington Luis Conrado Oliveira, Luciano |
author2_role |
author author author author author author author |
dc.contributor.author.fl_str_mv |
Chagas, Paulo Souza, Luiz Araújo, Ikaro Aldeman, Nayze Duarte, Angelo Angelo, Michele dosSantos, Washington Luis Conrado Oliveira, Luciano |
dc.subject.other.pt_BR.fl_str_mv |
Hipercelularidade Biópsia renal humana Rede neural convolucional |
topic |
Hipercelularidade Biópsia renal humana Rede neural convolucional Hypercellularity Human kidney biopsy Convolutional neural network |
dc.subject.en.pt_BR.fl_str_mv |
Hypercellularity Human kidney biopsy Convolutional neural network |
description |
Brazilian National Health Council. To preserve confidentiality, the images (including those shown in the paper) were separated from other patient's data. No data presented herein allows patient identification. All the procedures were approved by the Ethics Committee for Research Involving Human subjects of the Gonçalo Moniz Institute from the Oswaldo Cruz Foundation (CPqGM/FIOCRUZ), Protocols No. 188/ 09 and No. 1817574. |
publishDate |
2020 |
dc.date.accessioned.fl_str_mv |
2020-04-07T14:11:39Z |
dc.date.available.fl_str_mv |
2020-04-07T14:11:39Z |
dc.date.issued.fl_str_mv |
2020 |
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 |
CHAGAS, Paulo et al. Classification of glomerular hypercellularity using convolutional features and support vector machine. Artificial Intelligence in Medicine, v. 103, 2020. |
dc.identifier.uri.fl_str_mv |
https://www.arca.fiocruz.br/handle/icict/40666 |
dc.identifier.issn.pt_BR.fl_str_mv |
0933-3657 |
dc.identifier.doi.none.fl_str_mv |
10.1016/j.artmed.2020.101808 |
identifier_str_mv |
CHAGAS, Paulo et al. Classification of glomerular hypercellularity using convolutional features and support vector machine. Artificial Intelligence in Medicine, v. 103, 2020. 0933-3657 10.1016/j.artmed.2020.101808 |
url |
https://www.arca.fiocruz.br/handle/icict/40666 |
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 FIOCRUZ (ARCA) instname:Fundação Oswaldo Cruz (FIOCRUZ) instacron:FIOCRUZ |
instname_str |
Fundação Oswaldo Cruz (FIOCRUZ) |
instacron_str |
FIOCRUZ |
institution |
FIOCRUZ |
reponame_str |
Repositório Institucional da FIOCRUZ (ARCA) |
collection |
Repositório Institucional da FIOCRUZ (ARCA) |
bitstream.url.fl_str_mv |
https://www.arca.fiocruz.br/bitstream/icict/40666/1/license.txt https://www.arca.fiocruz.br/bitstream/icict/40666/2/Chagas%20P%20Classification....pdf https://www.arca.fiocruz.br/bitstream/icict/40666/3/Chagas%20P%20Classification....pdf.txt |
bitstream.checksum.fl_str_mv |
5a560609d32a3863062d77ff32785d58 8406d7cf2344ab16df8d3ee7ba290ed8 9c1a8565eab7b9cd834ebd7bddf4cf8a |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositório Institucional da FIOCRUZ (ARCA) - Fundação Oswaldo Cruz (FIOCRUZ) |
repository.mail.fl_str_mv |
repositorio.arca@fiocruz.br |
_version_ |
1798324720886611968 |