Publicação

Obtaining deep learning models for automatic classification of leukocytes

Ver documento

Detalhes bibliográficos
Resumo:In this work, the authors classify leukocyte images using the neural network architectures that won the annual ILSVRC competition. The classification of leukocytes is made using pretrained networks and the same networks trained from scratch in order to select the ones that achieve the best performance for the intended task. The categories used are eosinophils, lymphocytes, monocytes, and neutrophils. The analysis of the results takes into account the amount of training required, the regularization techniques used, the training time, and the accuracy in image classification. The best classification results, on the order of 98%, suggest that it is possible, considering a competent preprocessing, to train a network like the DenseNet with 169 or 201 layers, in about 100 epochs, to classify leukocytes in microscopy images.
Autores principais:Rodrigues, Pedro João
Outros Autores:Igrejas, Getúlio; Beato, Romeu Ferreira
Assunto:Deep learning Leukocytes
Ano:2020
País:Portugal
Tipo de documento:capítulo de livro
Tipo de acesso:acesso aberto
Instituição associada:Instituto Politécnico de Bragança
Idioma:inglês
Origem:Biblioteca Digital do IPB
_version_ 1867173122241724416
author Rodrigues, Pedro João
author2 Igrejas, Getúlio
Beato, Romeu Ferreira
author2_role author
author
author_facet Rodrigues, Pedro João
Igrejas, Getúlio
Beato, Romeu Ferreira
author_role author
contributor_name_str_mv Biblioteca Digital do IPB
country_str PT
creators_json_txt [{\"Person.name\":\"Rodrigues, Pedro João\",\"Person.identifier.orcid\":\"0000-0002-0555-2029\"},{\"Person.name\":\"Igrejas, Getúlio\",\"Person.identifier.orcid\":\"0000-0002-6820-8858\"},{\"Person.name\":\"Beato, Romeu Ferreira\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Biblioteca Digital do IPB
datacite.creators.creator.creatorName.fl_str_mv Rodrigues, Pedro João
Igrejas, Getúlio
Beato, Romeu Ferreira
datacite.date.Accepted.fl_str_mv 2020-01-01T00:00:00Z
datacite.date.available.fl_str_mv 2020-07-27T14:32:40Z
datacite.date.embargoed.fl_str_mv 2020-07-27T14:32:40Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv Deep learning
Leukocytes
datacite.titles.title.fl_str_mv Obtaining deep learning models for automatic classification of leukocytes
dc.contributor.none.fl_str_mv Biblioteca Digital do IPB
dc.creator.none.fl_str_mv Rodrigues, Pedro João
Igrejas, Getúlio
Beato, Romeu Ferreira
dc.date.Accepted.fl_str_mv 2020-01-01T00:00:00Z
dc.date.available.fl_str_mv 2020-07-27T14:32:40Z
dc.date.embargoed.fl_str_mv 2020-07-27T14:32:40Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10198/22527
dc.language.none.fl_str_mv eng
dc.publisher.none.fl_str_mv IGI Global
dc.rights.cclincense.fl_str_mv http://creativecommons.org/licenses/by/4.0/
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv Deep learning
Leukocytes
dc.title.fl_str_mv Obtaining deep learning models for automatic classification of leukocytes
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_3248
description In this work, the authors classify leukocyte images using the neural network architectures that won the annual ILSVRC competition. The classification of leukocytes is made using pretrained networks and the same networks trained from scratch in order to select the ones that achieve the best performance for the intended task. The categories used are eosinophils, lymphocytes, monocytes, and neutrophils. The analysis of the results takes into account the amount of training required, the regularization techniques used, the training time, and the accuracy in image classification. The best classification results, on the order of 98%, suggest that it is possible, considering a competent preprocessing, to train a network like the DenseNet with 169 or 201 layers, in about 100 epochs, to classify leukocytes in microscopy images.
dirty 0
eu_rights_str_mv openAccess
format bookPart
fulltext.url.fl_str_mv https://bibliotecadigital.ipb.pt/bitstreams/16442f87-768a-45f2-a552-fb63200e4065/download
id ipb_2ecf900d40143803870c514b62feb531
identifier.url.fl_str_mv http://hdl.handle.net/10198/22527
instacron_str ipb
institution Instituto Politécnico de Bragança
instname_str Instituto Politécnico de Bragança
language eng
network_acronym_str ipb
network_name_str Biblioteca Digital do IPB
oai_identifier_str oai:bibliotecadigital.ipb.pt:10198/22527
organization_str_mv urn:organizationAcronym:ipb
person_str_mv Rodrigues, Pedro João
Rodrigues, Pedro João
https://www.ciencia-id.pt/1316-21BB-9015
1316-21BB-9015
http://orcid.org/0000-0002-0555-2029
0000-0002-0555-2029
Igrejas, Getúlio
Igrejas, Getúlio
http://orcid.org/0000-0002-6820-8858
0000-0002-6820-8858
Beato, Romeu Ferreira
publishDate 2020
publisher.none.fl_str_mv IGI Global
reponame_str Biblioteca Digital do IPB
repository_id_str urn:repositoryAcronym:ipb
service_str_mv urn:repositoryAcronym:ipb
spelling engIGI Globalpt_PTIn this work, the authors classify leukocyte images using the neural network architectures that won the annual ILSVRC competition. The classification of leukocytes is made using pretrained networks and the same networks trained from scratch in order to select the ones that achieve the best performance for the intended task. The categories used are eosinophils, lymphocytes, monocytes, and neutrophils. The analysis of the results takes into account the amount of training required, the regularization techniques used, the training time, and the accuracy in image classification. The best classification results, on the order of 98%, suggest that it is possible, considering a competent preprocessing, to train a network like the DenseNet with 169 or 201 layers, in about 100 epochs, to classify leukocytes in microscopy images.application/pdfpt_PTObtaining deep learning models for automatic classification of leukocytesPersonalRodrigues, Pedro JoãoDSpacehttp://dspace.org/items/6c5911a6-b62b-4876-9def-60096b52383aDSpacehttp://dspace.org/items/6c5911a6-b62b-4876-9def-60096b52383aRodriguesPedro JoãoCiência IDhttps://www.ciencia-id.pt1316-21BB-9015ORCIDhttp://orcid.org0000-0002-0555-2029PersonalIgrejas, GetúlioDSpacehttp://dspace.org/items/ab4092ec-d1b1-4fe0-b65a-efba1310fd5aDSpacehttp://dspace.org/items/ab4092ec-d1b1-4fe0-b65a-efba1310fd5aIgrejasGetúlioORCIDhttp://orcid.org0000-0002-6820-8858Researcher IDhttps://www.researcherid.comM-8571-2013Scopus Author IDhttps://www.scopus.com47761255900Beato, Romeu FerreiraHostingInstitutionOrganizationalBiblioteca Digital do IPBe-mailmailto:dspace@ipb.ptdspace@ipb.ptDOIIsPartOf10.4018/978-1-7998-3095-5.ch0012020-07-27T14:32:40Z20202020-01-01T00:00:00ZHandlehttp://hdl.handle.net/10198/22527http://purl.org/coar/access_right/c_abf2open accessDeep learningLeukocytes2345365 bytesliteraturehttp://purl.org/coar/resource_type/c_3248book part2020http://creativecommons.org/licenses/by/4.0/http://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://bibliotecadigital.ipb.pt/bitstreams/16442f87-768a-45f2-a552-fb63200e4065/downloadMachine Learning and Deep Learning in Real- Time Applications132
spellingShingle Obtaining deep learning models for automatic classification of leukocytes
Rodrigues, Pedro João
Deep learning
Leukocytes
status SINGLETON
subject.fl_str_mv Deep learning
Leukocytes
title Obtaining deep learning models for automatic classification of leukocytes
title_full Obtaining deep learning models for automatic classification of leukocytes
title_fullStr Obtaining deep learning models for automatic classification of leukocytes
title_full_unstemmed Obtaining deep learning models for automatic classification of leukocytes
title_short Obtaining deep learning models for automatic classification of leukocytes
title_sort Obtaining deep learning models for automatic classification of leukocytes
topic Deep learning
Leukocytes
topic_facet Deep learning
Leukocytes
url http://hdl.handle.net/10198/22527
visible 1