A novel architecture to classify histopathology images using convolutional neural networks

Detalhes bibliográficos
Autor(a) principal: Kandel, Ibrahem
Data de Publicação: 2020
Outros Autores: Castelli, Mauro
Tipo de documento: Artigo
Idioma: eng
Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
Texto Completo: http://hdl.handle.net/10362/98755
Resumo: Kandel, I., & Castelli, M. (2020). A novel architecture to classify histopathology images using convolutional neural networks. Applied Sciences (Switzerland), 10(8), 1-17. [2929]. https://doi.org/10.3390/APP10082929
id RCAP_53c0c948ec2b3ca837528a7571df7005
oai_identifier_str oai:run.unl.pt:10362/98755
network_acronym_str RCAP
network_name_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository_id_str 7160
spelling A novel architecture to classify histopathology images using convolutional neural networksConvolutional neural networksDeep learningHistopathology imagesImage classificationMaterials Science(all)InstrumentationEngineering(all)Process Chemistry and TechnologyComputer Science ApplicationsFluid Flow and Transfer ProcessesKandel, I., & Castelli, M. (2020). A novel architecture to classify histopathology images using convolutional neural networks. Applied Sciences (Switzerland), 10(8), 1-17. [2929]. https://doi.org/10.3390/APP10082929Histopathology is the study of tissue structure under the microscope to determine if the cells are normal or abnormal. Histopathology is a very important exam that is used to determine the patients' treatment plan. The classification of histopathology images is very difficult to even an experienced pathologist, and a second opinion is often needed. Convolutional neural network (CNN), a particular type of deep learning architecture, obtained outstanding results in computer vision tasks like image classification. In this paper, we propose a novel CNN architecture to classify histopathology images. The proposed model consists of 15 convolution layers and two fully connected layers. A comparison between different activation functions was performed to detect the most efficient one, taking into account two different optimizers. To train and evaluate the proposed model, the publicly available PatchCamelyon dataset was used. The dataset consists of 220,000 annotated images for training and 57,000 unannotated images for testing. The proposed model achieved higher performance compared to the state-of-the-art architectures with an AUC of 95.46%.NOVA Information Management School (NOVA IMS)Information Management Research Center (MagIC) - NOVA Information Management SchoolRUNKandel, IbrahemCastelli, Mauro2020-06-03T00:55:39Z2020-04-232020-04-23T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article17application/pdfhttp://hdl.handle.net/10362/98755eng2076-3417PURE: 18414923https://doi.org/10.3390/APP10082929info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2024-05-22T17:45:48Zoai:run.unl.pt:10362/98755Portal AgregadorONGhttps://www.rcaap.pt/oai/openairemluisa.alvim@gmail.comopendoar:71602024-05-22T17:45:48Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse
dc.title.none.fl_str_mv A novel architecture to classify histopathology images using convolutional neural networks
title A novel architecture to classify histopathology images using convolutional neural networks
spellingShingle A novel architecture to classify histopathology images using convolutional neural networks
Kandel, Ibrahem
Convolutional neural networks
Deep learning
Histopathology images
Image classification
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
title_short A novel architecture to classify histopathology images using convolutional neural networks
title_full A novel architecture to classify histopathology images using convolutional neural networks
title_fullStr A novel architecture to classify histopathology images using convolutional neural networks
title_full_unstemmed A novel architecture to classify histopathology images using convolutional neural networks
title_sort A novel architecture to classify histopathology images using convolutional neural networks
author Kandel, Ibrahem
author_facet Kandel, Ibrahem
Castelli, Mauro
author_role author
author2 Castelli, Mauro
author2_role author
dc.contributor.none.fl_str_mv NOVA Information Management School (NOVA IMS)
Information Management Research Center (MagIC) - NOVA Information Management School
RUN
dc.contributor.author.fl_str_mv Kandel, Ibrahem
Castelli, Mauro
dc.subject.por.fl_str_mv Convolutional neural networks
Deep learning
Histopathology images
Image classification
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
topic Convolutional neural networks
Deep learning
Histopathology images
Image classification
Materials Science(all)
Instrumentation
Engineering(all)
Process Chemistry and Technology
Computer Science Applications
Fluid Flow and Transfer Processes
description Kandel, I., & Castelli, M. (2020). A novel architecture to classify histopathology images using convolutional neural networks. Applied Sciences (Switzerland), 10(8), 1-17. [2929]. https://doi.org/10.3390/APP10082929
publishDate 2020
dc.date.none.fl_str_mv 2020-06-03T00:55:39Z
2020-04-23
2020-04-23T00:00:00Z
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://hdl.handle.net/10362/98755
url http://hdl.handle.net/10362/98755
dc.language.iso.fl_str_mv eng
language eng
dc.relation.none.fl_str_mv 2076-3417
PURE: 18414923
https://doi.org/10.3390/APP10082929
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv 17
application/pdf
dc.source.none.fl_str_mv reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron:RCAAP
instname_str Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
instacron_str RCAAP
institution RCAAP
reponame_str Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
collection Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
repository.name.fl_str_mv Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação
repository.mail.fl_str_mv mluisa.alvim@gmail.com
_version_ 1817545744566976512