Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , |
Tipo de documento: | Livro |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | https://hdl.handle.net/10216/149208 |
Resumo: | Diabetic Foot Ulcers (DFU) are lesions in the foot region caused by diabetes mellitus. It is essential to define the appropriate treatment in the early stages of the disease once late treatment may result in amputation. This article proposes an ensemble approach composed of five modified convolutional neural networks (CNNs) - VGG-16, VGG-19, Resnet50, InceptionV3, and Densenet-201 - to classify DFU images. To define the parameters, we fine-tuned the CNNs, evaluated different configurations of fully connected layers, and used batch normalization and dropout operations. The modified CNNs were well suited to the problem; however, we observed that the union of the five CNNs significantly increased the success rates. We performed tests using 8,250 images with different resolution, contrast, color, and texture characteristics and included data augmentation operations to expand the training dataset. 5-fold cross-validation led to an average accuracy of 95.04%, resulting in a Kappa index greater than 91.85%, considered Excellent. |
id |
RCAP_b3b9aeed62e57d584a7a18fb995afcc8 |
---|---|
oai_identifier_str |
oai:repositorio-aberto.up.pt:10216/149208 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs EnsembleDiabetic Foot Ulcers (DFU) are lesions in the foot region caused by diabetes mellitus. It is essential to define the appropriate treatment in the early stages of the disease once late treatment may result in amputation. This article proposes an ensemble approach composed of five modified convolutional neural networks (CNNs) - VGG-16, VGG-19, Resnet50, InceptionV3, and Densenet-201 - to classify DFU images. To define the parameters, we fine-tuned the CNNs, evaluated different configurations of fully connected layers, and used batch normalization and dropout operations. The modified CNNs were well suited to the problem; however, we observed that the union of the five CNNs significantly increased the success rates. We performed tests using 8,250 images with different resolution, contrast, color, and texture characteristics and included data augmentation operations to expand the training dataset. 5-fold cross-validation led to an average accuracy of 95.04%, resulting in a Kappa index greater than 91.85%, considered Excellent.20222022-01-01T00:00:00Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/bookapplication/pdfhttps://hdl.handle.net/10216/149208eng10.1109/cbms55023.2022.00056Santos, ESantos, FDallyson, JAires, KJoão Manuel R. S. TavaresVeras, Rinfo: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:RCAAP2023-11-29T15:23:29Zoai:repositorio-aberto.up.pt:10216/149208Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-20T00:22:27.691485Repositório 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 |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble |
title |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble |
spellingShingle |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble Santos, E |
title_short |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble |
title_full |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble |
title_fullStr |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble |
title_full_unstemmed |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble |
title_sort |
Diabetic Foot Ulcers Classification using a fine-tuned CNNs Ensemble |
author |
Santos, E |
author_facet |
Santos, E Santos, F Dallyson, J Aires, K João Manuel R. S. Tavares Veras, R |
author_role |
author |
author2 |
Santos, F Dallyson, J Aires, K João Manuel R. S. Tavares Veras, R |
author2_role |
author author author author author |
dc.contributor.author.fl_str_mv |
Santos, E Santos, F Dallyson, J Aires, K João Manuel R. S. Tavares Veras, R |
description |
Diabetic Foot Ulcers (DFU) are lesions in the foot region caused by diabetes mellitus. It is essential to define the appropriate treatment in the early stages of the disease once late treatment may result in amputation. This article proposes an ensemble approach composed of five modified convolutional neural networks (CNNs) - VGG-16, VGG-19, Resnet50, InceptionV3, and Densenet-201 - to classify DFU images. To define the parameters, we fine-tuned the CNNs, evaluated different configurations of fully connected layers, and used batch normalization and dropout operations. The modified CNNs were well suited to the problem; however, we observed that the union of the five CNNs significantly increased the success rates. We performed tests using 8,250 images with different resolution, contrast, color, and texture characteristics and included data augmentation operations to expand the training dataset. 5-fold cross-validation led to an average accuracy of 95.04%, resulting in a Kappa index greater than 91.85%, considered Excellent. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022 2022-01-01T00:00:00Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/book |
format |
book |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
https://hdl.handle.net/10216/149208 |
url |
https://hdl.handle.net/10216/149208 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
10.1109/cbms55023.2022.00056 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
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 |
|
_version_ |
1799136140493586432 |