Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting

Skin lesions are caused due to multiple factors, like allergies, infections, exposition to the sun, etc. These skin diseases have become a challenge in medical diagnosis due to visual similarities, where image classification is an essential task to achieve an adequate diagnostic of different lesions...

Descripción completa

Detalles Bibliográficos
Autores: Thurnhofer-Hemsi, Karl, López-Rubio, Ezequiel, Domínguez, Enrique, Elizondo, David A.
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Instituto de Salud Carlos III (ISCIII)
Repositorio:Repisalud
Idioma:español
OAI Identifier:oai:repisalud.isciii.es:20.500.12105/18430
Acceso en línea:http://hdl.handle.net/20.500.12105/18430
Access Level:acceso abierto
Palabra clave:Image processing
Deep learning
Classification
Skin lesion
Melanoma
Convolutional neural networks
Skin cancer
Procesamiento de imagen asistido por computador
Aprendizaje profundo
Clasificación
Lesiones por desenguantamiento
Red nerviosa
Neoplasias cutáneas
Skin Neoplasms
Neural Networks (Computer)
Skin Diseases
Hypersensitivity
Humans
Melanocytes
Probability
Epidermis
Image Processing, Computer-Assisted
id ES_e7aab148e643a8ff58efea94577ab61a
oai_identifier_str oai:repisalud.isciii.es:20.500.12105/18430
network_acronym_str ES
network_name_str España
repository_id_str
spelling Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced ShiftingThurnhofer-Hemsi, KarlLópez-Rubio, EzequielDomínguez, EnriqueElizondo, David A.Image processingDeep learningClassificationSkin lesionMelanomaConvolutional neural networksSkin cancerProcesamiento de imagen asistido por computadorAprendizaje profundoClasificaciónLesiones por desenguantamientoRed nerviosaNeoplasias cutáneasMelanomaSkin NeoplasmsNeural Networks (Computer)Skin DiseasesHypersensitivityHumansMelanocytesProbabilityEpidermisImage Processing, Computer-AssistedClassificationSkin DiseasesSkin lesions are caused due to multiple factors, like allergies, infections, exposition to the sun, etc. These skin diseases have become a challenge in medical diagnosis due to visual similarities, where image classification is an essential task to achieve an adequate diagnostic of different lesions. Melanoma is one of the best-known types of skin lesions due to the vast majority of skin cancer deaths. In this work, we propose an ensemble of improved convolutional neural networks combined with a test-time regularly spaced shifting technique for skin lesion classification. The shifting technique builds several versions of the test input image, which are shifted by displacement vectors that lie on a regular lattice in the plane of possible shifts. These shifted versions of the test image are subsequently passed on to each of the classifiers of an ensemble. Finally, all the outputs from the classifiers are combined to yield the final result. Experiment results show a significant improvement on the well-known HAM10000 dataset in terms of accuracy and F-score. In particular, it is demonstrated that our combination of ensembles with test-time regularly spaced shifting yields better performance than any of the two methods when applied alone.Institute of Electrical and Electronics Engineers (IEEE)[Thurnhofer-Hemsi,K; López-Rubio,E; Domínguez,E] Department of Computer Languages and Computer Science, Universidad de Málaga, Málaga, Spain. [Thurnhofer-Hemsi,K; López-Rubio,E; Domínguez,E] Biomedic Research Institute of Málaga (IBIMA), Málaga, Spain. [Elizondo,DA] School of Computer Science and Informatics, De Montfort University, Leicester, U.K.20242024-02-1920212021-08-0920212021-08-09review articlehttp://purl.org/coar/resource_type/c_dcae04bcVoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articlehttp://hdl.handle.net/20.500.12105/18430reponame:Repisaludinstname:Instituto de Salud Carlos III (ISCIII)Españolspaopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivatives 4.0 Internationalhttp://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessoai:repisalud.isciii.es:20.500.12105/184302026-06-12T12:43:37Z
dc.title.none.fl_str_mv Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
title Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
spellingShingle Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
Thurnhofer-Hemsi, Karl
Image processing
Deep learning
Classification
Skin lesion
Melanoma
Convolutional neural networks
Skin cancer
Procesamiento de imagen asistido por computador
Aprendizaje profundo
Clasificación
Lesiones por desenguantamiento
Red nerviosa
Neoplasias cutáneas
Melanoma
Skin Neoplasms
Neural Networks (Computer)
Skin Diseases
Hypersensitivity
Humans
Melanocytes
Probability
Epidermis
Image Processing, Computer-Assisted
Classification
Skin Diseases
title_short Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
title_full Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
title_fullStr Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
title_full_unstemmed Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
title_sort Skin Lesion Classification by Ensembles of Deep Convolutional Networks and Regularly Spaced Shifting
dc.creator.none.fl_str_mv Thurnhofer-Hemsi, Karl
López-Rubio, Ezequiel
Domínguez, Enrique
Elizondo, David A.
author Thurnhofer-Hemsi, Karl
author_facet Thurnhofer-Hemsi, Karl
López-Rubio, Ezequiel
Domínguez, Enrique
Elizondo, David A.
author_role author
author2 López-Rubio, Ezequiel
Domínguez, Enrique
Elizondo, David A.
author2_role author
author
author
dc.contributor.none.fl_str_mv [Thurnhofer-Hemsi,K; López-Rubio,E; Domínguez,E] Department of Computer Languages and Computer Science, Universidad de Málaga, Málaga, Spain. [Thurnhofer-Hemsi,K; López-Rubio,E; Domínguez,E] Biomedic Research Institute of Málaga (IBIMA), Málaga, Spain. [Elizondo,DA] School of Computer Science and Informatics, De Montfort University, Leicester, U.K.
dc.subject.none.fl_str_mv Image processing
Deep learning
Classification
Skin lesion
Melanoma
Convolutional neural networks
Skin cancer
Procesamiento de imagen asistido por computador
Aprendizaje profundo
Clasificación
Lesiones por desenguantamiento
Red nerviosa
Neoplasias cutáneas
Melanoma
Skin Neoplasms
Neural Networks (Computer)
Skin Diseases
Hypersensitivity
Humans
Melanocytes
Probability
Epidermis
Image Processing, Computer-Assisted
Classification
Skin Diseases
topic Image processing
Deep learning
Classification
Skin lesion
Melanoma
Convolutional neural networks
Skin cancer
Procesamiento de imagen asistido por computador
Aprendizaje profundo
Clasificación
Lesiones por desenguantamiento
Red nerviosa
Neoplasias cutáneas
Melanoma
Skin Neoplasms
Neural Networks (Computer)
Skin Diseases
Hypersensitivity
Humans
Melanocytes
Probability
Epidermis
Image Processing, Computer-Assisted
Classification
Skin Diseases
description Skin lesions are caused due to multiple factors, like allergies, infections, exposition to the sun, etc. These skin diseases have become a challenge in medical diagnosis due to visual similarities, where image classification is an essential task to achieve an adequate diagnostic of different lesions. Melanoma is one of the best-known types of skin lesions due to the vast majority of skin cancer deaths. In this work, we propose an ensemble of improved convolutional neural networks combined with a test-time regularly spaced shifting technique for skin lesion classification. The shifting technique builds several versions of the test input image, which are shifted by displacement vectors that lie on a regular lattice in the plane of possible shifts. These shifted versions of the test image are subsequently passed on to each of the classifiers of an ensemble. Finally, all the outputs from the classifiers are combined to yield the final result. Experiment results show a significant improvement on the well-known HAM10000 dataset in terms of accuracy and F-score. In particular, it is demonstrated that our combination of ensembles with test-time regularly spaced shifting yields better performance than any of the two methods when applied alone.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-08-09
2021
2021-08-09
2024
2024-02-19
dc.type.none.fl_str_mv review article
http://purl.org/coar/resource_type/c_dcae04bc
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv http://hdl.handle.net/20.500.12105/18430
url http://hdl.handle.net/20.500.12105/18430
dc.language.none.fl_str_mv Español
spa
language_invalid_str_mv Español
language spa
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivatives 4.0 International
http://creativecommons.org/licenses/by-nc-nd/4.0/
eu_rights_str_mv openAccess
dc.publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
publisher.none.fl_str_mv Institute of Electrical and Electronics Engineers (IEEE)
dc.source.none.fl_str_mv reponame:Repisalud
instname:Instituto de Salud Carlos III (ISCIII)
instname_str Instituto de Salud Carlos III (ISCIII)
reponame_str Repisalud
collection Repisalud
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869422875048411136
score 15,811543

Similares en LA Referencia