Logo do repositório
 
Publicação

Skin Lesion Classification using Bag-of-3D-Features

2021-02Comunicação em conferência Acesso restrito
Ver registo simples
datacite.subject.fosCiências Naturais::Ciências da Computação e da Informação
datacite.subject.sdg03:Saúde de Qualidade
datacite.subject.sdg10:Reduzir as Desigualdades
datacite.subject.sdg11:Cidades e Comunidades Sustentáveis
dc.contributor.authorPereira, Pedro M. M.
dc.contributor.authorThomaz, Lucas A.
dc.contributor.authorTavora, Luis M. N.
dc.contributor.authorAssuncao, Pedro A. A.
dc.contributor.authorFonseca-Pinto, Rui
dc.contributor.authorPaiva, Rui Pedro
dc.contributor.authorFaria, Sergio M. M.
dc.date.accessioned2026-03-27T10:50:23Z
dc.date.available2026-03-27T10:50:23Z
dc.date.issued2021-02
dc.descriptionEISBN - 978-1-6654-1588-0
dc.descriptionDate of Conference: 11-12 February 2021
dc.description.abstractComputer-aided diagnostic has become a thriving research area in recent years, namely on the identification of skin lesions such as melanoma. This work presents a novel approach to this field by exploiting the 3D characteristics of the skin lesion surface, advancing beyond common features such as, shape, colour, and texture, extracted from dermoscopic RGB images. To this end, a relevant set of features was investigated to obtain 3D skin lesion characteristics from images with depth information. These features were used to train a Bag-of-Features model to distinguish between malignant and benign lesions, also discriminating melanoma from all other lesion types. Despite the large class imbalance, often present in medical image datasets, the feature set achieved a top accuracy of 73.08%, comprising 75.00% sensitivity and 66.67% specificity when classifying between malignant and benign lesions, and 88.46% accuracy (100.00% sensitivity and 86.96% specificity) when discriminating melanoma from all other lesion images, using only depth information. The achieved experimental results indicate the existence of relevant discriminative characteristics in the 3D surface of skin lesions which allow the improvement of existing classification methods based on 2D image characteristics only.eng
dc.description.sponsorshipThis work was supported by the Fundação para a Ciência e a Tecnologia (FCT), Portugal, under PhD Grant SFRH/BD/128669/2017, Programa Operacional Regional do Centro, project PlenoISLA POCI-01-0145-FEDER-028325 and by FCT/MCTES through national funds and when applicable co-funded by EU funds under the project UIDB/EEA/50008/2020.
dc.identifier.citationP. M. M. Pereira et al., "Skin Lesion Classification using Bag-of-3D-Features," 2021 Telecoms Conference (ConfTELE), Leiria, Portugal, 2021, pp. 1-6, doi: https://doi.org/10.1109/ConfTELE50222.2021.9435509.
dc.identifier.doi10.1109/conftele50222.2021.9435509
dc.identifier.isbn978-1-6654-4680-8
dc.identifier.isbn978-1-6654-1588-0
dc.identifier.urihttp://hdl.handle.net/10400.8/16029
dc.language.isoeng
dc.peerreviewedyes
dc.publisherIEEE Canada
dc.relationSkin Lesion Assessment based on Plenoptic Images for Melanoma Classification. Titulo anterior: Texture and Patterns in 3D plenoptic skin lesion assessment: A taxonomy proposal for melanoma classification
dc.relation.hasversionhttps://ieeexplore.ieee.org/document/9435509
dc.relation.ispartof2021 Telecoms Conference (ConfTELE)
dc.rights.uriN/A
dc.subjectMedical Image Analysis
dc.subject3D Features
dc.subjectClassification
dc.subjectMelanoma
dc.subjectSkin Lesion
dc.titleSkin Lesion Classification using Bag-of-3D-Featureseng
dc.typeconference paper
dspace.entity.typePublication
oaire.awardNumberSFRH/BD/128669/2017
oaire.awardTitleSkin Lesion Assessment based on Plenoptic Images for Melanoma Classification. Titulo anterior: Texture and Patterns in 3D plenoptic skin lesion assessment: A taxonomy proposal for melanoma classification
oaire.awardURIhttp://hdl.handle.net/10400.8/14125
oaire.citation.conferenceDate2021-02
oaire.citation.conferencePlaceLeiria, Portugal
oaire.citation.title2021 Telecoms Conference, ConfTELE 2021
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameThomaz
person.familyNamede Oliveira Pegado de Noronha E Távora
person.familyNameAssunção
person.familyNameFonseca-Pinto
person.familyNameFaria
person.givenNameLucas
person.givenNameLuís Miguel
person.givenNamePedro
person.givenNameRui
person.givenNameSergio
person.identifier.ciencia-id121C-FADA-D750
person.identifier.ciencia-id6811-3984-C17B
person.identifier.ciencia-id681D-C547-B184
person.identifier.ciencia-id8815-4101-28DD
person.identifier.orcid0000-0002-1004-7772
person.identifier.orcid0000-0002-8580-1979
person.identifier.orcid0000-0001-9539-8311
person.identifier.orcid0000-0001-6774-5363
person.identifier.orcid0000-0002-0993-9124
person.identifier.ridA-4827-2017
person.identifier.ridK-9449-2014
person.identifier.ridC-5245-2011
person.identifier.scopus-author-id6701838347
person.identifier.scopus-author-id26039086400
person.identifier.scopus-author-id14027853900
relation.isAuthorOfPublication5aaecc29-3e2f-49a6-9fd9-7000d9f6085f
relation.isAuthorOfPublication71940f24-f333-4ab6-abf6-00c7119a07c2
relation.isAuthorOfPublication25649bb9-f135-48e8-8d0f-3706b86701d3
relation.isAuthorOfPublication7eb9d123-1800-4afd-a2f6-91043353011b
relation.isAuthorOfPublicationf69bd4d6-a6ef-4d20-8148-575478909661
relation.isAuthorOfPublication.latestForDiscovery5aaecc29-3e2f-49a6-9fd9-7000d9f6085f
relation.isProjectOfPublication90b7c55a-b84e-4987-821f-cb7eb07499de
relation.isProjectOfPublication.latestForDiscovery90b7c55a-b84e-4987-821f-cb7eb07499de

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
Skin lesion classification using bag-of-3D-features.pdf
Tamanho:
238.6 KB
Formato:
Adobe Portable Document Format
Descrição:
Computer-aided diagnostic has become a thriving research area in recent years, namely on the identification of skin lesions such as melanoma. This work presents a novel approach to this field by exploiting the 3D characteristics of the skin lesion surface, advancing beyond common features such as, shape, colour, and texture, extracted from dermoscopic RGB images. To this end, a relevant set of features was investigated to obtain 3D skin lesion characteristics from images with depth information. These features were used to train a Bag-of-Features model to distinguish between malignant and benign lesions, also discriminating melanoma from all other lesion types. Despite the large class imbalance, often present in medical image datasets, the feature set achieved a top accuracy of 73.08%, comprising 75.00% sensitivity and 66.67% specificity when classifying between malignant and benign lesions, and 88.46% accuracy (100.00% sensitivity and 86.96% specificity) when discriminating melanoma from all other lesion images, using only depth information. The achieved experimental results indicate the existence of relevant discriminative characteristics in the 3D surface of skin lesions which allow the improvement of existing classification methods based on 2D image characteristics only.
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.32 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ESTG - Comunicações em conferências e congressos internacionais