Repository logo
 
Publication

Dermoscopic skin lesion image segmentation based on Local Binary Pattern Clustering: Comparative study

2020-05Journal article Open access
Simple item page
datacite.subject.fosCiências Naturais::Ciências da Computação e da Informação
datacite.subject.fosCiências Médicas::Outras Ciências Médicas
datacite.subject.fosEngenharia e Tecnologia::Engenharia Médica
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.authorFonseca-Pinto, Rui
dc.contributor.authorPaiva, Rui Pedro
dc.contributor.authorAssuncao, Pedro A. A.
dc.contributor.authorTavora, Luis M. N.
dc.contributor.authorThomaz, Lucas A.
dc.contributor.authorFaria, Sergio M. M.
dc.date.accessioned2025-09-25T15:46:33Z
dc.date.available2025-09-25T15:46:33Z
dc.date.issued2020-05
dc.description.abstractAccurate skin lesion segmentation is important for identification and classification through computational methods. However, when performed by dermatologists, the results of clinical segmentation are affected by a certain margin of inaccuracy (which exists since dermatologist do not delineate lesions for segmentation but for extraction) and also significant inter- and intra-individual variability, such segmentation is not sufficiently accurate for segmentation studies. This work addresses these limitations to enable detailed analysis of lesions’ geometry along with extraction of non-linear characteristics of region-of-interest border lines. A comprehensive review of 39 segmentation methods is carried out and a contribution to improve dermoscopic image segmentation is presented to determine the regions-of-interest of skin lesions, through accurate border lines with fine geometric details. This approach resorts to Local Binary Patterns and k-means clustering for precise identification of lesions boundaries, particularly the melanocytic. A comparative evaluation study is carried out using three different datasets and reviewed algorithms are grouped according to their approach. Results show that algorithms from the same group tend to perform similarly. Nevertheless, their performance does not depend uniquely on the algorithm itself but also on the underlying dataset characteristics. Throughout several evaluations, the proposed Local Binary Patterns method presents, consistently, better average performance than the current state-of-the-art techniques across the three different datasets without the need of training or supervised learning steps. Overall, apart from presenting a new segmentation method capable of outperforming the current state-of-the-art, this paper provides insightful information about the behaviour and performance of different image segmentation algorithms.eng
dc.description.sponsorshipThis work was supported by Programa Operacional Regional do Centro, project PlenoISLA POCI-01-0145-FEDER-28325, and funded by FCT/MCTES, under PhD Grant SFRH/BD/128669/2017, through national funds and when applicable co-funded by EU funds under the Instituto de Telecomunicacoes project UIDB/EEA/50008/2020.
dc.identifier.citationPedro M.M. Pereira, Rui Fonseca-Pinto, Rui Pedro Paiva, Pedro A.A. Assuncao, Luis M.N. Tavora, Lucas A. Thomaz, Sergio M.M. Faria, Dermoscopic skin lesion image segmentation based on Local Binary Pattern Clustering: Comparative study, Biomedical Signal Processing and Control, Volume 59, 2020, 101924, ISSN 1746-8094, https://doi.org/10.1016/j.bspc.2020.101924.
dc.identifier.doi10.1016/j.bspc.2020.101924
dc.identifier.eissn1746-8108
dc.identifier.issn1746-8094
dc.identifier.urihttp://hdl.handle.net/10400.8/14128
dc.language.isoeng
dc.peerreviewedyes
dc.publisherElsevier
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://www.sciencedirect.com/science/article/pii/S174680942030080X?via%3Dihub
dc.relation.ispartofBiomedical Signal Processing and Control
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectSkin lesion
dc.subjectSegmentation
dc.subjectMedical image analysis
dc.subjectDermoscopy
dc.titleDermoscopic skin lesion image segmentation based on Local Binary Pattern Clustering: Comparative studyeng
dc.typejournal article
dspace.entity.typePublication
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.endPage12
oaire.citation.startPage1
oaire.citation.titleBiomedical Signal Processing and Control
oaire.citation.volume59
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameFonseca-Pinto
person.familyNameAssunção
person.familyNamede Oliveira Pegado de Noronha E Távora
person.familyNameThomaz
person.familyNameFaria
person.givenNameRui
person.givenNamePedro
person.givenNameLuís Miguel
person.givenNameLucas
person.givenNameSergio
person.identifier.ciencia-id681D-C547-B184
person.identifier.ciencia-id6811-3984-C17B
person.identifier.ciencia-id121C-FADA-D750
person.identifier.ciencia-id8815-4101-28DD
person.identifier.orcid0000-0001-6774-5363
person.identifier.orcid0000-0001-9539-8311
person.identifier.orcid0000-0002-8580-1979
person.identifier.orcid0000-0002-1004-7772
person.identifier.orcid0000-0002-0993-9124
person.identifier.ridK-9449-2014
person.identifier.ridA-4827-2017
person.identifier.ridC-5245-2011
person.identifier.scopus-author-id26039086400
person.identifier.scopus-author-id6701838347
person.identifier.scopus-author-id14027853900
relation.isAuthorOfPublication7eb9d123-1800-4afd-a2f6-91043353011b
relation.isAuthorOfPublication25649bb9-f135-48e8-8d0f-3706b86701d3
relation.isAuthorOfPublication71940f24-f333-4ab6-abf6-00c7119a07c2
relation.isAuthorOfPublication5aaecc29-3e2f-49a6-9fd9-7000d9f6085f
relation.isAuthorOfPublicationf69bd4d6-a6ef-4d20-8148-575478909661
relation.isAuthorOfPublication.latestForDiscovery7eb9d123-1800-4afd-a2f6-91043353011b
relation.isProjectOfPublication90b7c55a-b84e-4987-821f-cb7eb07499de
relation.isProjectOfPublication.latestForDiscovery90b7c55a-b84e-4987-821f-cb7eb07499de

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Dermoscopic skin lesion image segmentation based on Local Binary Pattern Clustering Comparative study.pdf
Size:
1.35 MB
Format:
Adobe Portable Document Format
Description:
Accurate skin lesion segmentation is important for identification and classification through computational methods. However, when performed by dermatologists, the results of clinical segmentation are affected by a certain margin of inaccuracy (which exists since dermatologist do not delineate lesions for segmentation but for extraction) and also significant inter- and intra-individual variability, such segmentation is not sufficiently accurate for segmentation studies. This work addresses these limitations to enable detailed analysis of lesions’ geometry along with extraction of non-linear characteristics of region-of-interest border lines. A comprehensive review of 39 segmentation methods is carried out and a contribution to improve dermoscopic image segmentation is presented to determine the regions-of-interest of skin lesions, through accurate border lines with fine geometric details. This approach resorts to Local Binary Patterns and k-means clustering for precise identification of lesions boundaries, particularly the melanocytic. A comparative evaluation study is carried out using three different datasets and reviewed algorithms are grouped according to their approach. Results show that algorithms from the same group tend to perform similarly. Nevertheless, their performance does not depend uniquely on the algorithm itself but also on the underlying dataset characteristics. Throughout several evaluations, the proposed Local Binary Patterns method presents, consistently, better average performance than the current state-of-the-art techniques across the three different datasets without the need of training or supervised learning steps. Overall, apart from presenting a new segmentation method capable of outperforming the current state-of-the-art, this paper provides insightful information about the behaviour and performance of different image segmentation algorithms.
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.32 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ESTG - Artigos em revistas internacionais