Logo do repositório
 
Publicação

Application of vision transformers in the early detection of excavation in the BRSET base

2024-11-13Artigo científico Acesso aberto
Ver registo simples
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
datacite.subject.sdg11:Cidades e Comunidades Sustentáveis
datacite.subject.sdg16:Paz, Justiça e Instituições Eficazes
dc.contributor.authorFerreira, Joel Santos
dc.contributor.authorFernandes, Miguel M.
dc.contributor.authorLeite, Danilo D. L.
dc.contributor.authorGonzalez, Dibet
dc.contributor.authorGonzalez, Jose Carlos J. C. Raposo da Camara
dc.contributor.authorCunha, António A. C.
dc.contributor.authorRodrigues, Joao
dc.date.accessioned2026-04-07T09:35:52Z
dc.date.available2026-04-07T09:35:52Z
dc.date.issued2024-11-13
dc.description.abstractEnlarged excavation of the optic papilla, caused by the loss of fibres that originate in the retina and transmit electrical stimuli to the visual cortex, is a critical indicator in the early detection of glaucoma, a disease that can lead to irreversible blindness. As the optic papilla shows morphological variations in the population, its identification can be a challenge. Methods based on deep learning have shown promise in helping doctors analyse these images more accurately. Recently, models such as Vision Transformers (ViT) have shown significant results in various medical applications, including glaucoma detection. However, the scarcity of quality data remains a major obstacle to training these models. This study evaluated the performance of the Swin Transformer, DeiT and Linformer models in detecting optic papilla excavation, using the new Brazilian Multilabel Ophthalmological Dataset (BRSET). The results showed that the DeiT model obtained the best accuracy, with 0.94, followed by the Swin Transformer, with 0.88, and the Linformer, with 0.85. The findings of this study suggest that ViT models can not only significantly improve the detection of glaucomatous papillary excavation, but also strengthen Human-Machine Collaboration, promoting more effective interaction between doctors and automated systems in medical diagnosis.eng
dc.description.sponsorshipUIDP/04516/2020; LA/P/0063/2020
dc.identifier.doi10.1145/3696593.3696633
dc.identifier.isbn979-8-4007-0729-2
dc.identifier.urihttp://hdl.handle.net/10400.1/28606
dc.language.isoeng
dc.peerreviewedyes
dc.publisherAssociation for Computing Machinery (ACM)
dc.relationNOVA Laboratory for Computer Science and Informatics
dc.relation.ispartofDSAI '24: Proceedings of the 11th International Conference on Soware Development and Technologies for Enhancing Accessibility and Fighting Info-exclusion
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.subjectDeep learning
dc.subjectBrazilian multilabel ophthalmological dataset
dc.subjectImage classification
dc.subjectOpthalmology
dc.titleApplication of vision transformers in the early detection of excavation in the BRSET baseeng
dc.typejournal article
dspace.entity.typePublication
oaire.awardNumberUIDB/04516/2020
oaire.awardTitleNOVA Laboratory for Computer Science and Informatics
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F04516%2F2020/PT
oaire.citation.conferencePlaceAbu Dhabi, United Arab Emirate
oaire.citation.endPage31
oaire.citation.startPage25
oaire.citation.titleDSAI '24: Proceedings of the 11th International Conference on Soware Development and Technologies for Enhancing Accessibility and Fighting Info-exclusion
oaire.fundingStream6817 - DCRRNI ID
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameRodrigues
person.givenNameJoao
person.identifier.ciencia-id8A19-98F7-9914
person.identifier.orcid0000-0002-3562-6025
person.identifier.scopus-author-id55807461600
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
relation.isAuthorOfPublication683ba85b-459c-4789-a4ff-a4e2a904b295
relation.isAuthorOfPublication.latestForDiscovery683ba85b-459c-4789-a4ff-a4e2a904b295
relation.isProjectOfPublication1122b3d4-9740-4ad7-9abf-86bb7a3615da
relation.isProjectOfPublication.latestForDiscovery1122b3d4-9740-4ad7-9abf-86bb7a3615da

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
3696593.3696633.pdf
Tamanho:
2.81 MB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
3.46 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções