A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration

Registro completo de metadados
MetadadosDescriçãoIdioma
Autor(es): dc.contributorUniversidade Estadual Paulista (UNESP)-
Autor(es): dc.contributorUniversidade de São Paulo (USP)-
Autor(es): dc.creatorBenvenuto, Giovana A.-
Autor(es): dc.creatorColnago, Marilaine-
Autor(es): dc.creatorDias, Maurício A.-
Autor(es): dc.creatorNegri, Rogério G.-
Autor(es): dc.creatorSilva, Erivaldo A.-
Autor(es): dc.creatorCasaca, Wallace-
Data de aceite: dc.date.accessioned2025-08-21T17:12:35Z-
Data de disponibilização: dc.date.available2025-08-21T17:12:35Z-
Data de envio: dc.date.issued2023-03-01-
Data de envio: dc.date.issued2023-03-01-
Data de envio: dc.date.issued2022-08-01-
Fonte completa do material: dc.identifierhttp://dx.doi.org/10.3390/bioengineering9080369-
Fonte completa do material: dc.identifierhttp://hdl.handle.net/11449/241615-
Fonte: dc.identifier.urihttp://educapes.capes.gov.br/handle/11449/241615-
Descrição: dc.descriptionIn ophthalmology, the registration problem consists of finding a geometric transformation that aligns a pair of images, supporting eye-care specialists who need to record and compare images of the same patient. Considering the registration methods for handling eye fundus images, the literature offers only a limited number of proposals based on deep learning (DL), whose implementations use the supervised learning paradigm to train a model. Additionally, ensuring high-quality registrations while still being flexible enough to tackle a broad range of fundus images is another drawback faced by most existing methods in the literature. Therefore, in this paper, we address the above-mentioned issues by introducing a new DL-based framework for eye fundus registration. Our methodology combines a U-shaped fully convolutional neural network with a spatial transformation learning scheme, where a reference-free similarity metric allows the registration without assuming any pre-annotated or artificially created data. Once trained, the model is able to accurately align pairs of images captured under several conditions, which include the presence of anatomical differences and low-quality photographs. Compared to other registration methods, our approach achieves better registration outcomes by just passing as input the desired pair of fundus images.-
Descrição: dc.descriptionFaculty of Science and Technology (FCT) São Paulo State University (UNESP)-
Descrição: dc.descriptionInstitute of Mathematics and Computer Science (ICMC) São Paulo University (USP)-
Descrição: dc.descriptionScience and Technology Institute (ICT) São Paulo State University (UNESP)-
Descrição: dc.descriptionInstitute of Biosciences Letters and Exact Sciences (IBILCE) São Paulo State University (UNESP)-
Descrição: dc.descriptionFaculty of Science and Technology (FCT) São Paulo State University (UNESP)-
Descrição: dc.descriptionScience and Technology Institute (ICT) São Paulo State University (UNESP)-
Descrição: dc.descriptionInstitute of Biosciences Letters and Exact Sciences (IBILCE) São Paulo State University (UNESP)-
Idioma: dc.languageen-
Relação: dc.relationBioengineering-
???dc.source???: dc.sourceScopus-
Palavras-chave: dc.subjectcomputer vision applications-
Palavras-chave: dc.subjectdeep learning-
Palavras-chave: dc.subjectfundus image-
Palavras-chave: dc.subjectimage registration-
Título: dc.titleA Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration-
Tipo de arquivo: dc.typelivro digital-
Aparece nas coleções:Repositório Institucional - Unesp

Não existem arquivos associados a este item.