A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.3390/bioengineering9080369 http://hdl.handle.net/11449/241615 |
Resumo: | In 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. |
id |
UNSP_a3ff07622847e197c8c9937895896d20 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/241615 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registrationcomputer vision applicationsdeep learningfundus imageimage registrationIn 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.Faculty of Science and Technology (FCT) São Paulo State University (UNESP)Institute of Mathematics and Computer Science (ICMC) São Paulo University (USP)Science and Technology Institute (ICT) São Paulo State University (UNESP)Institute of Biosciences Letters and Exact Sciences (IBILCE) São Paulo State University (UNESP)Faculty of Science and Technology (FCT) São Paulo State University (UNESP)Science and Technology Institute (ICT) São Paulo State University (UNESP)Institute of Biosciences Letters and Exact Sciences (IBILCE) São Paulo State University (UNESP)Universidade Estadual Paulista (UNESP)Universidade de São Paulo (USP)Benvenuto, Giovana A. [UNESP]Colnago, MarilaineDias, Maurício A. [UNESP]Negri, Rogério G. [UNESP]Silva, Erivaldo A. [UNESP]Casaca, Wallace [UNESP]2023-03-01T21:13:09Z2023-03-01T21:13:09Z2022-08-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://dx.doi.org/10.3390/bioengineering9080369Bioengineering, v. 9, n. 8, 2022.2306-5354http://hdl.handle.net/11449/24161510.3390/bioengineering90803692-s2.0-85137360100Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengBioengineeringinfo:eu-repo/semantics/openAccess2024-06-18T18:17:56Zoai:repositorio.unesp.br:11449/241615Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-05T16:26:04.741674Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration |
title |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration |
spellingShingle |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration Benvenuto, Giovana A. [UNESP] computer vision applications deep learning fundus image image registration |
title_short |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration |
title_full |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration |
title_fullStr |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration |
title_full_unstemmed |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration |
title_sort |
A Fully Unsupervised Deep Learning Framework for Non-Rigid Fundus Image Registration |
author |
Benvenuto, Giovana A. [UNESP] |
author_facet |
Benvenuto, Giovana A. [UNESP] Colnago, Marilaine Dias, Maurício A. [UNESP] Negri, Rogério G. [UNESP] Silva, Erivaldo A. [UNESP] Casaca, Wallace [UNESP] |
author_role |
author |
author2 |
Colnago, Marilaine Dias, Maurício A. [UNESP] Negri, Rogério G. [UNESP] Silva, Erivaldo A. [UNESP] Casaca, Wallace [UNESP] |
author2_role |
author author author author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) Universidade de São Paulo (USP) |
dc.contributor.author.fl_str_mv |
Benvenuto, Giovana A. [UNESP] Colnago, Marilaine Dias, Maurício A. [UNESP] Negri, Rogério G. [UNESP] Silva, Erivaldo A. [UNESP] Casaca, Wallace [UNESP] |
dc.subject.por.fl_str_mv |
computer vision applications deep learning fundus image image registration |
topic |
computer vision applications deep learning fundus image image registration |
description |
In 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. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-08-01 2023-03-01T21:13:09Z 2023-03-01T21:13:09Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.3390/bioengineering9080369 Bioengineering, v. 9, n. 8, 2022. 2306-5354 http://hdl.handle.net/11449/241615 10.3390/bioengineering9080369 2-s2.0-85137360100 |
url |
http://dx.doi.org/10.3390/bioengineering9080369 http://hdl.handle.net/11449/241615 |
identifier_str_mv |
Bioengineering, v. 9, n. 8, 2022. 2306-5354 10.3390/bioengineering9080369 2-s2.0-85137360100 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Bioengineering |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808128650817568768 |