Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning
Autor(a) principal: | |
---|---|
Data de Publicação: | 2021 |
Outros Autores: | , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
Texto Completo: | http://hdl.handle.net/10316/100877 https://doi.org/10.1109/ACCESS.2021.3095655 |
Resumo: | Epiretinal membrane (ERM) is an eye disease that affects 7% of the world population, with a higher incidence in people over 75 years old. If left untreated, it can lead to complications in the central vision, resulting in severe vision loss. Early detection is important for progress follow-up, treatment monitoring, and to avoid total vision loss. Optical coherence tomography, a non-invasive retina imaging technique, can be used for effective detection and monitoring of this condition. To date, automatic methods to detect ERM have received little attention in the research literature. This article describes the application of deep learning to the automatic detection of ERM. The proposed solution is based on four widely used convolutional neural network architectures adapted to the task using transfer learning, and ne-tuned with a proprietary dataset. The architectures were specialized by optimizing the network hyperparameters and two loss functions, cross-entropy and focal loss.Adetailed description of the methods is provided, complemented with an exhaustive evaluation of their performance. Overall, the methods reached an accuracy of 99.7%, with sensitivity and speci city of 99.47% and 99.93%, respectively. The results showed that transfer learning enabled a successful use of deep learning to detect ERM in optical coherence tomography retinal images, even when only relatively small training datasets are available. |
id |
RCAP_f23d2af4170b8fb8654d56f8d1520f95 |
---|---|
oai_identifier_str |
oai:estudogeral.uc.pt:10316/100877 |
network_acronym_str |
RCAP |
network_name_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository_id_str |
7160 |
spelling |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep LearningArtificial intelligencedeep learningepiretinal membranemacular pukerneural networksoptical coherence tomographytransfer learningEpiretinal membrane (ERM) is an eye disease that affects 7% of the world population, with a higher incidence in people over 75 years old. If left untreated, it can lead to complications in the central vision, resulting in severe vision loss. Early detection is important for progress follow-up, treatment monitoring, and to avoid total vision loss. Optical coherence tomography, a non-invasive retina imaging technique, can be used for effective detection and monitoring of this condition. To date, automatic methods to detect ERM have received little attention in the research literature. This article describes the application of deep learning to the automatic detection of ERM. The proposed solution is based on four widely used convolutional neural network architectures adapted to the task using transfer learning, and ne-tuned with a proprietary dataset. The architectures were specialized by optimizing the network hyperparameters and two loss functions, cross-entropy and focal loss.Adetailed description of the methods is provided, complemented with an exhaustive evaluation of their performance. Overall, the methods reached an accuracy of 99.7%, with sensitivity and speci city of 99.47% and 99.93%, respectively. The results showed that transfer learning enabled a successful use of deep learning to detect ERM in optical coherence tomography retinal images, even when only relatively small training datasets are available.2021info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://hdl.handle.net/10316/100877http://hdl.handle.net/10316/100877https://doi.org/10.1109/ACCESS.2021.3095655eng2169-3536Parra-Mora, EstherCazañas-Gordón, AlexProença, Ruida Silva Cruz, Luis A.info:eu-repo/semantics/openAccessreponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãoinstacron:RCAAP2022-07-18T20:38:11Zoai:estudogeral.uc.pt:10316/100877Portal AgregadorONGhttps://www.rcaap.pt/oai/openaireopendoar:71602024-03-19T21:18:10.372134Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informaçãofalse |
dc.title.none.fl_str_mv |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning |
title |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning |
spellingShingle |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning Parra-Mora, Esther Artificial intelligence deep learning epiretinal membrane macular puker neural networks optical coherence tomography transfer learning |
title_short |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning |
title_full |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning |
title_fullStr |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning |
title_full_unstemmed |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning |
title_sort |
Epiretinal Membrane Detection in Optical Coherence Tomography Retinal Images Using Deep Learning |
author |
Parra-Mora, Esther |
author_facet |
Parra-Mora, Esther Cazañas-Gordón, Alex Proença, Rui da Silva Cruz, Luis A. |
author_role |
author |
author2 |
Cazañas-Gordón, Alex Proença, Rui da Silva Cruz, Luis A. |
author2_role |
author author author |
dc.contributor.author.fl_str_mv |
Parra-Mora, Esther Cazañas-Gordón, Alex Proença, Rui da Silva Cruz, Luis A. |
dc.subject.por.fl_str_mv |
Artificial intelligence deep learning epiretinal membrane macular puker neural networks optical coherence tomography transfer learning |
topic |
Artificial intelligence deep learning epiretinal membrane macular puker neural networks optical coherence tomography transfer learning |
description |
Epiretinal membrane (ERM) is an eye disease that affects 7% of the world population, with a higher incidence in people over 75 years old. If left untreated, it can lead to complications in the central vision, resulting in severe vision loss. Early detection is important for progress follow-up, treatment monitoring, and to avoid total vision loss. Optical coherence tomography, a non-invasive retina imaging technique, can be used for effective detection and monitoring of this condition. To date, automatic methods to detect ERM have received little attention in the research literature. This article describes the application of deep learning to the automatic detection of ERM. The proposed solution is based on four widely used convolutional neural network architectures adapted to the task using transfer learning, and ne-tuned with a proprietary dataset. The architectures were specialized by optimizing the network hyperparameters and two loss functions, cross-entropy and focal loss.Adetailed description of the methods is provided, complemented with an exhaustive evaluation of their performance. Overall, the methods reached an accuracy of 99.7%, with sensitivity and speci city of 99.47% and 99.93%, respectively. The results showed that transfer learning enabled a successful use of deep learning to detect ERM in optical coherence tomography retinal images, even when only relatively small training datasets are available. |
publishDate |
2021 |
dc.date.none.fl_str_mv |
2021 |
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://hdl.handle.net/10316/100877 http://hdl.handle.net/10316/100877 https://doi.org/10.1109/ACCESS.2021.3095655 |
url |
http://hdl.handle.net/10316/100877 https://doi.org/10.1109/ACCESS.2021.3095655 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
2169-3536 |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.source.none.fl_str_mv |
reponame:Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) instname:Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação instacron:RCAAP |
instname_str |
Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
instacron_str |
RCAAP |
institution |
RCAAP |
reponame_str |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
collection |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) |
repository.name.fl_str_mv |
Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos) - Agência para a Sociedade do Conhecimento (UMIC) - FCT - Sociedade da Informação |
repository.mail.fl_str_mv |
|
_version_ |
1799134076875046912 |