A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images
Retinal disorders are a severe health threat for older adults because they may lead to vision loss and blindness. Diabetic patients are particularly prone to suffer from Diabetic Retinopathy. Identifying relevant structural components in color fundus images like the optic disc (OD) is crucial to dia...
- Autores:
-
Escorcia-Gutierrez, Jose
Torrents-Barrena, Jordina
Gamarra, Margarita
Romero-Aroca, Pedro
Valls, Aida
Puig, Domenec
- Tipo de recurso:
- http://purl.org/coar/resource_type/c_816b
- Fecha de publicación:
- 2021
- Institución:
- Corporación Universidad de la Costa
- Repositorio:
- REDICUC - Repositorio CUC
- Idioma:
- eng
- OAI Identifier:
- oai:repositorio.cuc.edu.co:11323/8083
- Acceso en línea:
- https://hdl.handle.net/11323/8083
https://doi.org/10.1016/j.eswa.2021.114697
https://repositorio.cuc.edu.co/
- Palabra clave:
- Diabetic retinopathy
Optic disc
Color fusión
Markowitz portfolio
Segmentation
- Rights
- openAccess
- License
- CC0 1.0 Universal
id |
RCUC2_729f8eafff1089ac4f1a775b5f17690e |
---|---|
oai_identifier_str |
oai:repositorio.cuc.edu.co:11323/8083 |
network_acronym_str |
RCUC2 |
network_name_str |
REDICUC - Repositorio CUC |
repository_id_str |
|
dc.title.spa.fl_str_mv |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images |
title |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images |
spellingShingle |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images Diabetic retinopathy Optic disc Color fusión Markowitz portfolio Segmentation |
title_short |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images |
title_full |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images |
title_fullStr |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images |
title_full_unstemmed |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images |
title_sort |
A color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images |
dc.creator.fl_str_mv |
Escorcia-Gutierrez, Jose Torrents-Barrena, Jordina Gamarra, Margarita Romero-Aroca, Pedro Valls, Aida Puig, Domenec |
dc.contributor.author.spa.fl_str_mv |
Escorcia-Gutierrez, Jose Torrents-Barrena, Jordina Gamarra, Margarita Romero-Aroca, Pedro Valls, Aida Puig, Domenec |
dc.subject.spa.fl_str_mv |
Diabetic retinopathy Optic disc Color fusión Markowitz portfolio Segmentation |
topic |
Diabetic retinopathy Optic disc Color fusión Markowitz portfolio Segmentation |
description |
Retinal disorders are a severe health threat for older adults because they may lead to vision loss and blindness. Diabetic patients are particularly prone to suffer from Diabetic Retinopathy. Identifying relevant structural components in color fundus images like the optic disc (OD) is crucial to diagnose retinal diseases. Automatic OD detection is complex because of its location in an area where blood vessels converge, and color distribution is uneven. Several image processing techniques have been developed for OD detection so far, but vessel segmentation is sometimes required, increasing computational complexity and time. Moreover, precise OD segmentation methods utilize complex algorithms that need special hardware or extensive labeled datasets. We propose an OD detection approach based on the Modern Portfolio Theory of Markowitz to generate an innovative color fusion model. Specifically, the training phase calculates the optimal weights for each color channel. A fusion of weighted color channels is then applied in the testing phase. This approach acts as a powerful and real-time preprocessing stage. We use four heterogeneous datasets to validate the presented methodology. Three out of four datasets are publicly available (i.e., DRIVE, Messidor, and HRF), and the last corresponds to an in–house dataset acquired from Hospital Universitari Sant Joan de Reus (Spain). Two different segmentation methods are presented and compared with state-of-the-art computer vision techniques to analyze the model performance. An outstanding accuracy and overlap above 0.9 and 80%, respectively, and a minimal execution time of 0.05 s are reached. Therefore, our model could be integrated into daily clinical practice to accelerate the diagnosis of Diabetic Retinopathy due to its simplicity, performance, and speed. |
publishDate |
2021 |
dc.date.accessioned.none.fl_str_mv |
2021-04-07T13:52:18Z |
dc.date.available.none.fl_str_mv |
2021-04-07T13:52:18Z |
dc.date.issued.none.fl_str_mv |
2021-07-15 |
dc.date.embargoEnd.none.fl_str_mv |
2023-07-19 |
dc.type.spa.fl_str_mv |
Pre-Publicación |
dc.type.coar.spa.fl_str_mv |
http://purl.org/coar/resource_type/c_816b |
dc.type.content.spa.fl_str_mv |
Text |
dc.type.driver.spa.fl_str_mv |
info:eu-repo/semantics/preprint |
dc.type.redcol.spa.fl_str_mv |
http://purl.org/redcol/resource_type/ARTOTR |
dc.type.version.spa.fl_str_mv |
info:eu-repo/semantics/acceptedVersion |
format |
http://purl.org/coar/resource_type/c_816b |
status_str |
acceptedVersion |
dc.identifier.issn.spa.fl_str_mv |
0957-4174 |
dc.identifier.uri.spa.fl_str_mv |
https://hdl.handle.net/11323/8083 |
dc.identifier.doi.spa.fl_str_mv |
https://doi.org/10.1016/j.eswa.2021.114697 |
dc.identifier.instname.spa.fl_str_mv |
Corporación Universidad de la Costa |
dc.identifier.reponame.spa.fl_str_mv |
REDICUC - Repositorio CUC |
dc.identifier.repourl.spa.fl_str_mv |
https://repositorio.cuc.edu.co/ |
identifier_str_mv |
0957-4174 Corporación Universidad de la Costa REDICUC - Repositorio CUC |
url |
https://hdl.handle.net/11323/8083 https://doi.org/10.1016/j.eswa.2021.114697 https://repositorio.cuc.edu.co/ |
dc.language.iso.none.fl_str_mv |
eng |
language |
eng |
dc.rights.spa.fl_str_mv |
CC0 1.0 Universal |
dc.rights.uri.spa.fl_str_mv |
http://creativecommons.org/publicdomain/zero/1.0/ |
dc.rights.accessrights.spa.fl_str_mv |
info:eu-repo/semantics/openAccess |
dc.rights.coar.spa.fl_str_mv |
http://purl.org/coar/access_right/c_abf2 |
rights_invalid_str_mv |
CC0 1.0 Universal http://creativecommons.org/publicdomain/zero/1.0/ http://purl.org/coar/access_right/c_abf2 |
eu_rights_str_mv |
openAccess |
dc.format.mimetype.spa.fl_str_mv |
application/pdf |
dc.publisher.spa.fl_str_mv |
Corporación Universidad de la Costa |
dc.source.spa.fl_str_mv |
Expert Systems with Applications |
institution |
Corporación Universidad de la Costa |
dc.source.url.spa.fl_str_mv |
https://www.sciencedirect.com/science/article/abs/pii/S095741742100138X?utm_campaign=STMJ_AUTH_SERV_PUBLISHED&utm_medium=email&utm_acid=148664364&SIS_ID=&dgcid=STMJ_AUTH_SERV_PUBLISHED&CMX_ID=&utm_in=DM129530&utm_source=AC_ |
bitstream.url.fl_str_mv |
https://repositorio.cuc.edu.co/bitstreams/9d3fa9d1-ea78-4494-8422-226204187f11/download https://repositorio.cuc.edu.co/bitstreams/31d87f08-1697-4fdf-9c74-fb99b4942797/download https://repositorio.cuc.edu.co/bitstreams/0c787804-497d-4757-aea3-042af0c83eaa/download https://repositorio.cuc.edu.co/bitstreams/b86a38fc-e711-464d-92e7-3ed15f855399/download https://repositorio.cuc.edu.co/bitstreams/2f40c1c9-baf7-402d-aaec-db33e001de78/download https://repositorio.cuc.edu.co/bitstreams/6ae6a5fc-18dc-435e-9b3c-ec802a2397bf/download |
bitstream.checksum.fl_str_mv |
cde7873459869cd4a52e92b29d7772f6 42fd4ad1e89814f5e4a476b409eb708c e30e9215131d99561d40d6b0abbe9bad 22d37ae58b4fe22e180efe14a7a58bc2 22d37ae58b4fe22e180efe14a7a58bc2 55d9b336c3e7d02b289a69973d0c5ab8 |
bitstream.checksumAlgorithm.fl_str_mv |
MD5 MD5 MD5 MD5 MD5 MD5 |
repository.name.fl_str_mv |
Repositorio de la Universidad de la Costa CUC |
repository.mail.fl_str_mv |
repdigital@cuc.edu.co |
_version_ |
1828166861808730112 |
spelling |
Escorcia-Gutierrez, JoseTorrents-Barrena, JordinaGamarra, MargaritaRomero-Aroca, PedroValls, AidaPuig, Domenec2021-04-07T13:52:18Z2021-04-07T13:52:18Z2021-07-152023-07-190957-4174https://hdl.handle.net/11323/8083https://doi.org/10.1016/j.eswa.2021.114697Corporación Universidad de la CostaREDICUC - Repositorio CUChttps://repositorio.cuc.edu.co/Retinal disorders are a severe health threat for older adults because they may lead to vision loss and blindness. Diabetic patients are particularly prone to suffer from Diabetic Retinopathy. Identifying relevant structural components in color fundus images like the optic disc (OD) is crucial to diagnose retinal diseases. Automatic OD detection is complex because of its location in an area where blood vessels converge, and color distribution is uneven. Several image processing techniques have been developed for OD detection so far, but vessel segmentation is sometimes required, increasing computational complexity and time. Moreover, precise OD segmentation methods utilize complex algorithms that need special hardware or extensive labeled datasets. We propose an OD detection approach based on the Modern Portfolio Theory of Markowitz to generate an innovative color fusion model. Specifically, the training phase calculates the optimal weights for each color channel. A fusion of weighted color channels is then applied in the testing phase. This approach acts as a powerful and real-time preprocessing stage. We use four heterogeneous datasets to validate the presented methodology. Three out of four datasets are publicly available (i.e., DRIVE, Messidor, and HRF), and the last corresponds to an in–house dataset acquired from Hospital Universitari Sant Joan de Reus (Spain). Two different segmentation methods are presented and compared with state-of-the-art computer vision techniques to analyze the model performance. An outstanding accuracy and overlap above 0.9 and 80%, respectively, and a minimal execution time of 0.05 s are reached. Therefore, our model could be integrated into daily clinical practice to accelerate the diagnosis of Diabetic Retinopathy due to its simplicity, performance, and speed.Escorcia-Gutierrez, Jose-will be generated-orcid-0000-0003-0518-3187-600Torrents-Barrena, JordinaGamarra, Margarita-will be generated-orcid-0000-0003-1834-2984-600Romero-Aroca, Pedro-will be generated-orcid-0000-0002-7061-8987-600Valls, Aida-will be generated-orcid-0000-0003-3616-7809-600Puig, Domenec-will be generated-orcid-0000-0002-0562-4205-600application/pdfengCorporación Universidad de la CostaCC0 1.0 Universalhttp://creativecommons.org/publicdomain/zero/1.0/info:eu-repo/semantics/openAccesshttp://purl.org/coar/access_right/c_abf2Expert Systems with Applicationshttps://www.sciencedirect.com/science/article/abs/pii/S095741742100138X?utm_campaign=STMJ_AUTH_SERV_PUBLISHED&utm_medium=email&utm_acid=148664364&SIS_ID=&dgcid=STMJ_AUTH_SERV_PUBLISHED&CMX_ID=&utm_in=DM129530&utm_source=AC_Diabetic retinopathyOptic discColor fusiónMarkowitz portfolioSegmentationA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal imagesPre-Publicaciónhttp://purl.org/coar/resource_type/c_816bTextinfo:eu-repo/semantics/preprinthttp://purl.org/redcol/resource_type/ARTOTRinfo:eu-repo/semantics/acceptedVersionPublicationORIGINALA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdfA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdfapplication/pdf58699https://repositorio.cuc.edu.co/bitstreams/9d3fa9d1-ea78-4494-8422-226204187f11/downloadcde7873459869cd4a52e92b29d7772f6MD51CC-LICENSElicense_rdflicense_rdfapplication/rdf+xml; charset=utf-8701https://repositorio.cuc.edu.co/bitstreams/31d87f08-1697-4fdf-9c74-fb99b4942797/download42fd4ad1e89814f5e4a476b409eb708cMD52LICENSElicense.txtlicense.txttext/plain; charset=utf-83196https://repositorio.cuc.edu.co/bitstreams/0c787804-497d-4757-aea3-042af0c83eaa/downloade30e9215131d99561d40d6b0abbe9badMD53THUMBNAILA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdf.jpgA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdf.jpgimage/jpeg67042https://repositorio.cuc.edu.co/bitstreams/b86a38fc-e711-464d-92e7-3ed15f855399/download22d37ae58b4fe22e180efe14a7a58bc2MD54THUMBNAILA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdf.jpgA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdf.jpgimage/jpeg67042https://repositorio.cuc.edu.co/bitstreams/2f40c1c9-baf7-402d-aaec-db33e001de78/download22d37ae58b4fe22e180efe14a7a58bc2MD54TEXTA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdf.txtA color fusion model based on Markowitz portfolio optimization for optic disc segmentation in retinal images.pdf.txttext/plain2197https://repositorio.cuc.edu.co/bitstreams/6ae6a5fc-18dc-435e-9b3c-ec802a2397bf/download55d9b336c3e7d02b289a69973d0c5ab8MD5511323/8083oai:repositorio.cuc.edu.co:11323/80832024-09-17 14:19:18.438http://creativecommons.org/publicdomain/zero/1.0/CC0 1.0 Universalopen.accesshttps://repositorio.cuc.edu.coRepositorio de la Universidad de la Costa CUCrepdigital@cuc.edu.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 |