Publicação
Diabetic retinopathy grading using blended deep learning
| datacite.subject.fos | Engenharia e Tecnologia | |
| dc.contributor.author | Monteiro, Fernando C. | |
| dc.date.accessioned | 2026-05-18T14:26:05Z | |
| dc.date.available | 2026-05-18T14:26:05Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Diabetic retinopathy is a complication of diabetes that is mainly caused by the damage of the blood vessels located in the retina. Retinal screening contributes to early detection and treatment of diabetic retinopathy. DR has five stages, namely healthy, mild, moderate, severe and proliferative diabetic retinopathy. Computer-aided diagnosis approaches are needed to allow an early detection and treatment. Several automated deep learning (DL) based approaches have been proven to be a powerful tool for DR grading. However, these approaches are usually based on one DL architecture only which could produce over-fitted results. Another identified problem is the use of imbalanced datasets. In this paper, we proposed a blended deep learning approach obtained by training several individual DL models, using a 5-fold cross-validation technique and combining their predictions in a final score. This blended model highlights each individual model where it performs best and discredits where it performs poorly, increasing the robustness of the results. The experiments were conducted on a balanced DDR dataset containing 33310 retina fundus images equally distributed for the DR grades. An explainability algorithm was also used to show the efficiency of the proposed approach in detecting DR signs. | eng |
| dc.description.sponsorship | The authors are grateful to the Foundation for Science and Technology (FCT, Portugal) for financial support through national funds FCT/MCTES (PIDDAC) to CeDRI (UIDB/05757/2020 and UIDP/05757/2020) and SusTEC (LA/P/0007/2021). | |
| dc.identifier.citation | Monteiro, Fernando C. (2023). Diabetic retinopathy grading using blended deep learning. In International Conference on ENTERprise Information Systems and Technologies. 219, p. 1097-1104. ISBN 978-989-54617-4-5. DOI: 10.1016/j.procs.2023.01.389 | |
| dc.identifier.doi | 10.1016/j.procs.2023.01.389 | |
| dc.identifier.isbn | 978-989-54617-4-5 | |
| dc.identifier.uri | http://hdl.handle.net/10198/36710 | |
| dc.language.iso | eng | |
| dc.peerreviewed | yes | |
| dc.publisher | SciKA | |
| dc.relation | Research Centre in Digitalization and Intelligent Robotics | |
| dc.relation | NEXTGENmOCp: Next generation of a microfluidic Organ-on-a-Chip platform (mOCp) to assess and diagnosis therapeutic effects of innovative nanomedicines | |
| dc.relation | /05757/2020 | |
| dc.relation.hasversion | https://www.scika.org/centeris/2022/CONTENTS/downloads/boa2022.pdf | |
| dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | |
| dc.title | Diabetic retinopathy grading using blended deep learning | eng |
| dc.type | conference paper | |
| dspace.entity.type | Publication | |
| oaire.awardNumber | UIDB/05757/2020 | |
| oaire.awardNumber | 2021.00027.CEECIND/CP1664/CT0007 | |
| oaire.awardTitle | Research Centre in Digitalization and Intelligent Robotics | |
| oaire.awardTitle | NEXTGENmOCp: Next generation of a microfluidic Organ-on-a-Chip platform (mOCp) to assess and diagnosis therapeutic effects of innovative nanomedicines | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/6817 - DCRRNI ID/UIDB%2F05757%2F2020/PT | |
| oaire.awardURI | info:eu-repo/grantAgreement/FCT/CEEC IND4ed/2021.00027.CEECIND%2FCP1664%2FCT0007/PT | |
| oaire.citation.conferenceDate | 2022 | |
| oaire.citation.conferencePlace | Lisboa, Portugal | |
| oaire.citation.endPage | 1104 | |
| oaire.citation.startPage | 1097 | |
| oaire.citation.title | International Conference on Health and Social Care Information Systems and Technologies | |
| oaire.citation.volume | 219 | |
| oaire.fundingStream | 6817 - DCRRNI ID | |
| oaire.fundingStream | CEEC IND4ed | |
| oaire.version | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |
| person.familyName | Monteiro | |
| person.givenName | Fernando C. | |
| person.identifier.ciencia-id | 2019-BDBF-10E2 | |
| person.identifier.orcid | 0000-0002-1421-8006 | |
| person.identifier.rid | H-9213-2016 | |
| person.identifier.scopus-author-id | 8986162600 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.identifier | http://doi.org/10.13039/501100001871 | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| project.funder.name | Fundação para a Ciência e a Tecnologia | |
| relation.isAuthorOfPublication | 363b6c37-282c-4cd6-bb54-3c97cc700d78 | |
| relation.isAuthorOfPublication.latestForDiscovery | 363b6c37-282c-4cd6-bb54-3c97cc700d78 | |
| relation.isProjectOfPublication | 6e01ddc8-6a82-4131-bca6-84789fa234bd | |
| relation.isProjectOfPublication | 4669ae00-038b-4dc0-9d76-8cf5f4c11de2 | |
| relation.isProjectOfPublication.latestForDiscovery | 6e01ddc8-6a82-4131-bca6-84789fa234bd |