Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images

Diabetic retinopathy (DR) is a major health problem that can lead to vision loss if not treated early. In this study, a three-step system for DR detection utilizing optical coherence tomography (OCT) is presented. First, the proposed system segments the retinal layers from the input OCT images. Seco...

Descripción completa

Detalles Bibliográficos
Autores principales: Elgafi, Mahmoud, Sharafeldeen, Ahmed, Elnakib, Ahmed, Elgarayhi, Ahmed, Alghamdi, Norah S., Sallah, Mohammed, El-Baz, Ayman
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9610651/
https://www.ncbi.nlm.nih.gov/pubmed/36298186
http://dx.doi.org/10.3390/s22207833
_version_ 1784819329184825344
author Elgafi, Mahmoud
Sharafeldeen, Ahmed
Elnakib, Ahmed
Elgarayhi, Ahmed
Alghamdi, Norah S.
Sallah, Mohammed
El-Baz, Ayman
author_facet Elgafi, Mahmoud
Sharafeldeen, Ahmed
Elnakib, Ahmed
Elgarayhi, Ahmed
Alghamdi, Norah S.
Sallah, Mohammed
El-Baz, Ayman
author_sort Elgafi, Mahmoud
collection PubMed
description Diabetic retinopathy (DR) is a major health problem that can lead to vision loss if not treated early. In this study, a three-step system for DR detection utilizing optical coherence tomography (OCT) is presented. First, the proposed system segments the retinal layers from the input OCT images. Second, 3D features are extracted from each retinal layer that include the first-order reflectivity and the 3D thickness of the individual OCT layers. Finally, backpropagation neural networks are used to classify OCT images. Experimental studies on 188 cases confirm the advantages of the proposed system over related methods, achieving an accuracy of 96.81%, using the leave-one-subject-out (LOSO) cross-validation. These outcomes show the potential of the suggested method for DR detection using OCT images.
format Online
Article
Text
id pubmed-9610651
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-96106512022-10-28 Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images Elgafi, Mahmoud Sharafeldeen, Ahmed Elnakib, Ahmed Elgarayhi, Ahmed Alghamdi, Norah S. Sallah, Mohammed El-Baz, Ayman Sensors (Basel) Article Diabetic retinopathy (DR) is a major health problem that can lead to vision loss if not treated early. In this study, a three-step system for DR detection utilizing optical coherence tomography (OCT) is presented. First, the proposed system segments the retinal layers from the input OCT images. Second, 3D features are extracted from each retinal layer that include the first-order reflectivity and the 3D thickness of the individual OCT layers. Finally, backpropagation neural networks are used to classify OCT images. Experimental studies on 188 cases confirm the advantages of the proposed system over related methods, achieving an accuracy of 96.81%, using the leave-one-subject-out (LOSO) cross-validation. These outcomes show the potential of the suggested method for DR detection using OCT images. MDPI 2022-10-15 /pmc/articles/PMC9610651/ /pubmed/36298186 http://dx.doi.org/10.3390/s22207833 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Elgafi, Mahmoud
Sharafeldeen, Ahmed
Elnakib, Ahmed
Elgarayhi, Ahmed
Alghamdi, Norah S.
Sallah, Mohammed
El-Baz, Ayman
Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images
title Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images
title_full Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images
title_fullStr Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images
title_full_unstemmed Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images
title_short Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images
title_sort detection of diabetic retinopathy using extracted 3d features from oct images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9610651/
https://www.ncbi.nlm.nih.gov/pubmed/36298186
http://dx.doi.org/10.3390/s22207833
work_keys_str_mv AT elgafimahmoud detectionofdiabeticretinopathyusingextracted3dfeaturesfromoctimages
AT sharafeldeenahmed detectionofdiabeticretinopathyusingextracted3dfeaturesfromoctimages
AT elnakibahmed detectionofdiabeticretinopathyusingextracted3dfeaturesfromoctimages
AT elgarayhiahmed detectionofdiabeticretinopathyusingextracted3dfeaturesfromoctimages
AT alghamdinorahs detectionofdiabeticretinopathyusingextracted3dfeaturesfromoctimages
AT sallahmohammed detectionofdiabeticretinopathyusingextracted3dfeaturesfromoctimages
AT elbazayman detectionofdiabeticretinopathyusingextracted3dfeaturesfromoctimages

Ejemplares similares