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

Mahmoud Elgafi; Ahmed Sharafeldeen; Ahmed Elnakib; Ahmed Elgarayhi; Norah S. Alghamdi; Mohammed Sallah; Ayman El-Baz

doi:10.3390/s22207833

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

Mahmoud Elgafi
, Ahmed Sharafeldeen
, Ahmed Elnakib
, Ahmed Elgarayhi
, Norah S. Alghamdi
, Mohammed Sallah
, Ayman El-Baz

School of Engineering (Behrend)

Research output: Contribution to journal › Article › peer-review

37 Scopus citations

Abstract

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.

Original language	English (US)
Article number	7833
Journal	Sensors
Volume	22
Issue number	20
DOIs	https://doi.org/10.3390/s22207833
State	Published - Oct 2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

All Science Journal Classification (ASJC) codes

Analytical Chemistry
Information Systems
Atomic and Molecular Physics, and Optics
Biochemistry
Instrumentation
Electrical and Electronic Engineering

Access to Document

10.3390/s22207833

Cite this

@article{4fb84b813eb042e88b0c1579797420b5,

title = "Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images",

abstract = "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.",

author = "Mahmoud Elgafi and Ahmed Sharafeldeen and Ahmed Elnakib and Ahmed Elgarayhi and Alghamdi, \{Norah S.\} and Mohammed Sallah and Ayman El-Baz",

note = "Publisher Copyright: {\textcopyright} 2022 by the authors.",

year = "2022",

month = oct,

doi = "10.3390/s22207833",

language = "English (US)",

volume = "22",

journal = "Sensors",

issn = "1424-8220",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "20",

}

TY - JOUR

T1 - Detection of Diabetic Retinopathy Using Extracted 3D Features from OCT Images

AU - Elgafi, Mahmoud

AU - Sharafeldeen, Ahmed

AU - Elnakib, Ahmed

AU - Elgarayhi, Ahmed

AU - Alghamdi, Norah S.

AU - Sallah, Mohammed

AU - El-Baz, Ayman

PY - 2022/10

Y1 - 2022/10

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/85140657439

UR - https://www.scopus.com/pages/publications/85140657439#tab=citedBy

U2 - 10.3390/s22207833

DO - 10.3390/s22207833

M3 - Article

C2 - 36298186

AN - SCOPUS:85140657439

SN - 1424-8220

VL - 22

JO - Sensors

JF - Sensors

IS - 20

M1 - 7833

ER -

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

Abstract

UN SDGs

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this