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

被引：23

作者：

Elgafi, Mahmoud ^{[1
]}

Sharafeldeen, Ahmed ^{[2
]}

Elnakib, Ahmed ^{[2
]}

Elgarayhi, Ahmed ^{[1
]}

Alghamdi, Norah S. ^{[3
]}

Sallah, Mohammed ^{[1
,4
]}

El-Baz, Ayman ^{[2
]}

机构：

[1] Mansoura Univ, Fac Sci, Phys Dept, Appl Math Phys Res Grp, Mansoura 35516, Egypt

[2] Univ Louisville, Dept Bioengn, BioImaging Lab, Louisville, KY 40292 USA

[3] Princess Nourah Bint Abdulrahman Univ, Coll Comp & Informat Sci, Dept Comp Sci, Riyadh 11671, Saudi Arabia

[4] Higher Inst Engn & Technol, New Damietta 34517, Egypt

来源：

SENSORS | 2022年 / 22卷 / 20期

关键词：

diabetic retinopathy; neural networks; thickness; OCT; reflectivity; classification; AIDED DIAGNOSIS SYSTEM;

D O I：

10.3390/s22207833

中图分类号：

O65 [分析化学];

学科分类号：

070302 ; 081704 ;

摘要：

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.

引用

页数：13

共 50 条

[21] BIFURCATION DETECTION IN 3D VASCULAR IMAGES USING NOVEL FEATURES AND RANDOM FOREST
Zhao, Mengliu
Hamarneh, Ghassan
2014 IEEE 11TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI), 2014, : 421 - 424
[22] ROC Analysis of Classifiers in Automatic Detection of Diabetic Retinopathy using Shape Features of Fundus Images
Ramani, R. Geetha
Balasubramanian, Lakshmi
Jacob, Shomona Gracia
2013 INTERNATIONAL CONFERENCE ON ADVANCES IN COMPUTING, COMMUNICATIONS AND INFORMATICS (ICACCI), 2013, : 66 - 72
[23] Detection of Early Worsening of Diabetic Retinopathy in Diabetic Pregnant Women Using Oct Angiography
Pomytkina, Natalia
Sorokin, E.
Kolenko, O.
EUROPEAN JOURNAL OF OPHTHALMOLOGY, 2023, 33 (01) : 29 - 30
[24] Detection of hard exudates from diabetic retinopathy images using fuzzy logic
Ranamuka, Nayomi Geethanjali
Meegama, Ravinda Gayan N.
IET IMAGE PROCESSING, 2013, 7 (02) : 121 - 130
[25] 3D surgery for proliferative diabetic retinopathy
Pournaras, J. A.
ACTA OPHTHALMOLOGICA, 2018, 96 : 99 - 99
[26] Identifying Diabetic Retinopathy from OCT Images using Deep Transfer Learning with Artificial Neural Networks
Islam, Kh Tohidul
Wijewickrema, Sudanthi
O'Leary, Stephen
2019 IEEE 32ND INTERNATIONAL SYMPOSIUM ON COMPUTER-BASED MEDICAL SYSTEMS (CBMS), 2019, : 281 - 286
[27] Landmine Detection in 3D Images from Ground Penetrating Radar Using Haar-Like Features
Klesk, Przemyslaw
Godziuk, Andrzej
Kapruziak, Mariusz
Olech, Bogdan
ARTIFICIAL INTELLIGENCE AND SOFT COMPUTING, PT I, 2013, 7894 : 559 - +
[28] Classification of Hanging Garments Using Learned Features Extracted from 3D Point Clouds
Stria, Jan
Hlavac, Vaclav
2018 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2018, : 5307 - 5312
[29] Automatic Detection of Microaneurysms in OCT Images Using Bag of Features
Kazeminasab, Elahe Sadat
Almasi, Ramin
Shoushtarian, Bijan
Golkar, Ehsan
Rabbani, Hossein
COMPUTATIONAL AND MATHEMATICAL METHODS IN MEDICINE, 2022, 2022
[30] LEARNING 3D STRUCTURE FROM 2D IMAGES USING LBP FEATURES
Herrera, Jose L.
del-Blanco, Carlos R.
Garcia, Narciso
2014 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2014, : 2022 - 2025

← 1 2 3 4 5 →