Analysis of Diabetic Retinopathy (DR) Based on the Deep Learning

Abdul Muiz Fayyaz; Muhammad Imran Sharif; Sami Azam; Asif Karim; Jamal El-Den

doi:10.3390/info14010030

Analysis of Diabetic Retinopathy (DR) Based on the Deep Learning

Abdul Muiz Fayyaz, Muhammad Imran Sharif, Sami Azam, Asif Karim, Jamal El-Den

Faculty of Science and Technology

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

23 Citations (Scopus)

110 Downloads (Pure)

Abstract

If Diabetic Retinopathy (DR) patients do not receive quick diagnosis and treatment, they may lose vision. DR, an eye disorder caused by high blood glucose, is becoming more prevalent worldwide. Once early warning signs are detected, the severity of the disease must be validated before choosing the best treatment. In this research, a deep learning network is used to automatically detect and classify DR fundus images depending on severity using AlexNet and Resnet101-based feature extraction. Interconnected layers helps to identify the critical features or characteristics; in addition, Ant Colony systems also help choose the characteristics. Passing these chosen attributes through SVM with multiple kernels yielded the final classification model with promising accuracy. The experiment based on 750 features proves that the proposed approach has achieved an accuracy of 93%.

Original language	English
Article number	30
Pages (from-to)	1-14
Number of pages	14
Journal	Information (Switzerland)
Volume	14
Issue number	1
DOIs	https://doi.org/10.3390/info14010030
Publication status	Published - Jan 2023

Bibliographical note

Publisher Copyright:
© 2023 by the authors.

UN SDGs

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

Access to Document

10.3390/info14010030

68852373-oaFinal published version, 2.84 MBLicence: CC BY

Cite this

@article{7664537e7f1d4c189ae0f78c4f3913bc,

title = "Analysis of Diabetic Retinopathy (DR) Based on the Deep Learning",

abstract = "If Diabetic Retinopathy (DR) patients do not receive quick diagnosis and treatment, they may lose vision. DR, an eye disorder caused by high blood glucose, is becoming more prevalent worldwide. Once early warning signs are detected, the severity of the disease must be validated before choosing the best treatment. In this research, a deep learning network is used to automatically detect and classify DR fundus images depending on severity using AlexNet and Resnet101-based feature extraction. Interconnected layers helps to identify the critical features or characteristics; in addition, Ant Colony systems also help choose the characteristics. Passing these chosen attributes through SVM with multiple kernels yielded the final classification model with promising accuracy. The experiment based on 750 features proves that the proposed approach has achieved an accuracy of 93%.",

keywords = "AlexNet, classification, deep learning, diabetic retinopathy, Resnet101",

author = "Fayyaz, {Abdul Muiz} and Sharif, {Muhammad Imran} and Sami Azam and Asif Karim and Jamal El-Den",

note = "Publisher Copyright: {\textcopyright} 2023 by the authors.",

year = "2023",

month = jan,

doi = "10.3390/info14010030",

language = "English",

volume = "14",

pages = "1--14",

journal = "Information (Switzerland)",

issn = "2078-2489",

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

number = "1",

}

TY - JOUR

T1 - Analysis of Diabetic Retinopathy (DR) Based on the Deep Learning

AU - Fayyaz, Abdul Muiz

AU - Sharif, Muhammad Imran

AU - Azam, Sami

AU - Karim, Asif

AU - El-Den, Jamal

PY - 2023/1

Y1 - 2023/1

N2 - If Diabetic Retinopathy (DR) patients do not receive quick diagnosis and treatment, they may lose vision. DR, an eye disorder caused by high blood glucose, is becoming more prevalent worldwide. Once early warning signs are detected, the severity of the disease must be validated before choosing the best treatment. In this research, a deep learning network is used to automatically detect and classify DR fundus images depending on severity using AlexNet and Resnet101-based feature extraction. Interconnected layers helps to identify the critical features or characteristics; in addition, Ant Colony systems also help choose the characteristics. Passing these chosen attributes through SVM with multiple kernels yielded the final classification model with promising accuracy. The experiment based on 750 features proves that the proposed approach has achieved an accuracy of 93%.

AB - If Diabetic Retinopathy (DR) patients do not receive quick diagnosis and treatment, they may lose vision. DR, an eye disorder caused by high blood glucose, is becoming more prevalent worldwide. Once early warning signs are detected, the severity of the disease must be validated before choosing the best treatment. In this research, a deep learning network is used to automatically detect and classify DR fundus images depending on severity using AlexNet and Resnet101-based feature extraction. Interconnected layers helps to identify the critical features or characteristics; in addition, Ant Colony systems also help choose the characteristics. Passing these chosen attributes through SVM with multiple kernels yielded the final classification model with promising accuracy. The experiment based on 750 features proves that the proposed approach has achieved an accuracy of 93%.

KW - AlexNet

KW - classification

KW - deep learning

KW - diabetic retinopathy

KW - Resnet101

UR - http://www.scopus.com/inward/record.url?scp=85146650896&partnerID=8YFLogxK

U2 - 10.3390/info14010030

DO - 10.3390/info14010030

M3 - Article

AN - SCOPUS:85146650896

SN - 2078-2489

VL - 14

SP - 1

EP - 14

JO - Information (Switzerland)

JF - Information (Switzerland)

IS - 1

M1 - 30

ER -

Analysis of Diabetic Retinopathy (DR) Based on the Deep Learning

Abstract

Bibliographical note

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this