Home/International Journal of Computer Engineering and Data Science/Article Record
Peer-Reviewed Article July 19, 2021

Diabetic Retinopathy Classification Using ResNet50 and VGG-16 Pretrained Networks

Are you an author of this work?Link to your sovereign AfriScholar profile
Published in: International Journal of Computer Engineering and Data Science
Publisher: Cadi Ayyad University • Morocco • 2737-8543

Abstract

Diabetic retinopathy (DR) is considered one of the worldwide diseases of blindness, especially in the elderly. The main reason for this disease is the complication of diabetes in the retinal blood vessels. Usually, the warning signs are not observed. Screening is an important key to diagnosing the early stages of diabetic retinopathy. This work represents an intelligent system of DR classification based on deep learning (DL) tools, especially convolutional neural networks (CNN). Proposed system can assist ophthalmologists to make a preliminary decision, it allows a DR classification considering normal eyes, mild DR, Moderate DR, Severe DR and Proliferative DR. Obtained results, in terms of classification accuracy, for DR classification using the color retinal background images based on VGG-16 and ResNet50 models are in order 70% and 25% respectively.

Download Full Text PDFView at PublisherCrossref XML

Verified Citation Velocity

Recorded scholarly citations in African and international peer-reviewed literature

27
Total Citations

Citations are continuously tracked and harvested across continental OJS endpoints and OpenAlex feeds.