Deep Learning Grading System for Diabetic Retinopathy using Fundus Images.
Elsawah, D., Elnakib, A., Moustafa, H. (2020). Deep Learning Grading System for Diabetic Retinopathy using Fundus Images.. EKB Journal Management System, 45(4), 1-8. doi: 10.21608/bfemu.2020.118646
Doaa Elsawah; Ahmed Elnakib; Hossam El-Din Salah Moustafa. "Deep Learning Grading System for Diabetic Retinopathy using Fundus Images.". EKB Journal Management System, 45, 4, 2020, 1-8. doi: 10.21608/bfemu.2020.118646
Elsawah, D., Elnakib, A., Moustafa, H. (2020). 'Deep Learning Grading System for Diabetic Retinopathy using Fundus Images.', EKB Journal Management System, 45(4), pp. 1-8. doi: 10.21608/bfemu.2020.118646
Elsawah, D., Elnakib, A., Moustafa, H. Deep Learning Grading System for Diabetic Retinopathy using Fundus Images.. EKB Journal Management System, 2020; 45(4): 1-8. doi: 10.21608/bfemu.2020.118646

Deep Learning Grading System for Diabetic Retinopathy using Fundus Images.

MEJ- Mansoura Engineering Journal
Article 19, Volume 45, Issue 4, December 2020, Page 1-8  XML PDF (799.42 K)
Document Type: Research Studies
DOI: 10.21608/bfemu.2020.118646
View on SCiNiTO View on SCiNiTO
Authors
Doaa Elsawah1; Ahmed Elnakib email orcid 1; Hossam El-Din Salah Moustafa2
1ECE department, Faculty of Engineering, Mansoura University, Egypt
2Faculty of Engineering, Mansoura University, Mansoura, Egypt
Abstract
Diabetic Retinopathy (DR) is one of the main causes of blindness that can be overcome, if it is early detected. This work proposes an automated early detection and grading of DR using fundus images. The proposed detection and grading system investigate different deep learning architectures (i.e., ResNet and AlexNet) that are applied to an augment data to extract deep compact features of the fundus images. The extracted features are input to a pixel-wise Neural Network (NN) classifier or a Support Vector Machine (SVM) classifier for automated DR grading. The performance of the proposed system is evaluated using a publically available fundus Indian Diabetic Retinopathy Image Dataset (IDRiD), collected for ISBI-2018 challenge. The IDRiD dataset consists of 516 retinal images of normal and different DR grades, i.e., mild, moderate, severe, and Proliferative Diabetic Retinopathy (PDR). Our system achieves an overall accuracy of 95.73%, sensitivity of 95.73%, and specificity of 98.51% utilizing an AlexNet-based architecture and a pixel-wise NN classifier. Compared to the previous related work, the proposed system shows promising DR grading performance.
Keywords
Deep learning; Fundus images; Diabetic Retinopathy; Grading
Statistics
Article View: 337
PDF Download: 428