Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors
Mahmoud, S., omer, O., Mahmoud, H., Esmaiel, H., Abdel-Nasser, M. (2023). Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors. EKB Journal Management System, 3(1), 69-77. doi: 10.21608/aujst.2023.312701
Shimaa Mahmoud; osama Ahmed omer; Habeba Mahmoud; Hamada Esmaiel; Mohamed Abdel-Nasser. "Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors". EKB Journal Management System, 3, 1, 2023, 69-77. doi: 10.21608/aujst.2023.312701
Mahmoud, S., omer, O., Mahmoud, H., Esmaiel, H., Abdel-Nasser, M. (2023). 'Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors', EKB Journal Management System, 3(1), pp. 69-77. doi: 10.21608/aujst.2023.312701
Mahmoud, S., omer, O., Mahmoud, H., Esmaiel, H., Abdel-Nasser, M. Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors. EKB Journal Management System, 2023; 3(1): 69-77. doi: 10.21608/aujst.2023.312701

Diabetic retinopathy detection in eye fundus images using deep transfer learning and robust feature extractors

Aswan University Journal of Sciences and Technology
Volume 3, Issue 1, June 2023, Page 69-77  XML
Document Type: Original papers
DOI: 10.21608/aujst.2023.312701
View on SCiNiTO View on SCiNiTO
Authors
Shimaa Mahmoud1; osama Ahmed omer2; Habeba Mahmoud3; Hamada Esmaiel4; Mohamed Abdel-Nasser4
1Aswan water and wastewater Company
2Department of Electrical Engineering, Faculty of Engineering, Aswan University
3Department of Electrical Engineering, Aswan Faculty of Engineering, Aswan University,
4Department of Electrical Engineering, Aswan University
Abstract
 Diabetic retinopathy (DR) is one of the main global causes of preventable blindness. Its initial sign is red lesions, a word that refers to both hemorrhages (HEs) and microaneurysms (MAs). In typical clinical practice, doctors manually identify these lesions using fundus images. This is a difficult, time-consuming, and effort-intensive task because of the small size and lack of contrast in the lesions.  Hand-crafted feature extraction techniques, including Gabor wavelets, Local Binary Patterns (LBP), and Histogram of Oriented Gradients (HOG), were employed with the support vector machine (SVM) method for classification. Deep learning feature extraction techniques were employed using 16 pre-trained neural network feature extractors through transfer learning. The novelty of this study lies in the utilization and comparison of both hand-crafted and deep learning feature extraction approaches for diabetic retinopathy detection in eye fundus images. This study also explores the effectiveness of hand-crafted feature extraction techniques, which are less computationally expensive and easier to interpret. The study found that both hand-crafted and deep learning feature extraction techniques are effective for diabetic retinopathy detection. ResNet101 was discovered to be the best pre-trained neural network, achieving an accuracy of 95% and an area under the curve (AUC) of 96.0%.  Overall, the study's contributions include the development and evaluation of various CAD systems for diabetic retinopathy detection, insights into the effectiveness of different feature extraction techniques and classification methods, and potential improvements to traditional diabetes diagnosis methods.
Keywords
Computer-aided diagnosis; Deep learning, Diabetic retinopathy, handcrafted features extraction
Statistics
Article View: 382