Classification of Diabetic Retinopathy (DR) using ECA Attention Mechanism Deep learning Networks
salem, D., soliman, M., donkol, A., Dousoky, G. (2024). Classification of Diabetic Retinopathy (DR) using ECA Attention Mechanism Deep learning Networks. EKB Journal Management System, 43(1), 425-431. doi: 10.21608/jaet.2022.145091.1210
Doha salah salem; mahmoud sami soliman; ahmed abd el-baset donkol; Gamal M. Dousoky. "Classification of Diabetic Retinopathy (DR) using ECA Attention Mechanism Deep learning Networks". EKB Journal Management System, 43, 1, 2024, 425-431. doi: 10.21608/jaet.2022.145091.1210
salem, D., soliman, M., donkol, A., Dousoky, G. (2024). 'Classification of Diabetic Retinopathy (DR) using ECA Attention Mechanism Deep learning Networks', EKB Journal Management System, 43(1), pp. 425-431. doi: 10.21608/jaet.2022.145091.1210
salem, D., soliman, M., donkol, A., Dousoky, G. Classification of Diabetic Retinopathy (DR) using ECA Attention Mechanism Deep learning Networks. EKB Journal Management System, 2024; 43(1): 425-431. doi: 10.21608/jaet.2022.145091.1210

Classification of Diabetic Retinopathy (DR) using ECA Attention Mechanism Deep learning Networks

Journal of Advanced Engineering Trends
Volume 43, Issue 1, January 2024, Page 425-431  XML PDF (813.34 K)
Document Type: Original Article
DOI: 10.21608/jaet.2022.145091.1210
View on SCiNiTO View on SCiNiTO
Authors
Doha salah salem email 1; mahmoud sami soliman2; ahmed abd el-baset donkol3; Gamal M. Dousokyorcid 4
1communcation and computer,engineering, nahda, beni-suef
2Department of Communication and Computer,Engineering, Faculty of Engineering, Nahda University, Beni Suef 62521, Egypt.
3Communication and Computer Engineering, Dep., Faculty of Engineering, Nahda University, Bani-Sweif, Egypt
4Electrical Engineering Department, Faculty of Engineering, Minia University, Minia 61517, Egypt
Abstract
Diabetic retinopathy (DR) is the most frequent eye condition among diabetics and a leading cause of blindness. Effective management of the disease requires regular fundus photography screening and prompt action. A computer-aided and entirely automated diagnosis of DR has attracted attention due to the increasing number of diabetic patients and the extensive screening they need. In recent years, advanced deep neural networks have been widely used in various fields. We propose to early detect the DR using the Efficient channel attention (ECA) model. For DR color medical picture severity detection, a deep convolutional neural network model called ECA-Resnet101 (ERNet), ECA-VGG19 (EVNet), and ECA-InceptionV4 (EIANet) have been constructed using a flexible one-dimensional convolution kernel size approach dependent on the feature map dimension. As a result, the Kaggle competition's DR dataset has a precision, accuracy, sensitivity, and specificity of 0.974, 0.974, 0.974, and 0.992. According to several experiments, InceptionV4, depending on the ECA, could more accurately detect disease features and define DR severity.
Keywords
Deep learning; DCNN; ECA; ECA-Net
Supplementary Files
Statistics
Article View: 61
PDF Download: 47