Article: A deep learning model framework for diabetic retinopathy detection Journal: International Journal of Networking and Virtual Organisations (IJNVO) 2022 Vol.27 No.2 pp.107 - 124 Abstract: Diabetic retinopathy (DR) is the typical diabetic eye issue and a main reason of blindness around the world. As per the International Diabetes Federation (IDF), the rates of diabetes would rise to 552 million by 2034. Breakthroughs in computer science techniques inclusive of artificial intelligence (AI) and deep learning (DL) have multiplied opportunities for early detection of DR. This indicates that the likelihood of a patient's healing will improve, and the risk of eyesight loss could be minimised in due course. A deep learning model (ResNet) for medical DR detection was examined in this article. The dataset of Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 was used to train and test the DL model. To demonstrate the vitality of the chosen ResNet model, performance measures and testing accuracy like recall, precision, and F1 score were determined. The modified ResNet model attained a testing accuracy of around 84% even with only a few dataset images. Also, training time and computational complexity were reduced with this simpler model. Inderscience Publishers - linking academia, business and industry through research

Title: A deep learning model framework for diabetic retinopathy detection

Authors: M. Padmapriya; S. Pasupathy; R. Sumathi; V. Punitha

Addresses: Department of Computer Science and Engineering, Faculty of Engineering and Technology, Annamalai University, Chidambaram, India ' Department of Computer Science and Engineering, Annamalai University, Annamalai Nagar, Tamilnadu, India ' Department of Information Technology, Saranathan College of Engineering, Tamilnadu, India ' Department of Information Technology, Saranathan College of Engineering, Tamilnadu, India

Abstract: Diabetic retinopathy (DR) is the typical diabetic eye issue and a main reason of blindness around the world. As per the International Diabetes Federation (IDF), the rates of diabetes would rise to 552 million by 2034. Breakthroughs in computer science techniques inclusive of artificial intelligence (AI) and deep learning (DL) have multiplied opportunities for early detection of DR. This indicates that the likelihood of a patient's healing will improve, and the risk of eyesight loss could be minimised in due course. A deep learning model (ResNet) for medical DR detection was examined in this article. The dataset of Asia Pacific Tele-Ophthalmology Society (APTOS) 2019 was used to train and test the DL model. To demonstrate the vitality of the chosen ResNet model, performance measures and testing accuracy like recall, precision, and F1 score were determined. The modified ResNet model attained a testing accuracy of around 84% even with only a few dataset images. Also, training time and computational complexity were reduced with this simpler model.

Keywords: diabetic retinopathy; convolutional neural network; CNN; machine learning; deep learning; ResNet model.

DOI: 10.1504/IJNVO.2022.127584

International Journal of Networking and Virtual Organisations, 2022 Vol.27 No.2, pp.107 - 124

Received: 29 Dec 2021
Accepted: 10 Mar 2022
Published online: 12 Dec 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: A deep learning model framework for diabetic retinopathy detection

Keep up-to-date