Open Access

ARTICLE

Leveraging Retinal Fundus Images with Deep Learning for Diabetic Retinopathy Grading and Classification

Mohammad Yamin^1,*, Sarah Basahel¹, Saleh Bajaba², Mona Abusurrah³, E. Laxmi Lydia⁴

1 Department of Management Information Systems, Faculty of Economics and Administration King Abdulaziz University, P.O.Box 80201, Jeddah, 21589, Saudi Arabia
2 Department of Business Administration, King Abdulaziz University, P.O.Box 80201, Jeddah, 21589, Saudi Arabia
3 Department of Management Information Systems, College of Business Administration, Taibah University, Al-Madinah, Saudi Arabia
4Department of Computer Science and Engineering, GMR Institute of Technology, Andhra Pradesh, Rajam 532127, India

* Corresponding Author: Mohammad Yamin. Email:

Computer Systems Science and Engineering 2023, 46(2), 1901-1916. https://doi.org/10.32604/csse.2023.036455

Received 30 September 2022; Accepted 08 December 2022; Issue published 09 February 2023

Abstract

Recently, there has been a considerable rise in the number of diabetic patients suffering from diabetic retinopathy (DR). DR is one of the most chronic diseases and makes the key cause of vision loss in middle-aged people in the developed world. Initial detection of DR becomes necessary for decreasing the disease severity by making use of retinal fundus images. This article introduces a Deep Learning Enabled Large Scale Healthcare Decision Making for Diabetic Retinopathy (DLLSHDM-DR) on Retinal Fundus Images. The proposed DLLSHDM-DR technique intends to assist physicians with the DR decision-making method. In the DLLSHDM-DR technique, image preprocessing is initially performed to improve the quality of the fundus image. Besides, the DLLSHDM-DR applies HybridNet for producing a collection of feature vectors. For retinal image classification, the DLLSHDM-DR technique exploits the Emperor Penguin Optimizer (EPO) with a Deep Recurrent Neural Network (DRNN). The application of the EPO algorithm assists in the optimal adjustment of the hyperparameters related to the DRNN model for DR detection showing the novelty of our work. To assuring the improved performance of the DLLSHDM-DR model, a wide range of experiments was tested on the EyePACS dataset. The comparison outcomes assured the better performance of the DLLSHDM-DR approach over other DL models.

---

Keywords

---