RDS-DR: An Improved Deep Learning Model for Classifying Severity Levels of Diabetic Retinopathy
-
Published:2023-10-03
Issue:19
Volume:13
Page:3116
-
ISSN:2075-4418
-
Container-title:Diagnostics
-
language:en
-
Short-container-title:Diagnostics
Author:
Bashir Ijaz1, Sajid Muhammad Zaheer1ORCID, Kalsoom Rizwana2ORCID, Ali Khan Nauman1ORCID, Qureshi Imran3ORCID, Abbas Fakhar4, Abbas Qaisar3ORCID
Affiliation:
1. Department of Computer Software Engineering, Military College of Signals, National University of Sciences and Technology, Islamabad 44000, Pakistan 2. Faculty of Computer Science and Engineering, Ghulam Ishaq Khan Institute of Engineering Sciences and Technology, Topi 23460, Pakistan 3. College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), Riyadh 11432, Saudi Arabia 4. Centre for Trusted Internet and Community, National University of Singapore (NUS), Singapore 119228, Singapore
Abstract
A well-known eye disorder called diabetic retinopathy (DR) is linked to elevated blood glucose levels. Cotton wool spots, confined veins in the cranial nerve, AV nicking, and hemorrhages in the optic disc are some of its symptoms, which often appear later. Serious side effects of DR might include vision loss, damage to the visual nerves, and obstruction of the retinal arteries. Researchers have devised an automated method utilizing AI and deep learning models to enable the early diagnosis of this illness. This research gathered digital fundus images from renowned Pakistani eye hospitals to generate a new “DR-Insight” dataset and known online sources. A novel methodology named the residual-dense system (RDS-DR) was then devised to assess diabetic retinopathy. To develop this model, we have integrated residual and dense blocks, along with a transition layer, into a deep neural network. The RDS-DR system is trained on the collected dataset of 9860 fundus images. The RDS-DR categorization method demonstrated an impressive accuracy of 97.5% on this dataset. These findings show that the model produces beneficial outcomes and may be used by healthcare practitioners as a diagnostic tool. It is important to emphasize that the system’s goal is to augment optometrists’ expertise rather than replace it. In terms of accuracy, the RDS-DR technique fared better than the cutting-edge models VGG19, VGG16, Inception V-3, and Xception. This emphasizes how successful the suggested method is for classifying diabetic retinopathy (DR).
Funder
Deanship of Scientific Research at Imam Mohammad Ibn Saud Islamic University
Subject
Clinical Biochemistry
Reference39 articles.
1. (2023, July 23). IDF Diabetes Atlas 9th Edition. Available online: https://diabetesatlas.org/atlas/ninth-edition. 2. Sajid, M.Z., Hamid, M.F., Youssef, A., Yasmin, J., Perumal, G., Qureshi, I., Naqi, S.M., and Abbas, Q. (2023). DR-NASNet: Automated System to Detect and Classify Diabetic Retinopathy Severity Using Improved Pretrained NASNet Model. Diagnostics, 13. 3. Multi-stream deep neural network for diabetic retinopathy severity classification under a boosting framework;Mustafa;IEEE Access,2022 4. Sajid, M.Z., Qureshi, I., Abbas, Q., Albathan, M., Shaheed, K., Youssef, A., Ferdous, S., and Hussain, A. (2023). Mobile-HR: An Ophthalmologic-Based Classification System for Diagnosis of Hypertensive Retinopathy Using Optimized MobileNet Architecture. Diagnostics, 13. 5. Li, Y.H., Yeh, N.N., Chen, S.J., and Chung, Y.C. (2019). Computer-assisted diagnosis for diabetic retinopathy based on fundus images using deep convolutional neural network. Mob. Inf. Syst., 2019.
|
|