:: Volume 24, Issue 1 (Spring 2022) ::
EBNESINA 2022, 24(1): 36-45 Back to browse issues page
Effect of deep generative adversarial networks models in determining the degree of diabetic retinopathy
Shirin Mirabedini * , Mohammadreza Kangavari
Department of Computer Engineering, Payame Noor University, Tehran, Iran , Sh.Mirabedini@pnu.ac.ir
Abstract:   (1299 Views)

Background and aims: Early detection of diabetic retinopathy in the military forces can prevent their performance reduction or avoid the occurrence of operational errors. So an automated and optimal method to diagnose the degree of disease from retinal images is valuable in the prevention of acute phases. The purpose of this article is to present a new method in determining of proliferation based on the deep generative adversarial networks models (GANs).
Methods: In this study, which was conducted in 2018-2019, a new method was used to classify 35,126 medical images on the data set available from the Kagel site related to a hospital in the UK. To create a balance between levels, first with the help of a deep GAN, the number of small classes was increased, then using a designed classifier, the degree of disease was determined in different ways.
Results: Using the designed GAN, an accuracy of about 87% was obtained for classification, which was about 7% more than the best similar works. In addition, with the distribution of the model, the efficiency of automation also showed an improvement of 60%.
Conclusion: By solving the problem of imbalance between different levels of retinopathy, by producing new images using the designed GAN and distributing the mentioned operations, while increasing the performance, optimal accuracy has been obtained. Therefore, this new strategy can be used to automate the diagnosis of diabetic retinopathy.
 
Keywords: Diabetic Retinopathy, Neural Network Models, Deep Learning, Military
Full-Text [PDF 1153 kb]   (874 Downloads)    
Type of Study: Original | Subject: Military Medicine
Received: 2021/08/26 | Accepted: 2021/12/8 | Published: 2022/03/30



XML   Persian Abstract   Print



Rights and permissions
Creative Commons License This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Volume 24, Issue 1 (Spring 2022) Back to browse issues page