DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.

Diabetic retinopathy (DR) is a prominent reason of blindness globally, which is a diagnostically challenging disease owing to the intricate process of its development and the human eye's complexity, which consists of nearly forty connected components like the retina, iris, optic nerve, and so o...

Full description

Saved in:
Bibliographic Details
Main Authors: Sundreen Asad Kamal, Youtian Du, Majdi Khalid, Majed Farrash, Sahraoui Dhelim
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2024-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0312016
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850164871907246080
author Sundreen Asad Kamal
Youtian Du
Majdi Khalid
Majed Farrash
Sahraoui Dhelim
author_facet Sundreen Asad Kamal
Youtian Du
Majdi Khalid
Majed Farrash
Sahraoui Dhelim
author_sort Sundreen Asad Kamal
collection DOAJ
description Diabetic retinopathy (DR) is a prominent reason of blindness globally, which is a diagnostically challenging disease owing to the intricate process of its development and the human eye's complexity, which consists of nearly forty connected components like the retina, iris, optic nerve, and so on. This study proposes a novel approach to the identification of DR employing methods such as synthetic data generation, K- Means Clustering-Based Binary Grey Wolf Optimizer (KCBGWO), and Fully Convolutional Encoder-Decoder Networks (FCEDN). This is achieved using Generative Adversarial Networks (GANs) to generate high-quality synthetic data and transfer learning for accurate feature extraction and classification, integrating these with Extreme Learning Machines (ELM). The substantial evaluation plan we have provided on the IDRiD dataset gives exceptional outcomes, where our proposed model gives 99.87% accuracy and 99.33% sensitivity, while its specificity is 99. 78%. This is why the outcomes of the presented study can be viewed as promising in terms of the further development of the proposed approach for DR diagnosis, as well as in creating a new reference point within the framework of medical image analysis and providing more effective and timely treatments.
format Article
id doaj-art-74dcff98d48e41be9b02fb3c317b1e57
institution OA Journals
issn 1932-6203
language English
publishDate 2024-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-74dcff98d48e41be9b02fb3c317b1e572025-08-20T02:21:52ZengPublic Library of Science (PLoS)PLoS ONE1932-62032024-01-011912e031201610.1371/journal.pone.0312016DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.Sundreen Asad KamalYoutian DuMajdi KhalidMajed FarrashSahraoui DhelimDiabetic retinopathy (DR) is a prominent reason of blindness globally, which is a diagnostically challenging disease owing to the intricate process of its development and the human eye's complexity, which consists of nearly forty connected components like the retina, iris, optic nerve, and so on. This study proposes a novel approach to the identification of DR employing methods such as synthetic data generation, K- Means Clustering-Based Binary Grey Wolf Optimizer (KCBGWO), and Fully Convolutional Encoder-Decoder Networks (FCEDN). This is achieved using Generative Adversarial Networks (GANs) to generate high-quality synthetic data and transfer learning for accurate feature extraction and classification, integrating these with Extreme Learning Machines (ELM). The substantial evaluation plan we have provided on the IDRiD dataset gives exceptional outcomes, where our proposed model gives 99.87% accuracy and 99.33% sensitivity, while its specificity is 99. 78%. This is why the outcomes of the presented study can be viewed as promising in terms of the further development of the proposed approach for DR diagnosis, as well as in creating a new reference point within the framework of medical image analysis and providing more effective and timely treatments.https://doi.org/10.1371/journal.pone.0312016
spellingShingle Sundreen Asad Kamal
Youtian Du
Majdi Khalid
Majed Farrash
Sahraoui Dhelim
DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.
PLoS ONE
title DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.
title_full DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.
title_fullStr DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.
title_full_unstemmed DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.
title_short DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization.
title_sort drsegnet a cutting edge approach to diabetic retinopathy segmentation and classification using parameter aware nature inspired optimization
url https://doi.org/10.1371/journal.pone.0312016
work_keys_str_mv AT sundreenasadkamal drsegnetacuttingedgeapproachtodiabeticretinopathysegmentationandclassificationusingparameterawarenatureinspiredoptimization
AT youtiandu drsegnetacuttingedgeapproachtodiabeticretinopathysegmentationandclassificationusingparameterawarenatureinspiredoptimization
AT majdikhalid drsegnetacuttingedgeapproachtodiabeticretinopathysegmentationandclassificationusingparameterawarenatureinspiredoptimization
AT majedfarrash drsegnetacuttingedgeapproachtodiabeticretinopathysegmentationandclassificationusingparameterawarenatureinspiredoptimization
AT sahraouidhelim drsegnetacuttingedgeapproachtodiabeticretinopathysegmentationandclassificationusingparameterawarenatureinspiredoptimization