Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 May 20;19(5):e0303094.
doi: 10.1371/journal.pone.0303094. eCollection 2024.

A novel fusion of genetic grey wolf optimization and kernel extreme learning machines for precise diabetic eye disease classification

Abdul Qadir Khan  1 , Guangmin Sun  1 , Majdi Khalid  2 , Azhar Imran  3 , Anas Bilal  4   5 , Muhammad Azam  6 , Raheem Sarwar  7
Affiliations

A novel fusion of genetic grey wolf optimization and kernel extreme learning machines for precise diabetic eye disease classification

Abdul Qadir Khan et al. PLoS One. .

Abstract

In response to the growing number of diabetes cases worldwide, Our study addresses the escalating issue of diabetic eye disease (DED), a significant contributor to vision loss globally, through a pioneering approach. We propose a novel integration of a Genetic Grey Wolf Optimization (G-GWO) algorithm with a Fully Convolutional Encoder-Decoder Network (FCEDN), further enhanced by a Kernel Extreme Learning Machine (KELM) for refined image segmentation and disease classification. This innovative combination leverages the genetic algorithm and grey wolf optimization to boost the FCEDN's efficiency, enabling precise detection of DED stages and differentiation among disease types. Tested across diverse datasets, including IDRiD, DR-HAGIS, and ODIR, our model showcased superior performance, achieving classification accuracies between 98.5% to 98.8%, surpassing existing methods. This advancement sets a new standard in DED detection and offers significant potential for automating fundus image analysis, reducing reliance on manual examination, and improving patient care efficiency. Our findings are crucial to enhancing diagnostic accuracy and patient outcomes in DED management.

PubMed Disclaimer

Conflict of interest statement

The authors have declared that no competing interests exist.

Figures

Fig 1
Fig 1. CNN, FCN, and FCEDN architecture.
Fig 2
Fig 2. KELM configuration.
Fig 3
Fig 3. Genetic algorithm flowchart.
Fig 4
Fig 4. Proposed methodology.
Fig 5
Fig 5. Sample images from the datasets.
Fig 6
Fig 6. Segmentation performance matrices comparison.
Fig 7
Fig 7. Input, pre-processing, ground truth, and the predicted segmentation results were obtained by the proposed model for some sample images.
Fig 8
Fig 8. ACC, SEN, and SPC evaluation using IDRiD dataset.
Fig 9
Fig 9. MCC, ER, and F1-Score evaluation using IDRiD dataset.
Fig 10
Fig 10. Confusion matrix comparison of four algorithms on IDRiD dataset for diabetic retinopathy, showcasing GGWO-KELM’s exceptional performance.
Fig 11
Fig 11. Accuracy evaluation using DR-HAGIS dataset.
Fig 12
Fig 12. Sensitivity evaluation using DR-HAGIS dataset.
Fig 13
Fig 13. Error Rate evaluation using DR-HAGIS dataset.
Fig 14
Fig 14. Specificity evaluation using DR-HAGIS dataset.
Fig 15
Fig 15. MCC evaluation using DR-HAGIS dataset.
Fig 16
Fig 16. F-1 Score valuation using DR-HAGIS dataset.
Fig 17
Fig 17. Comparison of confusion matrices for different classifiers across three diseases: Diabetic retinopathy, DME, and Glaucoma.
Fig 18
Fig 18. Accuracy evaluation using OIDR dataset.
Fig 19
Fig 19. Sensitivity evaluation using OIDR dataset.
Fig 20
Fig 20. Specificity evaluation using OIDR dataset.
Fig 21
Fig 21. MCC evaluation using OIDR dataset.
Fig 22
Fig 22. Error Rate evaluation using OIDR dataset.
Fig 23
Fig 23. F-1 Score evaluation using OIDR dataset.
Fig 24
Fig 24. Comparison of confusion matrices for different classifiers using OIDR dataset.
See this image and copyright information in PMC

References

    1. International Diabetes Federation. Diabetes Atlas. 2021;9th Editio. Available: https://www.diabetesatlas.org/. - PubMed
    1. Nita Gandhi ForouhiNicholas J. Wareham. Epidemiology of diabetes. Med (United Kingdom). 2022.
    1. Bilal A, Sun G, Mazhar S. Survey on recent developments in automatic detection of diabetic retinopathy. Journal Francais d’Ophtalmologie. 2021. pp. 420–440. doi: 10.1016/j.jfo.2020.08.009 - DOI - PubMed
    1. Wong TY, Sun J, Kawasaki R, Ruamviboonsuk P, Gupta N, Lansingh VC, et al.. Guidelines on Diabetic Eye Care: The International Council of Ophthalmology Recommendations for Screening, Follow-up, Referral, and Treatment Based on Resource Settings. Ophthalmology. 2018. doi: 10.1016/j.ophtha.2018.04.007 - DOI - PubMed
    1. Bilal A, Sun G, Li Y, Mazhar S, Latif J. Lung nodules detection using grey wolf optimization by weighted filters and classification using CNN. J Chinese Inst Eng Trans Chinese Inst Eng A. 2022;45. doi: 10.1080/02533839.2021.2012525 - DOI