Almaarefa University
The authoritative source for research information and outputs is Elsevier Scopus, with researcher profile verification from the Deanship of Scientific Research.
ArticleOpen access2026SDG 31 citation

Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network

Ashit Kumar Dutta،Nasser Ali Aljarallah،Abdul Rahaman Wahab Sait ✉

Frontiers in Medicine · vol. 13 · 1709872-1709872 · 2026

Abstract

Introduction: Diabetic retinopathy (DR) is an inflammatory condition affecting the retina caused by elevated and unregulated blood glucose levels. On a global scale, it is a contributing factor to vision impairment. Several deep learning (DL) methods use retinal images to identify DR severity. However, a significant improvement is required to assist medical professionals in recognizing DR in its early phases. Methods: Thus, the author introduced a method based on the DL technique to determine the DR severity grades using retinal images. A ShuffleNet V2 model with vision transformers' (ViT) attention mechanism was used to extract the features. An improved Whale optimization method (IWO) was used to fine-tune the feature extraction model. We employed a convolutional Kolmogorov-Arnold Network to categorize the DR severity using the extracted features. The EyePACS dataset was utilized to train the proposed DR severity grading model using a five-fold cross-validation strategy. We generalized the model on the Messidor-2 dataset. Results: The findings revealed an average accuracy of 93.84% on the MESSIDOR-2 dataset, demonstrating a substantial improvement in detecting DR using the fundus images. Discussion: Furthermore, the model demands minimal processing resources to generate the outcomes, leading to the deployment of the proposed DR severity detection model in healthcare facilities with limited computational resources.

Details

Journal
Frontiers in Medicine
Publisher
Frontiers Media
Volume
13
Issue
—
Pages
1709872-1709872
ISSN
2296-858X
Year
2026
Language
en
License
cc-by
Open access
gold
Citations
1
Source
scopus

Topics

Artificial intelligenceComputer scienceDiabetic retinopathyConvolutional neural networkCategorizationDeep learning

Retinal Imaging and Analysis (Medicine) · Retinal Diseases and Treatments (Medicine) · Ophthalmology and Visual Health Research (Medicine)

Cite this

APA
Dutta, A. K., Aljarallah, N. A., Sait, A. R. W. (2026). Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network. Frontiers in Medicine, 13, 1709872-1709872. https://doi.org/10.3389/fmed.2026.1709872
Harvard
Dutta, A. K., Aljarallah, N. A., Sait, A. R. W. 2026, 'Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network', Frontiers in Medicine, vol. 13, 1709872-1709872. Available at: https://doi.org/10.3389/fmed.2026.1709872
Vancouver
Dutta AK, Aljarallah NA, Sait ARW. Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network. Frontiers in Medicine. 2026;13, 1709872-1709872.
BibTeX
@article{dutta2026264,
  title = {Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network},
  author = {Ashit Kumar Dutta and Nasser Ali Aljarallah and Abdul Rahaman Wahab Sait},
  year = {2026},
  journal = {Frontiers in Medicine},
  volume = {13},
  pages = {1709872-1709872},
  publisher = {Frontiers Media},
  doi = {10.3389/fmed.2026.1709872},
  url = {https://doi.org/10.3389/fmed.2026.1709872}
}
RIS
TY  - JOUR
AU  - Ashit Kumar Dutta
AU  - Nasser Ali Aljarallah
AU  - Abdul Rahaman Wahab Sait
TI  - Diabetic retinopathy severity detection using an improved Whale optimization algorithm and convolutional Kolmogorov-Arnold network
PY  - 2026
JO  - Frontiers in Medicine
VL  - 13
SP  - 1709872-1709872
DO  - 10.3389/fmed.2026.1709872
UR  - https://doi.org/10.3389/fmed.2026.1709872
ER  - 

Related outputs