ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization
MethodsX · 2024-12 · 13 · 103018
DOI: 10.1016/j.mex.2024.103018 ↗Kurz gefasst
Fachartikel in der Zeitschrift MethodsX, 2024-12. Verfasst von Vishal Awasthi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics & Communication Engineering, School of Engineering & Technology (UIET), Chhatrapati Shahu Ji Maharaj University, Kanpur, In…. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Diabetic retinopathy (DR) is a significant cause of vision impairment globally, emphasizing the importance of timely and precise detection to prevent severe consequences. This study presents an optimized Vision Transformer (ViT) model that incorporates Harris Hawk Optimization (HHO) to improve the automated detection of diabetic retinopathy (DR). The ViT architecture utilizes self-attention mechanisms to capture local and global features in retinal images. Additionally, HHO optimizes key hyperparameters to maximize the performance of the model. The proposed ViT-HHO model achieved exceptional performance on the APTOS-2019 and IDRiD datasets. Specifically, it achieved 99.83 % accuracy, 99.78 % sensitivity, 99.85 % specificity, and 99.80 % AUC-ROC on the APTOS-2019 dataset, surpassing traditional CNNs and alternative optimization techniques. The model exhibited strong generalization on the IDRiID dataset, achieving an accuracy of 99.11 % and an AUC-ROC of 99.12 %. The ViT-HHO model demonstrates the potential for enhancing the clinical detection of diabetic retinopathy (DR), providing high precision and reliability.•An optimized Vision Transformer (ViT) model was developed using HHO for improved detection of Diabetic Retinopathy (DR).•The model was validated on the APTOS-2019 and IDRiID datasets, demonstrating superior accuracy and AUC-ROC metrics.•The model's generalization and robustness were demonstrated through comprehensive performance evaluations.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electronics & Communication Engineering, School of Engineering & Technology (UIET), Chhatrapati Shahu Ji Maharaj University, Kanpur, India.
- Department of Computer Application, Allenhouse Business School, Dr. A.P.J. Abdul Kalam Technical University, Lucknow, India.
- Department of Information Technology, School of Engineering & Technology (UIET), Chhatrapati Shahu Ji Maharaj University, Kanpur, India.
- Department of Physics, School of Engineering & Technology (UIET), Chhatrapati Shahu Ji Maharaj University, Kanpur, India.
- Department of Mathematics, School of Engineering & Technology (UIET), Chhatrapati Shahu Ji Maharaj University, Kanpur, India.
- Department of Computer Science and Engineering, Harcourt Butler Technical University, Kanpur, India.
Zitieren
APA
Awasthi, V., Awasthi, N., Kumar, H., Singh, S., Singh, P. P., Dixit, P., & Agarwal, R. (2024). ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization. MethodsX, 13, 103018. https://doi.org/10.1016/j.mex.2024.103018
Vancouver
Awasthi V, Awasthi N, Kumar H, Singh S, Singh PP, Dixit P, et al. ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization. MethodsX. 2024;13:103018. doi:10.1016/j.mex.2024.103018
BibTeX
@article{Awasthi2024,
author = {Awasthi, Vishal and Awasthi, Namita and Kumar, Hemant and Singh, Shubhendra and Singh, Prabal Pratap and Dixit, Poonam and Agarwal, Rashi},
title = {ViT-HHO: Optimized vision transformer for diabetic retinopathy detection using Harris Hawk optimization},
journal = {MethodsX},
year = {2024},
volume = {13},
pages = {103018},
doi = {10.1016/j.mex.2024.103018}
}
EUVIMED