IRO Journals
Journal of Innovative Image Processing

An Empirical Evaluation and Comparative Study of Metaheuristic-Optimized Deep Learning for Four-Class Retinal Disease Classification

Open Access
Published: 12 May, 2026
Pages: 665-683
  • Audrey Huong , Audrey Huong
    Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, Malaysia
    Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, Malaysia
  • Wan Mahani Hafizah Wan Mahmud , Wan Mahani Hafizah Wan Mahmud
    Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, Malaysia
    Department of Electronic Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, Malaysia
  • Ser Lee Loh , Ser Lee Loh
    Centre for Robotics and Industrial Automation, Fakulti Teknologi dan Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia
    Centre for Robotics and Industrial Automation, Fakulti Teknologi dan Kejuruteraan Elektrik, Universiti Teknikal Malaysia Melaka, Melaka, Malaysia
  • Kim Gaik Tay , Kim Gaik Tay
    Department of Computer Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, Malaysia
    Department of Computer Engineering, Faculty of Electrical and Electronic Engineering, Universiti Tun Hussein Onn Malaysia, Parit Raja, Johor, Malaysia
  • Xavier Ngu Xavier Ngu
    RF EMC Centre Malaysia Sdn. Bhd., Universiti Tun Hussein Onn Malaysia, Johor, Malaysia
    RF EMC Centre Malaysia Sdn. Bhd., Universiti Tun Hussein Onn Malaysia, Johor, Malaysia
view PDF
view PDF

How to Cite

Huong, Audrey, Wan Mahani Hafizah Wan Mahmud, Ser Lee Loh, Kim Gaik Tay, and Xavier Ngu. 2026. “An Empirical Evaluation and Comparative Study of Metaheuristic-Optimized Deep Learning for Four-Class Retinal Disease Classification”. Journal of Innovative Image Processing 8 (2): 665-83. https://doi.org/10.36548/jiip.2026.2.012.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Deep Learning
EfficientNet
Fundus
Hyperparameter
Optimization

Abstract

Traditional retinal disease diagnosis using colour fundus imaging is subject to inter- and intra-observer variability and subjective bias. Meanwhile, manual or heuristic hyperparameter selection for neural network training is vulnerable to suboptimal convergence. There are also common challenges, including the lack of standardized evaluation protocols, non-uniform experimental designs, and class imbalance, which further hinder the development of reliable classifiers. This research addresses these limitations by employing metaheuristic algorithms to optimize the training of AlexNet, GoogleNet, and EfficientNet-B0. Particle swarm optimization (PSO), grey wolf optimization (GWO), and wild horse optimization (WHO) are evaluated for their effectiveness in identifying optimal training hyperparameter configurations for a four-class fundus image classification task. Statistical analysis revealed no significant association between the choice of optimization algorithm and the prediction performance (ρ = 0.341). The difference is more pronounced when testing the relationship between the network architecture and the prediction outcomes (ρ = 0.015). Among the evaluated optimizer-architecture pairs, GWO-EfficientNet demonstrates superior performance, achieving an accuracy of 96.52%, precision of 96.50%, recall of 96.47%, specificity of 98.84%, F1 score of 96.48%, and a Matthew’s correlation coefficient (MCC) of 95.33%, outperforming other optimizer-architecture combinations. Repeated experiments show strong performance consistency across the best-performing pairs, with a standard deviation of below 2%. The high accuracy and low inference time highlight the potential of the proposed approach for real-time ophthalmology applications, supporting improved clinical decision-making and more efficient eye care delivery.

References

  1. Jaffet, Jilu, Tejaswini Pingali, Arun Kumar Raut, Sonali Mohapatra, and Vivek Singh. "Eye: Anatomy, Physiology, and Disease." In Complex Ophthalmic Dosage Forms: Advances in Biomedical Applications and Future Perspectives, Singapore: Springer Nature Singapore, 2025, 45-69.
  2. Pieńczykowska, Kamila, Anna Bryl, and Małgorzata Mrugacz. "Link between Metabolic Syndrome, Inflammation, and Eye Diseases." International Journal of Molecular Sciences 26, no. 5 (2025): 2174.
  3. Pardeshi, Sagar R., Mahesh P. More, Abhijeet D. Kulkarni, Chandrakantsing V. Pardeshi, Pritam B. Patil, Ankit S. Patil, Prabhanjan S. Giram et al. "Current Perspectives in Nanomedicine Delivery for Targeted Ocular Therapeutics." Bulletin of Materials Science 46, no. 1 (2023): 35.
  4. Robles, Rafael, Nikhil Patel, Emily Neag, Ajay Mittal, Zahra Markatia, Kambiz Ameli, and Benjamin Lin. "A Systematic Review of Digital Ophthalmoscopes in Medicine." Clinical Ophthalmology (2023): 2957-2965.
  5. Iovino, Claudio, Clemente Maria Iodice, Danila Pisani, Luciana Damiano, Valentina Di Iorio, Francesco Testa, and Francesca Simonelli. "Clinical Applications of Optical Coherence Tomography Angiography in Inherited Retinal Diseases: An Up-To-Date Review of the Literature." Journal of Clinical Medicine 12, no. 9 (2023): 3170.
  6. Adenigba, Peter T., Ademola J. Adekanmi, and Olufunmilola A. Ogun. "Central Retinal and Ophthalmic Artery Doppler Velocimetry among Hypertensives and Normotensive Adults at a Nigerian Tertiary Health Facility." Nigerian Medical Journal 63 (2022):385–393.
  7. Dragoi, Elena Niculina, and Vlad Dafinescu. "Review of Metaheuristics Inspired from the Animal Kingdom." Mathematics 9, no. 18 (2021): 2335.
  8. Patil, Mahesh, Satyadhyan Chickerur, Vijayalakshmi Bakale, Shantala Giraddi, Vivekanand Roodagi, and Yashaswini Kulkarni. "Deep Hyperparameter Transfer Learning for Diabetic Retinopathy Classification." Turkish Journal of Electrical Engineering and Computer Sciences 29, no. 8 (2021): 2824-2839.
  9. Ghosh, Swarup Kr, Biswajit Biswas, and Anupam Ghosh. "A Novel Approach of Retinal Image Enhancement Using PSO System and Measure oof Fuzziness." Procedia Computer Science 167 (2020): 1300-1311.
  10. Raza, Asif, Shahrulniza Musa, Ahmad Shahrafidz Khalid, Muhammad Mansoor Alam, Mazliham Mohd Su’ud, and Fouzia Noor. "Multiclass Diabetic Retinopathy: Hybrid Metaheuristic Particle Swarm Optimization and Classification for Severity Grading and Feature Extraction." Engineering, Technology & Applied Science Research 15, no. 6 (2025): 30317-30323.
  11. Koishiyeva, Dina, Kuanysh Alipbayev, Jeong Won Kang, Adil Mukhamedgali, and Assel Mukasheva. "Optimisation of Glaucoma Detection in Fundus Imaging Using Particle Swarm Optimization, Artificial Bee Colony, and Binary Cuckoo Search." In 2025 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA), IEEE, 2025, 1-8.
  12. Dayana, A. Mary, and WR Sam Emmanuel. "An Enhanced Swarm Optimization-Based Deep Neural Network for Diabetic Retinopathy Classification in Fundus Images." Multimedia Tools and Applications 81, no. 15 (2022): 20611-20642.
  13. Geetha, A., M. Carmel Sobia, D. Santhi, and A. Ahilan. "DEEP GD: Deep Learning Based Snapshot Ensemble CNN with EfficientNet for Glaucoma Detection." Biomedical Signal Processing and Control 100 (2025): 106989.
  14. Almeshrky, Hamida, and Abdulkadir Karacı. "Optic Disc Segmentation in Human Retina Images Using a Meta Heuristic Optimization Method and Disease Diagnosis with Deep Learning." Applied Sciences 14, no. 12 (2024): 5103.
  15. Gül, Muhammed Furkan, Özlem Polat, and Halit Bakir. "TL-GWO: Fine-Tuned Transfer Learning with Grey Wolf Optimizer for Accurate Fundus Image-Based Eye Disease Classification." Experimental Eye Research (2025): 110598.
  16. Subramaniam, Krishnakumar, and Archana Naganathan. "Enhancing Retinal Fundus Image Classification Through Active Gradient Deep Convolutional Neural Network and Red Spider Optimization." Neural Computing and Applications 36, no. 26 (2024): 16607-16619.
  17. Mohan, Janani Priya, and Yamuna Govindarajan. "Wild Horse Optimization and Deep Learning Based Computer Aided Diagnostic Tool for Retinal Diseases." OPSEARCH (2025): 1-28.
  18. Ali, Mona AS, Kishore Balasubramanian, Gayathri Devi Krishnamoorthy, Suresh Muthusamy, Santhiya Pandiyan, Hitesh Panchal, Suman Mann et al. "Classification of Glaucoma Based on Elephant-Herding Optimization Algorithm and Deep Belief Network." Electronics 11, no. 11 (2022): 1763.
  19. Ashanand, and Manpreet Kaur. "A Novel Chaotic Weighted EHO-Based Methodology for Retinal Vessel Segmentation." Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization 11, no. 7 (2024): 2285455.
  20. Doddi, Guna V. "Eye Diseases Classification Dataset." Kaggle Datasets (2022).
  21. Aurangzeb, Khursheed, Sheraz Aslam, Musaed Alhussein, Rizwan Ali Naqvi, Muhammad Arsalan, and Syed Irtaza Haider. "Contrast Enhancement of Fundus Images by Employing Modified PSO For Improving the Performance of Deep Learning Models." IEEE Access 9 (2021): 47930-47945.
  22. Kansal, Kajal, Tej Bahadur Chandra, and Akansha Singh. "ResNet-50 vs. EfficientNet-B0: Multi-Centric Classification of Various Lung Abnormalities Using Deep Learning." Procedia Computer Science 235 (2024): 70-80.
  23. Naruei, Iraj, and Farshid Keynia. "Wild Horse Optimizer: A New Meta-Heuristic Algorithm for Solving Engineering Optimization Problems." Engineering with computers 38, no. Suppl 4 (2022): 3025-3056.
  24. Huong, Audrey, KimGaik Tay, KokBeng Gan, and Xavier Ngu. "A Hierarchical Optimisation Framework for Pigmented Lesion Diagnosis." CAAI Transactions on Intelligence Technology 7, no. 1 (2022): 34-45.
  25. Tadisetty, Srikanth, Ranjith Chodavarapu, Ruoming Jin, Robert J. Clements, and Minzhong Yu. "Identifying the Edges of the Optic Cup and the Optic Disc in Glaucoma Patients by Segmentation." Sensors 23, no. 10 (2023): 4668.