Multiclass Diabetic Retinopathy: Hybrid Metaheuristic Particle Swarm Optimization and Classification for Severity Grading and Feature Extraction
Received: 26 March 2025 | Revised: 27 April 2025, 8 May 2025, and 13 May 2025 | Accepted: 15 May 2025 | Online: 8 December 2025
Corresponding author: Shahrulniza Musa
Abstract
This study aimed to effectively classify a Diabetic Retinopathy (DR) image dataset consisting of colored images by developing a hybrid and robust transfer learning model called MOB-PSO, integrating MobileNet with Particle Swarm Optimization (PSO) to enhance performance and accuracy. A well-structured dataset is crucial for building a high-performance model capable of accurate feature extraction and precise identification of image features within each class. Traditional statistical algorithms often struggle to classify colored images accurately, leading to errors in detecting diseases within DR image datasets. To reduce error rates and improve classification accuracy, this study developed a hybrid, reliable, and optimized image classification model. The DR dataset consists of ten distinct classes. Experimental results demonstrate that the MOB-PSO model surpasses state-of-the-art algorithms in terms of accuracy, robustness, precision, recall, and F1 score, achieving optimal validation loss values. Specifically, the MOB-PSO model recorded training and validation losses of 0.1515 and 0.1853, respectively, with corresponding accuracies of 98.58% and 96.7%. The precision, recall, and F1-score were 0.9744, 0.9657, and 0.9698, respectively, showcasing the model's effectiveness.
Keywords:
MobileNet, CNN, deep learning, diabetic retinopathy, Particle Swarm Optimization (PSO)Downloads
References
A. Voulodimos, N. Doulamis, A. Doulamis, and E. Protopapadakis, "Deep Learning for Computer Vision: A Brief Review," Computational Intelligence and Neuroscience, vol. 2018, pp. 1–13, 2018. DOI: https://doi.org/10.1155/2018/7068349
D. Vallabha, R. Dorairaj, K. Namuduri, and H. Thompson, "Automated detection and classification of vascular abnormalities in diabetic retinopathy," in Conference Record of the Thirty-Eighth Asilomar Conference on Signals, Systems and Computers, 2004., Pacific Grove, CA, USA, 2004, vol. 2, pp. 1625–1629. DOI: https://doi.org/10.1109/ACSSC.2004.1399432
G. Wang, "A Perspective on Deep Imaging," IEEE Access, vol. 4, pp. 8914–8924, 2016. DOI: https://doi.org/10.1109/ACCESS.2016.2624938
A. A. Siddique, A. Raza, M. S. Alshehri, N. Alasbali, and S. F. Abbasi, "Optimizing Tumor Classification Through Transfer Learning and Particle Swarm Optimization-Driven Feature Extraction," IEEE Access, vol. 12, pp. 85929–85939, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3412412
G. Litjens et al., "A survey on deep learning in medical image analysis," Medical Image Analysis, vol. 42, pp. 60–88, Dec. 2017. DOI: https://doi.org/10.1016/j.media.2017.07.005
M. Puttagunta and S. Ravi, "Medical image analysis based on deep learning approach," Multimedia Tools and Applications, vol. 80, no. 16, pp. 24365–24398, Jul. 2021. DOI: https://doi.org/10.1007/s11042-021-10707-4
A. Sopharak and B. Uyyanonvara, "Automatic exudates detection from diabetic retinopathy retinal image using fuzzy c-means and morphological methods," in Proceedings of the Third IASTED International Conference Advances in Computer Science and Technology, 2007, pp. 359–364.
P. Uppamma and S. Bhattacharya, "Deep Learning and Medical Image Processing Techniques for Diabetic Retinopathy: A Survey of Applications, Challenges, and Future Trends," Journal of Healthcare Engineering, vol. 2023, no. 1, Jan. 2023, Art. no. 2728719. DOI: https://doi.org/10.1155/2023/2728719
C. Mohanty et al., "Using Deep Learning Architectures for Detection and Classification of Diabetic Retinopathy," Sensors, vol. 23, no. 12, Jun. 2023, Art. no. 5726. DOI: https://doi.org/10.3390/s23125726
F. H. Kuwil, "A new feature extraction approach of medical image based on data distribution skew," Neuroscience Informatics, vol. 2, no. 3, Sep. 2022, Art. no. 100097. DOI: https://doi.org/10.1016/j.neuri.2022.100097
S. Karthika and M. Durgadevi, "IMDE-UGAN: Improved Memetic Direction Exploitation Optimized U-Net Generative Adversarial Network for Classification of Diabetic Retinopathy," IETE Journal of Research, vol. 70, no. 8, pp. 6802–6818, Aug. 2024. DOI: https://doi.org/10.1080/03772063.2024.2310111
P. Melin, D. Sánchez, and R. Cordero-Martínez, "Particle Swarm Optimization of Convolutional Neural Networks for Diabetic Retinopathy Classification," in Fuzzy Logic and Neural Networks for Hybrid Intelligent System Design, vol. 1061, O. Castillo and P. Melin, Eds. Springer International Publishing, 2023, pp. 237–252. DOI: https://doi.org/10.1007/978-3-031-22042-5_14
E. Barges and E. Thabet, "GLDM and Tamura features based KNN and particle swarm optimization for automatic diabetic retinopathy recognition system," Multimedia Tools and Applications, vol. 82, no. 1, pp. 271–295, Jan. 2023. DOI: https://doi.org/10.1007/s11042-022-13282-4
M. Hussain et al., "An Enhanced Convolutional Neural Network (CNN) based P-EDR Mechanism for Diagnosis of Diabetic Retinopathy (DR) using Machine Learning," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19062–19067, Feb. 2025. DOI: https://doi.org/10.48084/etasr.8854
R. Ramesh and S. Sathiamoorthy, "A Deep Learning Grading Classification of Diabetic Retinopathy on Retinal Fundus Images with Bio-inspired Optimization," Engineering, Technology & Applied Science Research, vol. 13, no. 4, pp. 11248–11252, Aug. 2023. DOI: https://doi.org/10.48084/etasr.6033
J. Ramya, M. P. Rajakumar, and B. U. Maheswari, "Deep CNN with Hybrid Binary Local Search and Particle Swarm Optimizer for Exudates Classification from Fundus Images," Journal of Digital Imaging, vol. 35, no. 1, pp. 56–67, Feb. 2022. DOI: https://doi.org/10.1007/s10278-021-00534-2
A. Raza, S. B. Musa, A. S. B. Khalid, M. M. Alam, M. M. Su’ud, and F. Noor, "Enhancing Medical Image Classification Through PSO-Optimized Dual Deterministic Approach and Robust Transfer Learning," IEEE Access, vol. 12, pp. 177144–177159, 2024. DOI: https://doi.org/10.1109/ACCESS.2024.3504266
A. M. Javid, S. Das, M. Skoglund, and S. Chatterjee, "A ReLU Dense Layer to Improve the Performance of Neural Networks," in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, Canada, Jun. 2021, pp. 2810–2814. DOI: https://doi.org/10.1109/ICASSP39728.2021.9414269
A. Krizhevsky, I. Sutskever, and G. E. Hinton, "ImageNet classification with deep convolutional neural networks," Communications of the ACM, vol. 60, no. 6, pp. 84–90, May 2017. DOI: https://doi.org/10.1145/3065386
A. Raza, M. S. Alshehri, S. Almakdi, A. A. Siddique, M. Alsulami, and M. Alhaisoni, "Enhancing brain tumor classification with transfer learning: Leveraging DenseNet121 for accurate and efficient detection," International Journal of Imaging Systems and Technology, vol. 34, no. 1, Jan. 2024, Art. no. e22957. DOI: https://doi.org/10.1002/ima.22957
Y. Tian, Y. Zhang, and H. Zhang, "Recent Advances in Stochastic Gradient Descent in Deep Learning," Mathematics, vol. 11, no. 3, Jan. 2023, Art. no. 682. DOI: https://doi.org/10.3390/math11030682
E. Jeczmionek and P. A. Kowalski, "Flattening Layer Pruning in Convolutional Neural Networks," Symmetry, vol. 13, no. 7, Jun. 2021, Art. no. 1147. DOI: https://doi.org/10.3390/sym13071147
Y. B. Özçelik and A. Altan, "Overcoming Nonlinear Dynamics in Diabetic Retinopathy Classification: A Robust AI-Based Model with Chaotic Swarm Intelligence Optimization and Recurrent Long Short-Term Memory," Fractal and Fractional, vol. 7, no. 8, Aug. 2023, Art. no. 598. DOI: https://doi.org/10.3390/fractalfract7080598
A. M. Dayana and W. R. S. Emmanuel, "An enhanced swarm optimization-based deep neural network for diabetic retinopathy classification in fundus images," Multimedia Tools and Applications, vol. 81, no. 15, pp. 20611–20642, Jun. 2022. DOI: https://doi.org/10.1007/s11042-022-12492-0
S. Sundaram et al., "Diabetic Retinopathy and Diabetic Macular Edema Detection Using Ensemble Based Convolutional Neural Networks," Diagnostics, vol. 13, no. 5, Mar. 2023, Art. no. 1001. DOI: https://doi.org/10.3390/diagnostics13051001
S. Lakhera and A. Garg, "Diabetic Retinopathy Classification Using PSOSVM Based Deep Learning Model," in 2023 Seventh International Conference on Image Information Processing (ICIIP), Solan, India, Nov. 2023, pp. 183–187. DOI: https://doi.org/10.1109/ICIIP61524.2023.10537630
O. Higgins and C. Thompson, "Combination of artificial neural network and particle swarm intelligence algorithm for diagnosing diabetes," Advances in Engineering and Intelligence Systems, vol. 3, no. 1, Mar. 2024.
R. G. Tiwari and A. Kumar, "Integrated Transfer Learning and Nature-Inspired Optimization for Enhanced Feature Extraction in Diabetic Retinopathy Image Analysis," in 2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS), Manama, Bahrain, Jan. 2024, pp. 1–6. DOI: https://doi.org/10.1109/ICETSIS61505.2024.10459394
L. Xiao et al., "HHO optimized support vector machine classifier for traditional Chinese medicine syndrome differentiation of diabetic retinopathy," International Journal of Ophthalmology, vol. 17, no. 6, pp. 991–1000, Jun. 2024. DOI: https://doi.org/10.18240/ijo.2024.06.02
V. Sapra et al., "Diabetic Retinopathy Detection Using Deep Learning with Optimized Feature Selection," Traitement du Signal, vol. 41, no. 2, pp. 781–790, Apr. 2024. DOI: https://doi.org/10.18280/ts.410219
L. K. Singh, M. Khanna, and R. Singh, "Feature subset selection through nature inspired computing for efficient glaucoma classification from fundus images," Multimedia Tools and Applications, vol. 83, no. 32, pp. 77873–77944, Feb. 2024. DOI: https://doi.org/10.1007/s11042-024-18624-y
"National Medical Centre." https://nmc.net.pk/.
Downloads
How to Cite
License
Copyright (c) 2025 Asif Raza, Shahrulniza Musa, Ahmad Shahrafidz Bin Khalid, Muhammad Mansoor Alam, Mazliham Mohd Su’ud, Fouzia Noor
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
