Improving Knee Osteoarthritis Classification Using Swarm-Based Optimization and Deep Learning Models

Dilan Jameel Sulaiman; Baraa Wasfi Salim

doi:10.65542/djei.v2i2.42

Authors

Dilan Jameel Sulaiman Information Technology Management Department, Technical College of Administration, Duhok Polytechnic University, Duhok, Iraq https://orcid.org/0009-0006-4840-1753
Baraa Wasfi Salim Information Technology Management Department, Technical College of Administration, Duhok Polytechnic University, Duhok, Iraq

DOI:

https://doi.org/10.65542/djei.v2i2.42

Keywords:

Knee Osteoarthritis, Particle Swarm Optimization, Deep Learning, Convolutional Neural Network, X-ray, Image Classification

Abstract

Knee Osteoarthritis (KOA) is a persistent and expensive joint condition which can be accurately identified with radiographic examination. This study suggests combining deep models with swarm intelligence to diagnose KOA through X-ray images. A systematic review was carried out to find the best strategies for detecting KOA. After the data preprocessing, features were obtained by using the pre-trained CNNs (EfficientNetB0, VGG19, ResNet50, MobileNetV2) model. Multilayer Perceptron (MLP) classifiers were trained using the features obtained. The collected features of both models were fed into classifiers like MLP. In the second phase, optimal MLP hyperparameters were calibrated via Particle Swarm Optimization (PSO) to improve the classification performance. The experiments were conducted on a balanced dataset containing 10,000 knee X-ray images across five KL grades. Among all the models we investigated, the VGG19 along with PSO and MLP achieved the accuracy of 98.8% on test set. The model also achieved 98.8% precision, 98.8% recall, and 98.8% F1-score, outperforming the corresponding non-optimized baseline models. The results indicate that the integration of swarm systems with deep learning significantly enhances the recognition performance of KOA grade. Based on such a technique, clinicians of the field of orthopedics would be able to diagnose at an earlier stage more easily and accurately.

References

R. Ahmed and A. Shariq Imran, “Knee Osteoarthritis Analysis Using Deep Learning and XAI on X-rays,” IEEE Access, 2024, doi: 10.1109/ACCESS.2017.DOI. DOI: https://doi.org/10.1109/ACCESS.2024.3400987

X. Wang, S. Liu, and C. Zhou, “Classification of Knee Osteoarthritis Based on Transfer Learning Model and Magnetic Resonance Images,” in Proceedings - 2022 International Conference on Machine Learning, Control, and Robotics, MLCR 2022, Institute of Electrical and Electronics Engineers Inc., 2022, pp. 67–71. doi: 10.1109/MLCR57210.2022.00021. DOI: https://doi.org/10.1109/MLCR57210.2022.00021

D. Shen, G. Wu, and H. Il Suk, “Deep Learning in Medical Image Analysis,” Annu Rev Biomed Eng, vol. 19, pp. 221–248, Jun. 2017, doi: 10.1146/annurev-bioeng-071516-044442. DOI: https://doi.org/10.1146/annurev-bioeng-071516-044442

J. Qadir, “Enhancing Skin Disease Diagnosis: A Hybrid Approach Combining Vision Transformer and Feature Selection Techniques.,” Zanin Journal of Science and Engineering, vol. 1, no. 1, pp. 54–71, Mar. 2025, doi: 10.64362/zjse.37. DOI: https://doi.org/10.64362/zjse.37

M. Jahan et al., “KOA-CCTNet: An Enhanced Knee Osteoarthritis Grade Assessment Framework Using Modified Compact Convolutional Transformer Model,” IEEE Access, vol. 12, pp. 107719–107741, 2024, doi: 10.1109/ACCESS.2024.3435572. DOI: https://doi.org/10.1109/ACCESS.2024.3435572

M. D. Fall, “Quantifying Uncertainty in Knee Osteoarthritis Diagnosis,” in Proceedings - International Symposium on Biomedical Imaging, IEEE Computer Society, 2024. doi: 10.1109/ISBI56570.2024.10635586.

A. Khalid, E. M. Senan, K. Al-Wagih, M. M. Ali Al-Azzam, and Z. M. Alkhraisha, “Hybrid Techniques of X-ray Analysis to Predict Knee Osteoarthritis Grades Based on Fusion Features of CNN and Handcrafted,” Diagnostics, vol. 13, no. 9, May 2023, doi: 10.3390/diagnostics13091609. DOI: https://doi.org/10.3390/diagnostics13091609

D. Sarkar, T. Khan, and F. Ahmed Talukdar, “Hyperparameters optimization of neural network using improved particle swarm optimization for modeling of electromagnetic inverse problems,” Int J Microw Wirel Technol, vol. 14, no. 10, pp. 1326–1337, Dec. 2022, doi: 10.1017/S1759078721001690. DOI: https://doi.org/10.1017/S1759078721001690

J. Wang, Z. Lei, X. Chang, and D. Huang, “IPSO-CNN: Malicious Code Classification with Improved PSO Optimized CNN,” in 2023 5th International Conference on Frontiers Technology of Information and Computer, ICFTIC 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 906–910. doi: 10.1109/ICFTIC59930.2023.10455878. DOI: https://doi.org/10.1109/ICFTIC59930.2023.10455878

A. Qadir, R. Mahum, and S. Aladhadh, “A Robust Approach for Detection and Classification of KOA Based on BILSTM Network,” Computer Systems Science and Engineering, vol. 47, no. 2, pp. 1365–1384, 2023, doi: 10.32604/csse.2023.037033. DOI: https://doi.org/10.32604/csse.2023.037033

T. Momenpour and A. Abu Mallouh, “Optimizing CNN-Based Diagnosis of Knee Osteoarthritis: Enhancing Model Accuracy with CleanLab Relabeling,” Diagnostics, vol. 15, no. 11, p. 1332, May 2025, doi: 10.3390/diagnostics15111332. DOI: https://doi.org/10.3390/diagnostics15111332

Y. Wang, S. Li, B. Zhao, J. Zhang, Y. Yang, and B. Li, “A ResNet-based approach for accurate radiographic diagnosis of knee osteoarthritis,” CAAI Trans Intell Technol, vol. 7, no. 3, pp. 512–521, Sep. 2022, doi: 10.1049/cit2.12079. DOI: https://doi.org/10.1049/cit2.12079

A. S. Mohammed, A. A. Hasanaath, G. Latif, and A. Bashar, “Knee Osteoarthritis Detection and Severity Classification Using Residual Neural Networks on Preprocessed X-ray Images,” Diagnostics, vol. 13, no. 8, Apr. 2023, doi: 10.3390/diagnostics13081380. DOI: https://doi.org/10.3390/diagnostics13081380

B. Bugday, H. Bingol, M. Yildirim, and B. Alatas, “Enhancing knee osteoarthritis detection with AI, image denoising, and optimized classification methods and the importance of physical therapy methods,” PeerJ Comput Sci, Feb. 2025, doi: 10.7717/peerj. DOI: https://doi.org/10.7717/peerj-cs.2766

P. S. Q. Yeoh, K. W. Lai, S. L. Goh, K. Hasikin, X. Wu, and P. Li, “Transfer learning-assisted 3D deep learning models for knee osteoarthritis detection: Data from the osteoarthritis initiative,” Front Bioeng Biotechnol, vol. 11, 2023, doi: 10.3389/fbioe.2023.1164655. DOI: https://doi.org/10.3389/fbioe.2023.1164655

S. Rani et al., “Deep learning to combat knee osteoarthritis and severity assessment by using CNN-based classification,” BMC Musculoskelet Disord, vol. 25, no. 1, Dec. 2024, doi: 10.1186/s12891-024-07942-9. DOI: https://doi.org/10.1186/s12891-024-07942-9

H. Harish, A. Patrot, S. Bhavan, S. Gousiya, and A. Livitha, “Knee Osteoarthritis Prediction Using Deep Learning,” in 2023 International Conference on Recent Advances in Information Technology for Sustainable Development, ICRAIS 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 14–19. doi: 10.1109/ICRAIS59684.2023.10367065. DOI: https://doi.org/10.1109/ICRAIS59684.2023.10367065

T. M. Shami, A. A. El-Saleh, M. Alswaitti, Q. Al-Tashi, M. A. Summakieh, and S. Mirjalili, “Particle Swarm Optimization: A Comprehensive Survey,” IEEE Access, vol. 10, pp. 10031–10061, 2022, doi: 10.1109/ACCESS.2022.3142859. DOI: https://doi.org/10.1109/ACCESS.2022.3142859

T. Li, H. Luo, and C. Wu, “A PSO-based fine-tuning algorithm for CNN,” in Proceedings of 2021 5th Asian Conference on Artificial Intelligence Technology, ACAIT 2021, Institute of Electrical and Electronics Engineers Inc., 2021, pp. 704–709. doi: 10.1109/ACAIT53529.2021.9731225. DOI: https://doi.org/10.1109/ACAIT53529.2021.9731225

S. U. Rehman and V. Gruhn, “A Sequential VGG16+CNN-Based Automated Approach With Adaptive Input for Efficient Detection of Knee Osteoarthritis Stages,” IEEE Access, vol. 12, pp. 62407–62415, 2024, doi: 10.1109/ACCESS.2024.3395062. DOI: https://doi.org/10.1109/ACCESS.2024.3395062

G. Harish Kumar and K. Jaisharma, “Enhancing the Handwritten Digit Recognition by Employing Novel Progressive VGG19 Model and Compare with SVM Performance,” in 2024 15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024, Institute of Electrical and Electronics Engineers Inc., 2024. doi: 10.1109/ICCCNT61001.2024.10724278. DOI: https://doi.org/10.1109/ICCCNT61001.2024.10724278

M. I. F. Jamil, R. Samad, D. Pebrianti, M. Mustafa, N. R. H. Abdullah, and N. H. Noordin, “A Comparative Study of Deep Learning Models for the Classification of Knee Osteoarthritis in X-Ray Images,” Institute of Electrical and Electronics Engineers (IEEE), Sep. 2024, pp. 228–233. doi: 10.1109/icom61675.2024.10652557. DOI: https://doi.org/10.1109/ICOM61675.2024.10652557

A. Haseeb et al., “Knee Osteoarthritis Classification Using X-Ray Images Based on Optimal Deep Neural Network,” Computer Systems Science and Engineering, vol. 47, no. 2, pp. 2397–2415, 2023, doi: 10.32604/csse.2023.040529. DOI: https://doi.org/10.32604/csse.2023.040529

A. Asnidar et al., “Application of MobileNetV2 Architecture to Classification of Knee Osteoarthritis Based on X-ray Images,” in 2023 International Conference on Advanced Mechatronics, Intelligent Manufacture and Industrial Automation, ICAMIMIA 2023 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 375–380. doi: 10.1109/ICAMIMIA60881.2023.10427581. DOI: https://doi.org/10.1109/ICAMIMIA60881.2023.10427581

R. Singh, N. Sharma, D. Upadhyay, S. Devliyal, and R. Gupta, “A Fine-Tuned EfficientNet B5 Transfer Learning Model for the Classification of Knee Osteoarthritis,” in 2023 3rd International Conference on Smart Generation Computing, Communication and Networking, SMART GENCON 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/SMARTGENCON60755.2023.10442712. DOI: https://doi.org/10.1109/SMARTGENCON60755.2023.10442712

A. Pandey and V. Kumar, “Enhancing Knee Osteoarthritis Severity Classification using Improved Efficientnet,” in 2023 10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering, UPCON 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 1351–1356. doi: 10.1109/UPCON59197.2023.10434740. DOI: https://doi.org/10.1109/UPCON59197.2023.10434740

R. Singh, N. Sharma, R. Chauhan, D. Rawat, and R. Gupta, “Knee Osteoarthritis Classification Using EfficientNet B3 Transfer Learning Model,” in 2023 2nd International Conference on Futuristic Technologies, INCOFT 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/INCOFT60753.2023.10425390. DOI: https://doi.org/10.1109/INCOFT60753.2023.10425390

T. Tariq, Z. Suhail, and Z. Nawaz, “Knee Osteoarthritis Detection and Classification Using X-Rays,” IEEE Access, vol. 11, pp. 48292–48303, 2023, doi: 10.1109/ACCESS.2023.3276810. DOI: https://doi.org/10.1109/ACCESS.2023.3276810

Y. X. Teoh, A. Othmani, S. L. Goh, J. Usman, and K. W. Lai, “Predicting Knee Osteoarthritis Pain Severity through A Deep Hybrid Learning Model: Data from the Osteoarthritis Initiative,” in Proceedings - 2023 2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023, Institute of Electrical and Electronics Engineers Inc., 2023, pp. 4148–4153. doi: 10.1109/BIBM58861.2023.10385415. DOI: https://doi.org/10.1109/BIBM58861.2023.10385415

A. Marimuthu, A. R. Kavitha, and S. S. Abdullah, “Minimal Knee Joint Space Width Detection in Digital X-Ray Images using Deep Learning,” in 2023 International Conference on Data Science, Agents and Artificial Intelligence, ICDSAAI 2023, Institute of Electrical and Electronics Engineers Inc., 2023. doi: 10.1109/ICDSAAI59313.2023.10452517. DOI: https://doi.org/10.1109/ICDSAAI59313.2023.10452517

V. Bhateja et al., “Ensemble CNN Model for Computer-Aided Knee Osteoarthritis Diagnosis,” International Journal of Service Science, Management, Engineering, and Technology, vol. 15, no. 1, 2024, doi: 10.4018/IJSSMET.349913. DOI: https://doi.org/10.4018/IJSSMET.349913

M. D. Fall, “Quantifying Uncertainty in Knee Osteoarthritis Diagnosis,” in Proceedings - International Symposium on Biomedical Imaging, IEEE Computer Society, 2024. doi: 10.1109/ISBI56570.2024.10635586. DOI: https://doi.org/10.1109/ISBI56570.2024.10635586