An Ensemble Deep Learning Approach for Automated Knee Osteoarthritis Detection Using X-Ray Images
Keywords:
Kellgren-Lawrence (KL) grading, convolutional neural networks, transfer learningAbstract
Osteoarthritis of the knee is a common joint disorder where the cartilage in the knee gradually deteriorates over time. It often causes stiffness, reduced movement, and persistent discomfort, especially in older persons. For better treatment and to stop more joint damage, early identification of KOA and precise evaluation of its severity are essential. In traditional diagnosis, knee X-ray pictures are mostly evaluated visually using the Kellgren-Lawrence (KL) grading system. Hand-reading X-ray pictures takes time and may differ depending on the doctor's experience and preferences. To address these issues, this work proposes an automated deep learning-based method for the detection and classification of knee osteoarthritis from radiography pictures. The suggested method uses transfer learning with two potent convolutional neural network models, InceptionV3 and NASNetLarge, to extract comprehensive information from knee X-ray images. Before starting the model's training, some image processing tasks are finished, including resizing, normalising, and improving the photos. These processes help to enhance the quality of the data and make it possible for the model to perform well on a range of data sources. The program uses the KL grading scale to categorise knee photos into various seriousness levels. Additionally, a group technique is used to aggregate the predictions from both models, improving overall performance and raising the dependability of the classification.
Downloads
References
V. Vijaya Kishore and others: Using Deep Learning and the Kellgren-Lawrence Grading System to Predict Knee Osteoarthritis. Engineering Sciences Proceedings, Volume 05, Issue 3, pages 475-484, 2023.
Kalpana, V., and Hemanth Kumar G.: Evaluating Deep Learning Models for Knee Osteoarthritis Prediction Using the Kellgren-Lawrence Grading System, ePrime Advances in Electrical, Engineering, Electronics, and Energy, 2023.
Tariq, Z. Suhail, and Z. Nawaz: Using X-rays to identify and categorise knee osteoarthritis, IEEE Access, volume 11, pages 48292 to 48303, 2023.
J. Kaur & C.C., Alvaro & M. Kermani & R. A thorough analysis of the current NIST standards' implementations, attacks, and defences. standard for lightweight cryptography (2023).
The impact of class imbalance in the VeReMi dataset on identifying misbehaviour in autonomous vehicles was investigated by S.C. Sangapu, K.S.N. Prasad, R.J. Kannan, and others; the study was published in Soft Computing in 2023.
C.C., Alvaro & J. Kaur & M.K., Mehran & R. Algorithmic security is inadequate: a thorough analysis of implementation assaults endangering post-quantum security (2023)
A. Tiwari, M. Poduval, V. Bagaria: Using deep learning algorithms to evaluate artificial intelligence models for knee osteoarthritis in orthopaedic X-rays, World J. Orthop. 13 (6) (2022) 603-614.
The Knee OsteoArthritis Prediction (KNOAP2020) challenge is an image processing task that uses MRI and X-ray data to predict incidence symptomatic radiographic knee osteoarthritis. S10–S11, 2022.
[9] A survey titled "Al-big data analytics for building automation and management systems: a survey, actual challenges and future perspectives" was written by Y. Himeur, M. Elnour, F. Fadli, and others and published in the journal Artif. Intell. Rev. 56 (2023) 4929-5021.
M. Yang, C. Colak, K.K. Chundru, and others: Generative adversarial networks with transfer learning for automated knee cartilage segmentation for various clinical MRI images, Quantitative Imaging in Medicine and Surgery, volume 12, issue 5, pages 2620-2633, 2022.
S. Ebrahimkhani, M. H. Jaward, F. M. Cicuttini, A. Dharmaratne, Y. Wang, and A. G. S. de Herrera, "A review on segmentation of knee articular cartilage: from conventional methods towards deep learning," Artificial Intelligence in Medicine, vol. 106, p. 101851, Dec. 2020.
"Deep residual learning for image recognition," by K. He, X. Zhang, S. Ren, and J. Sun, Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778, 2016.
A. Razmjoo, F. Liu, F. Caliva, A. M. Martinez, S. Majumdar, and V. Pedoia, "Semi-supervised graph-based deep learning for multi-modal prediction of knee osteoarthritis incidence," Osteoarthritis and Cartilage, vol. 28, pp. S305-S306, 2020.
Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6–12, 2014, Proceedings, Part I, ser. LNCS, vol. 8693, pp. 818–833, Springer, 2014, M. D. Zeiler and R. Fergus, "Visualising and understanding convolutional networks."
B. Norman, V. Pedoia, A. Noworolski, T. M. Link, and S. Majumdar, "Using densely connected convolutional neural networks for staging osteoarthritis severity from plain radiographs," Journal of Digital Imaging, vol. 32, no. 3, pp. 471-477, June 2019.
Neogi, T., "The epidemiology and impact of pain in osteoarthritis," Osteoarthritis and Cartilage, vol. 21, no. 9, pp. 1145-1153, Sep. 2013.
Varma, M., Lu, R. Gardner, J. Dunnmon, N. Khandwala, P. Rajpurkar, et al., "Automated abnormality detection in lower extremity radiographs using deep learning," Nature Machine Intelligence, vol. 1, no. 12, pp. 578-583, Dec. 2019.
Guan, B., F. Liu, A. Haj-Mirzaian, S. Demehri, A. Samsonov, T. Neogi, et al., "Deep learning risk assessment models for predicting progression of radiographic medial joint space loss over a 48-MONTH follow-up period," Osteoarthritis and Cartilage, vol. 28, no. 4, pp. 428-437, April 2020.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Journal of Scientific Research in Science and Technology
This work is licensed under a Creative Commons Attribution 4.0 International License.
https://creativecommons.org/licenses/by/4.0
