Utilizing Cascade Deep Metric Learning for the Kellgren-Lawrence Grading of Knee Osteoarthritis Classification from X-Ray Images
Received: 12 January 2026 | Revised: 10 February 2026 | Accepted: 20 February 2026 | Online: 4 April 2026
Corresponding author: Mauridhi Hery Purnomo
Abstract
Accurate automated grading of knee osteoarthritis from X-ray images remains challenging due to inter-radiologist label noise and the inherent ordinal nature of the Kellgren-Lawrence (KL) grading scale. Most existing deep learning approaches address label noise handling, feature embedding, and ordinal modeling as separate components, which limits robustness and consistency across adjacent grades. This study presents a Cascade Deep Metric Learning (CDML) framework that integrates adaptive label reliability updating and ordinal-aware metric learning within a unified cascade design. By iteratively refining feature embeddings under ordinal constraints, the proposed framework explicitly addresses both noisy annotations and ordinal dependencies in KL grading. Experiments conducted on the Osteoarthritis Initiative (OAI) dataset demonstrated that the proposed method achieved an accuracy of 82.12%, a Mean Absolute Error (MAE) of 0.179, and a Quadratic Weighted Kappa (QWK) of 0.935, outperforming baseline deep metric learning methods. Ablation studies further confirmed the effectiveness of the cascade design in improving robustness and preserving clinically consistent ordinal predictions.
Keywords:
cascade deep metric learning, Kellgren–Lawrence grading, knee osteoarthritis, label noise handling, ordinal classificationDownloads
References
L. Qiao et al., ''Epidemiological trends of osteoarthritis at the global, regional, and national levels from 1990 to 2021 and projections to 2050,'' Arthritis Research & Therapy, vol. 27, no. 1, Oct. 2025, Art. no. 199. DOI: https://doi.org/10.1186/s13075-025-03658-w
F. Muttaqin et al., ''A Combination Method of ROI, CLAHE, and DenseNet-169 for Hip Osteoarthritis Detection,'' Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 22690–22697, June 2025. DOI: https://doi.org/10.48084/etasr.10576
D. J. Hunter, L. March, and M. Chew, ''Osteoarthritis in 2020 and beyond: a Lancet Commission,'' The Lancet, vol. 396, no. 10264, pp. 1711–1712, Nov. 2020. DOI: https://doi.org/10.1016/S0140-6736(20)32230-3
K. S. Basavaraju, T. K. Kumar, and K. A. Reddy, ''Vibroarthrographic Signal Classification for Knee Joint Disorder Detection using Tunable Q-factor Wavelet Transform based on Entropy Measures,'' Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19953–19958, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9245
J. H. Kellgren and J. S. Lawrence, ''Radiological Assessment of Osteo-Arthrosis,'' Annals of the Rheumatic Diseases, vol. 16, no. 4, pp. 494–502, Dec. 1957. DOI: https://doi.org/10.1136/ard.16.4.494
J. S. Yoon et al., ''Assessment of a novel deep learning-based software developed for automatic feature extraction and grading of radiographic knee osteoarthritis,'' BMC Musculoskeletal Disorders, vol. 24, no. 1, Nov. 2023, Art. no. 869. DOI: https://doi.org/10.1186/s12891-023-06951-4
S. Beyaz, S. B. Yayli, and K. Kılıç, ''From variability to consistency: building a Kellgren-Lawrence gonarthrosis dataset,'' Journal of Orthopaedic Surgery and Research, vol. 20, no. 1, Oct. 2025, Art. no. 922. DOI: https://doi.org/10.1186/s13018-025-06057-8
A. G. Culvenor, C. N. Engen, B. E. Øiestad, L. Engebretsen, and M. A. Risberg, ''Defining the presence of radiographic knee osteoarthritis: a comparison between the Kellgren and Lawrence system and OARSI atlas criteria,'' Knee Surgery, Sports Traumatology, Arthroscopy, vol. 23, no. 12, pp. 3532–3539, Dec. 2015. DOI: https://doi.org/10.1007/s00167-014-3205-0
K. Klara et al., ''Reliability and Accuracy of Cross-sectional Radiographic Assessment of Severe Knee Osteoarthritis: Role of Training and Experience,'' The Journal of Rheumatology, vol. 43, no. 7, pp. 1421–1426, July 2016. DOI: https://doi.org/10.3899/jrheum.151300
A. S. Buriboev, A. Abduvaitov, and H. S. Jeon, ''Binary Classification of Pneumonia in Chest X-Ray Images Using Modified Contrast-Limited Adaptive Histogram Equalization Algorithm,'' Sensors, vol. 25, no. 13, June 2025, Art. no. 3976. DOI: https://doi.org/10.3390/s25133976
V. Jain, A. K. Dubey, and A. Jain, ''SCDNet 1.0: Adaptive CNN Framework for Sickle Cell Disease Detection with OTSU Segmentation and Gaussian Filter,'' Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology, Dec. 2025, Art. no. 18758967251405463. DOI: https://doi.org/10.1177/18758967251405463
R. R. Sarra, A. E. Korial, I. I. Gorial, and A. J. Humaidi, ''Enhancing Migraine Classification Through Machine Learning: A Comparative Study of Ensemble Methods,'' Technologies, vol. 13, no. 11, Nov. 2025, Art. no. 500. DOI: https://doi.org/10.3390/technologies13110500
Y. Wang, X. Wang, T. Gao, L. Du, and W. Liu, ''An Automatic Knee Osteoarthritis Diagnosis Method Based on Deep Learning: Data from the Osteoarthritis Initiative,'' Journal of Healthcare Engineering, vol. 2021, pp. 1–10, Sept. 2021. DOI: https://doi.org/10.1155/2021/5586529
D. Karimi, H. Dou, S. K. Warfield, and A. Gholipour, ''Deep learning with noisy labels: Exploring techniques and remedies in medical image analysis,'' Medical Image Analysis, vol. 65, Oct. 2020, Art. no. 101759. DOI: https://doi.org/10.1016/j.media.2020.101759
J. Antony, K. McGuinness, N. E. O’Connor, and K. Moran, ''Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks,'' in 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico, Dec. 2016, pp. 1195–1200. DOI: https://doi.org/10.1109/ICPR.2016.7899799
P. Chen, L. Gao, X. Shi, K. Allen, and L. Yang, ''Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss,'' Computerized Medical Imaging and Graphics, vol. 75, pp. 84–92, July 2019. DOI: https://doi.org/10.1016/j.compmedimag.2019.06.002
A. Tiulpin, J. Thevenot, E. Rahtu, P. Lehenkari, and S. Saarakkala, ''Automatic Knee Osteoarthritis Diagnosis from Plain Radiographs: A Deep Learning-Based Approach,'' Scientific Reports, vol. 8, no. 1, Jan. 2018, Art. no. 1727. DOI: https://doi.org/10.1038/s41598-018-20132-7
J. Pan et al., ''Automatic knee osteoarthritis severity grading based on X-ray images using a hierarchical classification method,'' Arthritis Research & Therapy, vol. 26, no. 1, Nov. 2024, Art. no. 203. DOI: https://doi.org/10.1186/s13075-024-03416-4
S. W. Pi, B. D. Lee, M. S. Lee, and H. J. Lee, ''Ensemble deep-learning networks for automated osteoarthritis grading in knee X-ray images,'' Scientific Reports, vol. 13, no. 1, Dec. 2023, Art. no. 22887. DOI: https://doi.org/10.1038/s41598-023-50210-4
Y. Wang et al., ''Learning From Highly Confident Samples for Automatic Knee Osteoarthritis Severity Assessment: Data From the Osteoarthritis Initiative,'' IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 3, pp. 1239–1250, Mar. 2022. DOI: https://doi.org/10.1109/JBHI.2021.3102090
T. Momenpour and A. Abu Mallouh, ''Optimizing CNN-Based Diagnosis of Knee Osteoarthritis: Enhancing Model Accuracy with CleanLab Relabeling,'' Diagnostics, vol. 15, no. 11, May 2025, Art. no. 1332. DOI: https://doi.org/10.3390/diagnostics15111332
K. Simonyan and A. Zisserman, ''Very Deep Convolutional Networks for Large-Scale Image Recognition.'' arXiv, Apr. 10, 2015.
R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, ''Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization,'' presented at the Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 2017, Art. no. 618–626. DOI: https://doi.org/10.1109/ICCV.2017.74
P. Chen, ''Knee Osteoarthritis Severity Grading Dataset.'' Mendeley, Sept. 04, 2018.
J. B. Driban et al., ''The state of the Osteoarthritis Initiative (OAI): Entering a new era,'' Seminars in Arthritis and Rheumatism, vol. 75, Dec. 2025, Art. no. 152887. DOI: https://doi.org/10.1016/j.semarthrit.2025.152887
E. Hoffer and N. Ailon, ''Deep Metric Learning Using Triplet Network,'' in Similarity-Based Pattern Recognition, vol. 9370, A. Feragen, M. Pelillo, and M. Loog, Springer International Publishing, 2015, pp. 84–92. DOI: https://doi.org/10.1007/978-3-319-24261-3_7
D. M. W. Powers, ''Evaluation: from precision, recall and F-measure to ROC, informedness, markedness and correlation.'' arXiv, Oct. 11, 2020.
C. Willmott and K. Matsuura, ''Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance,'' Climate Research, vol. 30, pp. 79–82, 2005. DOI: https://doi.org/10.3354/cr030079
J. Cohen, ''Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit.,'' Psychological Bulletin, vol. 70, no. 4, pp. 213–220, 1968. DOI: https://doi.org/10.1037/h0026256
Downloads
How to Cite
License
Copyright (c) 2026 Supatman, Eko Mulyanto Yuniarno, Mauridhi Hery Purnomo
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.
