Classification of Severity of Osteoarthritis using Artificial Intelligence
Keywords:
Convolutional Neural Network (CNN), Deep learning, Knee osteoarthritis, Machine learning, X-RayAbstract
Background: Osteoarthritis (OA) is a highly common form of arthritis that affects millions of people worldwide. It forms as a tissue barrier known as cartilage, which cushions the ends of bones and deteriorates over time.
Objectives: The primary objective of this study is to predict the severity of knee osteoarthritis in individuals.
Methods and Materials: The proposed method is a deep-learning framework designed to automatically assess the severity of knee osteoarthritis by classifying the Kellgren and Lawrence (KL) grade from knee X-rays. Convolutional Neural Network (CNN) models are used to predict severity, taking into account key factors such as joint space narrowing, osteophyte formation, and bone deformities over time.
Results: The architecture described, based on ResNet50, PCA (Principal Component Analysis), and FeedForward Neural Network, is a comprehensive approach to detecting knee osteoarthritis in its early stages. PCA and ResNet integration enhances the interpretability, which enables medical professionals to identify the features that most significantly impact the model's predictions.
Conclusions: In conclusion, integrating ResNet for feature extraction, PCA for dimensionality reduction, and FFNN for classification allows the model to identify complex patterns related to early-stage osteoarthritis. By leveraging deep learning and dimensionality reduction techniques, the proposed architecture effectively captures subtle indicators that reflect the severity of the disease.
References
K. He, X. Zhang, S. Ren, and J. Sun, “Deep Residual Learning for Image Recognition,” arXiv.org, Dec. 10, 2015. https://arxiv.org/abs/1512.03385
R. T. Wahyuningrum, L. Anifah, E. Purnama, and M. Hery Purnomo, “A New Approach to Classify Knee Osteoarthritis Severity from Radiographic Images based on CNN-LSTM Method,” In2019 IEEE 10th International Conference on Awareness Science and Technology, Oct. 2019, doi: https://doi.org/10.1109/icawst.2019.8923284
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, Jul. 2019, doi: https://doi.org/10.1016/j.compmedimag.
06.002
H. Bonakdari, A. Jamshidi, J.-P. Pelletier, F. Abram, G. Tardif, and J. Martel-Pelletier, “A warning machine learning algorithm for early knee osteoarthritis structural progressor patient screening,” Therapeutic Advances in Musculoskeletal Disease, vol. 13, pp. 1759720X2199325–1759720X2199325, Jan. 2021, doi: https://doi.org/10.1177/1759720x21993254
M. Górriz, J. Antony, K. McGuinness, X. Giró-i-Nieto, and N. E. O’Connor, “Assessing Knee OA Severity with CNN attention-based end-to-end architectures,” arXiv.org, 2019. https://arxiv.org/abs/1908.08856
S. B. Kwon, H.-S. Han, M. C. Lee, H. C. Kim, Y. Ku, and D. H. Ro, “Machine Learning-Based Automatic Classification of Knee Osteoarthritis Severity Using Gait Data and Radiographic Images,” IEEE Access, vol. 8, pp. 120597–120603, 2020, doi: https://doi.org/10.1109/access.2020.3006335
R. K. Jain, P. Kumar Sharma, S. Gaj, A. Sur, and P. Ghosh, “Knee osteoarthritis severity prediction using an attentive multi-scale deep convolutional neural network,” Multimedia tools and applications, Jun. 2023, doi: https://doi.org/10.1007/s11042-023-15484-w
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, Sep. 2021, doi: https://doi.org/10.1155/2021/5586529
R. Mahum, “A Novel Hybrid Approach Based on Deep CNN Features to Detect Knee Osteoarthritis,” Sensors, vol. 21, no. 18, p. 6189, Sep. 2021, doi: https://doi.org/10.3390/s21186189
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, p. 1380, Jan. 2023, doi: https://doi.org/10.3390/diagnostics13081380
A. Liu, J. Luo, and H. Huang, “Toward automatic quantification of knee osteoarthritis severity using improved Faster R-CNN,” International Journal of Computer Assisted Radiology and Surgery, vol. 15, no. 3, pp. 457–466, Jan. 2020, doi: https://doi.org/10.1007/s11548-019-02096-9
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 Transactions on Intelligent Technology, vol. 7, no. 3, pp. 512–521, Mar. 2022, doi: https://doi.org/10.1049/cit2.12079.
A. Swiecicki, N. Li, J. O'Donnell, “Deep learning-based algorithm for assessment of knee osteoarthritis severity in radiographs matches performance of radiologists,” Computers in Biology and Medicine, vol. 133, p. 104334, Jun. 2021, doi: https://doi.org/10.1016/j.compbiomed.2021.104334
K. A. Thomas, L. Kidziński, “Automated Classification of Radiographic Knee Osteoarthritis Severity Using Deep Neural Networks,” Radiology: Artificial Intelligence, vol. 2, no. 2, p. e190065, Mar. 2020, doi: https://doi.org/10.1148/ryai.2020190065
S. M. Ahmed and R. J. Mstafa, “Identifying Severity Grading of Knee Osteoarthritis from X-ray Images Using an Efficient Mixture of Deep Learning and Machine Learning Models,” Diagnostics, vol. 12, no. 12, p. 2939, Nov. 2022, doi: https://doi.org/10.3390/diagnostics12122939
G. K. M and A. D. Goswami, “Automatic Classification of the Severity of Knee Osteoarthritis Using Enhanced Image Sharpening and CNN,” Applied Sciences, vol. 13, no. 3, p. 1658, Jan. 2023, doi: https://doi.org/10.3390/app13031658
S. S. Abdullah and M. P. Rajasekaran, “Automatic detection and classification of knee osteoarthritis using a deep learning approach,” La Radiologia Medica, Mar. 2022, doi: https://doi.org/10.1007/s11547-022-01476-7
H. A. Alshamrani, M. Rashid, S. S. Alshamrani, and Ali, “Osteo-NeT: An Automated System for Predicting Knee Osteoarthritis from X-ray Images Using Transfer-Learning-Based Neural Networks Approach,” Healthcare, vol. 11, no. 9, pp. 1206–1206, Apr. 2023, doi: https://doi.org/10.3390/healthcare11091206
T. Tariq, Z. Suhail, and Z. Nawaz, “Knee Osteoarthritis Detection and Classification Using X-Rays,” IEEE Access, vol. 11, pp. 48292–48303, Jan. 2023, doi: https://doi.org/10.1109/access.2023.3276810
S. Abd El-Ghany and M. Elmogy, “A fully automatic fine-tuned deep learning model for knee osteoarthritis detection and progression analysis,” Egyptian Informatics Journal, vol. 24, no. 2, pp. 229–240, Jul. 2023, doi: https://doi.org/10.1016/j.eij.2023.03.005
