Advanced Bi-CNN for Detection of Knee Osteoarthritis using Joint Space Narrowing Analysis
Abstract
The prevalence of knee osteoarthritis is significantly increasing due to the expanding global ageing population and the rising incidence of obesity. Many researchers use artificial intelligence analytics for knee osteoarthritis (KOA) prediction and treatment. The majority of research is restricted to particular patient groups or attributes, such MRI, X-ray, or questionnaire groups. In our research we propose the use of advanced ortho bilinear convolutional neural network (CNN) classifier to enhance the precision of knee osteoarthritis detection through joint space narrowing analysis. Recognizing the critical need for accurate and early diagnosis in osteoarthritis, this study introduces a sophisticated approach leveraging the unique capabilities of bilinear CNNs (BiCNN). By integrating bilinear interactions within the CNN architecture, the model aims to capture convoluted spatial and channel-wise dependencies in knee radiographic images, thereby improving the capability to understated changes in osteoarthritis progression, particularly within the joint space. The proposed bilinear CNN classifier technique promises to refine the precision of knee osteoarthritis detection, providing clinicians with a powerful tool for identifying joint space narrowing with improved accuracy. Based on the experiment over unseen images, the recall was 93.04%, precision 96.33%, F1 Score was 95.46% and overall accuracy was 94.28%. Results show the superiority of the proposed method compared to other state-of-the-art methods. Hence the proposed method can be used for KOA diagnosis and KL grading in real time scenarios.
Downloads
References
C. Ntakolia, C. Kokkotis, S. Moustakidis, and D. Tsaopoulos, “Prediction of Joint Space Narrowing Progression in Knee Osteoarthritis Patients,” Diagnostics, vol. 11, no. 2, p. 285, Feb. 2021, doi: 10.3390/diagnostics11020285.
AN Bing-chen, FANG Kai, WANG You, ZENG Yi-ming, “New variables for measuring joint space width to evaluate knee osteoarthritis”, Chinese Medical Journal 2011, PP. 3886-3890, DOI: 10.3760/cma.j.
W. P. Chan, G.-S. Huang, S.-M. Hsu, Y.-C. Chang, and W.-P. Ho, “Radiographic joint space narrowing inosteoarthritis of the knee: relationship to meniscal tears and duration of pain,” Skeletal Radiology, vol. 37, no. 10, pp. 917–922, Jul. 2008, doi: 10.1007/s00256-008-0530-8.
P. S. Q. Yeoh et al., “Emergence of Deep Learning in Knee Osteoarthritis Diagnosis,” Computational Intelligence and Neuroscience, vol. 2021, pp. 1–20, Nov. 2021, doi: 10.1155/2021/4931437.
J. Hu et al., “DeepKOA: a deep-learning model for predicting progression in knee osteoarthritis using multimodal magnetic resonance images from the osteoarthritis initiative,” Quantitative Imaging in Medicine and Surgery, vol. 13, no. 8, pp. 4852–4866, Aug. 2023, doi: 10.21037/qims-22-1251.
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: 10.3390/app13031658.
U. Yunus, J. Amin, M. Sharif, M. Yasmin, S. Kadry, and S. Krishnamoorthy, “Recognition of Knee Osteoarthritis (KOA) Using YOLOv2 and Classification Based on Convolutional Neural Network,” Life, vol. 12, no. 8, p. 1126, Jul. 2022, doi: 10.3390/life12081126.
B. S. Dhami, M. Mehra, and R. P. Singh, “VGG16 Based Knee Osteoarthritis Grading Using X-Ray Images,” International Journal for Research in Applied Science and Engineering Technology, vol. 10, no. 10, pp. 678–683, Oct. 2022, doi: 10.22214/ijraset.2022.46994.
Virendra Patel, Sanyam Shukla, Manasi Gyanchandani “Analysis of Different Loss Function for Designing Custom CNN for Traffic Sign Recognition” CEUR Workshop Proceedings, Vol. 3269
D. R. Sarvamangala and R. V. Kulkarni, “Grading of Knee Osteoarthritis Using Convolutional Neural Networks,” Neural Processing Letters, vol. 53, no. 4, pp. 2985–3009, May 2021, doi: 10.1007/s11063-021-10529-3.
B. Zhang, J. Tan, K. Cho, G. Chang, and C. M. Deniz, “Attention-based CNN for KL Grade Classification: Data from the Osteoarthritis Initiative,” 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), Apr. 2020, doi: 10.1109/isbi45749.2020.9098456.
J. Antony, K. McGuinness, N. E. O’Connor, and K. Moran, “Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks,” 2016 23rd International Conference on Pattern Recognition (ICPR), Dec. 2016, doi: 10.1109/icpr.2016.7899799.
C. Ntakolia, C. Kokkotis, S. Moustakidis, and D. Tsaopoulos, “A machine learning pipeline for predicting joint space narrowing in knee osteoarthritis patients,” 2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE), Oct. 2020, doi: 10.1109/bibe50027.2020.00158.
T. Sivakumari and R. Vani, “Implementation of AlexNet for Classification of Knee Osteoarthritis,” 2022 7th International Conference on Communication and Electronics Systems (ICCES), Jun. 2022, doi: 10.1109/icces54183.2022.9835835.
R. Madan-Sharma et al., “Do MRI features at baseline predict radiographic joint space narrowing in the medial compartment of the osteoarthritic knee 2 years later?,” Skeletal Radiology, vol. 37, no. 9, pp. 805–811, Sep. 2008, doi: 10.1007/s00256-008-0508-6.
S. S. Abdullah and M. P. Rajasekaran, “Automatic detection and classification of knee osteoarthritis using deep learning approach,” La radiologia medica, vol. 127, no. 4, pp. 398–406, Mar. 2022, doi: 10.1007/s11547-022-01476-7.
S. S., P. U., and R. R., “Detection of Osteoarthritis using Knee X-Ray Image Analyses: A Machine Vision based Approach,” International Journal of Computer Applications, vol. 145, no. 1, pp. 20–26, Jul. 2016, doi: 10.5120/ijca2016910544.
H. H, A. Patrot, B. S, G. S, and L. A, “Knee Osteoarthritis Prediction Using Deep Learning,” 2023 International Conference on Recent Advances in Information Technology for Sustainable Development (ICRAIS), Nov. 2023, doi: 10.1109/icrais59684.2023.10367065.
W. Wirth et al., “Lateral and medial joint space narrowing predict subsequent cartilage loss in the narrowed, but not in the non-narrowed femorotibial compartment – data from the Osteoarthritis Initiative,” Osteoarthritis and Cartilage, vol. 22, no. 1, pp. 63–70, Jan. 2014, doi: 10.1016/j.joca.2013.10.011.
O. M. Babatunde, J. R. Danoff, D. A. Patrick, J. H. Lee, J. K. Kazam, and W. Macaulay, “The Combination of the Tunnel View and Weight-Bearing Anteroposterior Radiographs Improves the Detection of Knee Arthritis,” Arthritis, vol. 2016, pp. 1–8, Jan. 2016, doi: 10.1155/2016/9786924.
O. Cigdem and C. M. Deniz, “Artificial intelligence in knee osteoarthritis: A comprehensive review for 2022,” Osteoarthritis Imaging, vol. 3, no. 3, p. 100161, Sep. 2023, doi: 10.1016/j.ostima.2023.100161.
V. Silverwood, M. Blagojevic-Bucknall, C. Jinks, J. L. Jordan, J. Protheroe, and K. P. Jordan, “Current evidence on risk factors for knee osteoarthritis in older adults: a systematic review and meta-analysis,” Osteoarthritis and Cartilage, vol. 23, no. 4, pp. 507–515, Apr. 2015, doi: 10.1016/j.joca.2014.11.019.
J. C. Buckland-Wright, D. G. Macfarlane, J. A. Lynch, M. K. Jasani, and C. R. Bradshaw, “Joint space width measures cartilage thickness in osteoarthritis of the knee: high resolution plain film and double contrast macroradiographic investigation.,” Annals of the Rheumatic Diseases, vol. 54, no. 4, pp. 263–268, Apr. 1995, doi: 10.1136/ard.54.4.263.
H. A. Alshamrani, M. Rashid, S. S. Alshamrani, and A. H. D. Alshehri, “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, p. 1206, Apr. 2023, doi: 10.3390/healthcare11091206.
J.B. Schiratti et al., “A deep learning method for predicting knee osteoarthritis radiographic progression from MRI,” Arthritis Research & Therapy, vol. 23, no. 1, Oct. 2021, doi: 10.1186/s13075-021-02634-4.
A. Almhdie-Imjabbar, K.-L. Nguyen, H. Toumi, R. Jennane, and E. Lespessailles, “Prediction of knee osteoarthritis progression using radiological descriptors obtained from bone texture analysis and Siamese neural networks: data from OAI and MOST cohorts,” Arthritis Research & Therapy, vol. 24, no. 1, Mar. 2022, doi: 10.1186/s13075-022-02743-8.
P. J. A. Antonio, J. Aldwayne B. Delmo, R. V. Sevilla, M. Angelo D. Ligayo, and D. L. Montesines, “Deep Transfer Network of Knee Osteoarthritis Progression Rate Classification in MR Imaging for Medical Imaging Support System,” 2022 International Conference on Decision Aid Sciences and Applications (DASA), Mar. 2022, doi: 10.1109/dasa54658.2022.9765065.
B. Norman, V. Pedoia, A. Noworolski, T. M. Link, and S. Majumdar, “Applying Densely Connected Convolutional Neural Networks for Staging Osteoarthritis Severity from Plain Radiographs,” Journal of Digital Imaging, vol. 32, no. 3, pp. 471–477, Oct. 2018, doi: 10.1007/s10278-018-0098-3.
B. Guan 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, Apr. 2020, doi: 10.1016/j.joca.2020.01.010.
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.
S. Botha-Scheepers et al., “Fixed-flexion knee radiography: the sensitivity to detect knee joint space narrowing in osteoarthritis,” Osteoarthritis and Cartilage, vol. 15, no. 3, pp. 350–353, Mar. 2007, doi: 10.1016/j.joca.2006.09.006.
G. W. Stachowiak, M. Wolski, T. Woloszynski, and P. Podsiadlo, “Detection and prediction of osteoarthritis in knee and hand joints based on the X-ray image analysis,” Biosurface and Biotribology, vol. 2, no. 4, pp. 162–172, Dec. 2016, doi: 10.1016/j.bsbt.2016.11.004.
F. Khury, M. Fuchs, H. Awan Malik, J. Leiprecht, H. Reichel, and M. Faschingbauer, “Validation of joint space narrowing on plain radiographs and its relevance to partial knee arthroplasty,” Bone & Joint Research, vol. 10, no. 3, pp. 173–187, Mar. 2021, doi: 10.1302/2046-3758.103.bjr-2020-0216.r1.
A. Tack and S. Zachow, “Accurate Automated Volumetry of Cartilage of the Knee Using Convolutional Neural Networks: Data From the Osteoarthritis Initiative,” 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019), Apr. 2019, doi: 10.1109/isbi.2019.8759201.
Y. Du, J. Shan, R. Almajalid, and M. Zhang, “Knee osteoarthritis severity level classification using whole knee cartilage damage Index and ANN,” Proceedings of the 2018 IEEE/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies, Sep. 2018, doi: 10.1145/3278576.3278585.
A. Alexos, C. Kokkotis, S. Moustakidis, E. Papageorgiou, and D. Tsaopoulos, “Prediction of pain in knee osteoarthritis patients using machine learning: Data from Osteoarthritis Initiative,” 2020 11th International Conference on Information, Intelligence, Systems and Applications (IISA, Jul. 2020, doi: 10.1109/iisa50023.2020.9284379.
Copyright (c) 2024 Rahul Kadu, Sunil N. Pawar
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution-ShareAlikel 4.0 International (CC BY-SA 4.0) 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) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
