Abstract
Knee osteoarthritis (OA) is a common musculoskeletal illness. To solve the problem that inaccurate knee joint localization and inadequate knee OA features extracted from plain radiographs affect the accuracy of knee OA diagnosis in X-rays, we propose a novel Two-Stage Convolutional Neural Network (TS-CNN) method, consisting of the KneeDetnet and the KLnet. The KneeDetnet with two small multi-task convolutional neural networks is proposed to locate knee joints, improving the accuracy of knee joint localization. Then KLnet is designed to assess knee OA, where a shared Siamese network via ResNet is used to extract more discriminative deep learning features that are fused with gender information for obtaining richer features. Our method is evaluated on public OAI and MOST datasets. The highest detection accuracy of knee joints can reach 99.93% and 99.02% on two datasets, respectively. The KLnet algorithm achieves 78.85% and 68.20% prediction accuracy on the OAI and MOST datasets, respectively. Experimental results show that our method outperforms the existing workhorse. The proposed approach may become a potentially useful tool for assisting physicians.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
The details of KL are described in the Sect. 3.
- 3.
The training data needs to be normally sized as \(48\times 48\times 3\) while test ones need to generate the pyramid.
- 4.
The coefficient 0.2 can be chosen as others.
References
Antony, J., McGuinness, K., Moran, K., O’Connor, N.E.: Automatic detection of knee joints and quantification of knee osteoarthritis severity using convolutional neural networks. In: International Conference on Machine Learning and Data Mining in Pattern Recognition, pp. 376–390. Springer (2017). https://doi.org/10.1007/978-3-319-62416-7_27
Antony, J., McGuinness, K., O’Connor, N.E., Moran, K.: Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 1195–1200. IEEE (2016). https://doi.org/10.1109/ICPR.2016.7899799
Arden, N., Nevitt, M.C.: Osteoarthritis: epidemiology. Best Pract. Res. Clin. Rheumatol. 20(1), 3–25 (2006). https://doi.org/10.1016/j.berh.2005.09.007
Braun, H.J., Gold, G.E.: Diagnosis of osteoarthritis: imaging. Bone 51(2), 278–288 (2012). https://doi.org/10.1016/j.bone.2011.11.019
Chatfield, K., Simonyan, K., Vedaldi, A., Zisserman, A.: Return of the devil in the details: delving deep into convolutional nets. arXiv preprint arXiv:1405.3531 (2014). https://doi.org/10.5244/C.28.6
Cross, M., et al.: The global burden of hip and knee osteoarthritis: estimates from the global burden of disease 2010 study. Ann. Rheumat. Dis. 73(7), 1323–1330 (2014). https://doi.org/10.1136/annrheumdis-2013-204763
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
Jia, Y., et al.: Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM International Conference on Multimedia, pp. 675–678. ACM (2014). https://doi.org/10.1145/2647868.2654889
Kellgren, J., Lawrence, J.: Radiological assessment of osteo-arthrosis. Ann. Rheumat. Dis. 16(4), 494 (1957). https://doi.org/10.1136/ard.16.4.494
Kong, F.: Facial expression recognition method based on deep convolutional neural network combined with improved LBP features. Pers. Ubiquit. Comput. 1–9 (2019). https://doi.org/10.1007/s00779-019-01238-9
Liu, C., et al.: Automatic segmentation of the prostate on CT images using deep neural networks (DNN). Int. J. Radiat. Oncol.* Biol.* Phys. 104(4), 924–932 (2019). https://doi.org/10.1016/j.ijrobp.2019.03.017
Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3431–3440 (2015). https://doi.org/10.1109/CVPR.2015.7298965
Nguyen, C.C., Tran, G.S., Nghiem, T.P., Burie, J.C., Luong, C.M.: Real-time smile detection using deep learning. J. Comput. Sci. Cybern. 35(2), 135–145 (2019). https://doi.org/10.15625/1813-9663/35/2/13315
Norman, B., Pedoia, V., Majumdar, S.: Use of 2D U-net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry. Radiology 288(1), 177–185 (2018). https://doi.org/10.1148/radiol.2018172322
Oka, H., et al.: Fully automatic quantification of knee osteoarthritis severity on plain radiographs. Osteoarthritis Cartilage 16(11), 1300–1306 (2008). https://doi.org/10.1016/j.joca.2008.03.011
Orlov, N., Shamir, L., Macura, T., Johnston, J., Eckley, D.M., Goldberg, I.G.: WND-CHARM: multi-purpose image classification using compound image transforms. Pattern Recogn. Lett. 29(11), 1684–1693 (2008). https://doi.org/10.1016/j.patrec.2008.04.013
Pedoia, V., Norman, B., Mehany, S.N., Bucknor, M.D., Link, T.M., Majumdar, S.: 3D convolutional neural networks for detection and severity staging of meniscus and PFJ cartilage morphological degenerative changes in osteoarthritis and anterior cruciate ligament subjects. J. Magn. Reson. Imaging 49(2), 400–410 (2019). https://doi.org/10.1002/jmri.26246
Puig-Junoy, J., Zamora, A.R.: Socio-economic costs of osteoarthritis: a systematic review of cost-of-illness studies. In: Seminars in Arthritis and Rheumatism, vol. 44, pp. 531–541. Elsevier (2015). https://doi.org/10.1016/j.semarthrit.2014.10.012
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y
Shamir, L., Ling, S.M., Scott, W., Hochberg, M., Ferrucci, L., Goldberg, I.G.: Early detection of radiographic knee osteoarthritis using computer-aided analysis. Osteoarthritis Cartilage 17(10), 1307–1312 (2009). https://doi.org/10.1016/j.joca.2009.04.010
Shamir, L., et al.: Knee x-ray image analysis method for automated detection of osteoarthritis. IEEE Trans. Biomed. Eng. 56(2), 407–415 (2008). https://doi.org/10.1109/TBME.2008.2006025
Shamir, L., Orlov, N., Eckley, D.M., Macura, T., Johnston, J., Goldberg, I.: WND-CHARM: multi-purpose image classifier. Astrophysics Source Code Library (2013)
Shamir, L., Orlov, N., Eckley, D.M., Macura, T., Johnston, J., Goldberg, I.G.: Wndchrm-an open source utility for biological image analysis. Sour. Code Biol. Med. 3(1), 13 (2008). https://doi.org/10.1186/1751-0473-3-13
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Tiulpin, A., Thevenot, J., Rahtu, E., Lehenkari, P., Saarakkala, S.: Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci. Rep. 8(1), 1727 (2018). https://doi.org/10.1038/s41598-018-20132-7
Tiulpin, A., Thevenot, J., Rahtu, E., Saarakkala, S.: A novel method for automatic localization of joint area on knee plain radiographs. In: Scandinavian Conference on Image Analysis, pp. 290–301. Springer (2017). https://doi.org/10.1007/978-3-319-59129-2_25
Tran, D., Wang, H., Torresani, L., Feiszli, M.: Video classification with channel-separated convolutional networks. arXiv preprint arXiv:1904.02811 (2019)
Wiggers, K.L., Britto Jr., A.S., Heutte, L., Koerich, A.L., Oliveira, L.S.: Image retrieval and pattern spotting using siamese neural network. arXiv preprint arXiv:1906.09513 (2019). https://doi.org/10.1109/IJCNN.2019.8852197
Yang, S.: Feature engineering in fine-grained image classification. Ph.D. thesis (2013). http://hdl.handle.net/1773/23376
Yoo, T.K., Kim, D.W., Choi, S.B., Park, J.S.: Simple scoring system and artificial neural network for knee osteoarthritis risk prediction: a cross-sectional study. PLoS ONE 11(2), e0148,724 (2016). https://doi.org/10.1371/journal.pone.0148724
Zhang, K., Zhang, Z., Li, Z., Qiao, Y.: Joint face detection and alignment using multitask cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499–1503 (2016). https://doi.org/10.1109/LSP.2016.2603342
Acknowledgments
This work is supported by the National Key Research and Development Program of China under No. 2018YFB0204301.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wang, K., Niu, X., Dou, Y., Yang, D., Xie, D., Yang, T. (2022). Two-Stage Convolutional Neural Network for Knee Osteoarthritis Diagnosis in X-Rays. In: Su, R., Zhang, YD., Liu, H. (eds) Proceedings of 2021 International Conference on Medical Imaging and Computer-Aided Diagnosis (MICAD 2021). MICAD 2021. Lecture Notes in Electrical Engineering, vol 784. Springer, Singapore. https://doi.org/10.1007/978-981-16-3880-0_22
Download citation
DOI: https://doi.org/10.1007/978-981-16-3880-0_22
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-3879-4
Online ISBN: 978-981-16-3880-0
eBook Packages: EngineeringEngineering (R0)