Abstract
Osteoarthritis (OA) is the most common form of joint disease in the world. The diagnosis of OA is currently made by human experts and suffers from subjectivity, but recently new promising detection algorithms have been developed. We validated the current state-of-the-art KL-classifying neural network model for knee OA using knee X-rays taken from postmenopausal women suffering from knee pain attributable to OA. The performance of the model on the clinical data was considerably lower compared to the previous results on population-based test data. This suggests that the performance of the current grading methods is not yet adequate to be applied in clinical settings. The present results also emphasize the importance of using clinical data for performance evaluation before deploying medical machine learning models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Abedin J, Antony J, McGuinness K, Moran K, O’Connor NE, Rebholz-Schuhmann D, Newell J (2019) Predicting knee osteoarthritis severity: comparative modeling based on patient’s data and plain X-ray images. Sci Rep 9(1):5761
Antony J, McGuinness K, O’Connor NE, Moran K (2016) Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks. In: 2016 23rd international conference on pattern recognition (ICPR). IEEE, pp 1195–1200
Antony J, McGuinness K, Moran K, O’Connor NE (2017) Automatic detection of knee joints and quantification of knee osteoarthritis severity using convolutional neural networks. In: Machine learning and data mining in pattern recognition: proceedings of 13th international conference—MLDM 2017. Springer, New York, pp 376–390
Arokoski JPA, Manninen P, Kröger H, Heliövaara M, Nykyri E, Impivaara O (2007) Hip and knee pain and osteoarthritis. In: Musculoskeletal Disorders and diseases in Finland: results of the health 2000 survey, number B 25 in Publications of the National Public Health Institute, pp 37–41
Chen P, Gao L, Shi X, Allen K, Yang L (2019) Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss. Comput Med Imaging Graph 75:84–92
Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Proceedings of the 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), vol 1. IEEE, pp 886–893
Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, Thrun S (2017) Dermatologist-level classification of skin cancer with deep neural networks. Nature 542:115–118
Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press. http://www.deeplearningbook.org
Heliövaara M, Slätis P, Paavolainen P (2008) Nivelrikon esiintyvyys ja kustannukset (Prevalence and cost of osteoarthritis). Duodecim 124(16):1869–1874
Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv:1502.03167
Kaypahoito (2018) Knee and hip osteoarthritis. Current care guidelines, the Finnish medical society Duodecim, Helsinki. http://www.kaypahoito.fi/web/kh/suositukset/suositus?id=hoi50054 Accessed 27 Aug 2018. (Working group appointed by the Finnish Medical Society Duodecim and the Finnish Orthopaedic Association)
Kellgren JH, Lawrence JS (1963) The epidemiology of chronic rheumatism. In: Kellgren JH (ed) Atlas of standard radiographs of arthritis. F.A. Davis, Philadelphia, PA, pp 10–11
Kingma DP, Adam JB (2014) A method for stochastic optimization. arXiv:1412.6980
Litjens G, Kooi T, Ehteshami Bejnordi B, Setio A, Ciompi F, Ghafoorian M, van der Laak J, Van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis. Med Image Anal 42:60–88
Munukka M, Waller B, Multanen J, Rantalainen T, Häkkinen A, Nieminen MT, Lammentausta E, Kujala UM, Paloneva J, Kautiainen H, Kiviranta I, Heinonen A (2014) Relationship between lower limb neuromuscular performance and bone strength in postmenopausal women with mild knee osteoarthritis. J Musculoskelet Neuronal Interact 14(4):418–424
Munukka M, Waller B, Rantalainen T, Häkkinen A, Nieminen MT, Lammentausta E, Kujala UM, Paloneva J, Sipilä S, Peuna A, Kautiainen H, Selänne H, Kiviranta I, Heinonen A (2016) Efficacy of progressive aquatic resistance training for tibiofemoral cartilage in postmenopausal women with mild knee osteoarthritis: a randomised controlled trial. Osteoarthr Cartil 24(10):1708–1717
Munukka M, Waller B, Häkkinen A, Nieminen MT, Lammentausta E, Kujala U, Paloneva J, Kautiainen H, Kiviranta I, Heinonen A (2017) Physical activity is related with cartilage quality in women with knee osteoarthritis. Med Sci Sports Exerc 49(7):1323–1330
Teramoto A, Fujita H, Yamamuro O, Tamaki T (2016) Automated detection of pulmonary nodules in PET/CT images: ensemble false-positive reduction using a convolutional neural network technique. Med Phys 43(6):2821–2827
Tiulpin A, Saarakkala S (2019) Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks. arXiv:1907.08020
Tiulpin A, Thevenot J, Rahtu E, Saarakkala S (2017) A novel method for automatic localization of joint area on knee plain radiographs. In: Image analysis: proceedings of the 20th Scandinavian conference—SCIA 2017 (Tromsø), Part II. Springer, Berlin, pp 290–301
Tiulpin A, Thevenot J, Rahtu E, Lehenkari P, Saarakkala S (2018) Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci Rep 8(1):1727
Waller B, Munukka M, Multanen J, Rantalainen T, Pöyhönen T, Nieminen MT, Kiviranta I, Kautiainen H, Selänne H, Dekker J, Sipilä S, Kujala UM, Häkkinen A, Heinonen A (2013) Effects of a progressive aquatic resistance exercise program on the biochemical composition and morphology of cartilage in women with mild knee osteoarthritis: protocol for a randomised controlled trial. BMC Musculoskelet Disord 14(1):82
Waller B, Munukka M, Rantalainen T, Lammentausta E, Nieminen MT, Kiviranta I, Kautiainen H, Häkkinen A, Kujala UM, Heinonen A (2017) Effects of high intensity resistance aquatic training on body composition and walking speed in women with mild knee osteoarthritis: a 4-month RCT with 12-month follow-up. Osteoarthr Cartil 25(8):1238–1246
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Niinimäki, E., Paloneva, J., Pölönen, I., Heinonen, A., Äyrämö, S. (2022). Validation of Knee KL-classifying Deep Neural Network with Finnish Patient Data. In: Tuovinen, T., Periaux, J., Neittaanmäki, P. (eds) Computational Sciences and Artificial Intelligence in Industry. Intelligent Systems, Control and Automation: Science and Engineering, vol 76. Springer, Cham. https://doi.org/10.1007/978-3-030-70787-3_12
Download citation
DOI: https://doi.org/10.1007/978-3-030-70787-3_12
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-70786-6
Online ISBN: 978-3-030-70787-3
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)