Abstract
Knee Osteoarthritis (KOA) is becoming one of the most frequent degenerative and irreversible diseases in elderly people. Its early detection and diagnosis is also a difficult and time-intensive task. The recent advances in Machine Learning (ML) and Computer Vision (CV) created new paths to automatically detect KOA in the early stages. Detecting and grading the severity of KOA requires a dedicated ML model. This paper proposes a Side-by-Side Additive Network (SSANet)-based model for detecting and grading the severity of KOA. Since KOA affects the knee joint space by narrowing the gap between the joints, we preprocess the X-ray images to detect the Region of Interest (ROI) before the training of the model. From experimental results, it is evidenced that the ROI selection is really improving the detection accuracy of the model. Unlike sequentially connected convolution layer-based deep learning models, the proposed SSANet is based on a parallel convolution layer to reduce the degradation of feature quality. Again, to enhance the edge feature maps, we apply an additive layer that couples the previous layers’ convolutional output. SSANet captures both high-level and low-level features to predict the KOA severity effectively. The presence of a smaller number of layers and fewer numbers of learnable parameters than the existing popular deep learning models, make SSANet a time and space-efficient network. Moreover, the performance of the proposed SSANet in detecting KOA severity is significantly superior to that of other popular state-of-the-art networks.
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
References
Lespasio M, Piuzzi N, Husni M, Muschler G, Guarino A, Mont M (2017) Knee osteoarthritis: a primer. J Perm 21:16–183
Luyten FP et al (2012) Definition and classification of early osteoarthritis of the knee. Knee Surg Sports Traumatol Arthrosc Off J ESSKA 20(3):401–406
Ho T (1995) Random decision forests. In: The proceedings of IEEE conference DAR, pp 278–282
Cortes C, Vapnik V (1995) Support vector networks. J Mach Learn 20:273–297
Lazzarini N, Runhaar J, Bay-Jensen A, Thudium C, Bierma-Zeinstra S, Henrotin Y, Bacardit J (2017) A machine learning approach for the identification of new biomarkers for knee osteoarthritis development in overweight and obese women. J Osteoarthr Cartil 25(12):2014–2021
Halilaj E, Le Y, Hicks J, Hastei T, Delp S (2018) Modeling and predicting osteoarthritis progression: data from the osteoarthritis initiative. J Osteoarthr Cartil 26:1643–1650
Kokkotis C, Moustakidis S, Papageorgiou E, Giakas G, Tsaopoulos D (2020) A machine learning workflow for diagnosis of knee osteoarthritis with a focus on post-hoc explainability. In: Proceedingd of IEEE conference IISA, pp 1–7
Alexos A, Kokkotis C, Moustakidis S, Papageorgiou E, Tsaopoulos D (2020) Prediction of pain in knee osteoarthritis patients using machine learning: data from osteoarthritis initiative. In: Proceedings of IEEE conference IISA, pp 1–7
Ntakolia C, Kokkotis C, Moustakidis S, Tsaopoulos D (2020) Machine learning pipeline for predicting joint space narrowing in knee osteoarthritis patients. In: Proceedings of IEEE conference BIBE, pp 934–941
Bandyopadhyay S, Sharma P (2016) Detection of osteoarthritis using knee X-ray image analyses: a machine vision based approach. In: Proceedings
Deng J, Dong W, Socher R, Li L, Li K, Fei-Fei L (2009) ImageNet: a large-scale hierarchical image database. In: Proceedings of IEEE conference CVPR , pp 248–255
Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet classification with deep convolutional neural networks. In: Proceedings of NIPS conference , pp 1097–1105
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. ar**v:1409.1556
He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. In: Proceedings of IEEE conference CVPR, pp 770–778
Huang G, Zhuang L, Maaten L, Weinberger K (2018) Densely connected convolutional networks. ar**v:1608.06993
Antony J, McGuinness K, Moran K, OConnor N (2017) Automatic detection of knee joints and quantification of knee osteoarthritis severity using convolutional neural networks. ar**v:1703.09856
Tiulpin A, Thevenot J, Rahtu E (2019) Automatic knee osteoarthritis diagnosis from plain radiographs: a deep learning-based approach. Sci Rep 8:1727
Wahyuningrum R, Anifah L, Purnama I, Purnomo M (2019) A new approach to classify knee osteoarthritis severity from radiographic images based on CNN-LSTM method. In: Proceedings of IEEE conference iCAST, pp 1–6
Muhammad B et al (2019) Deep ensemble network for quantification and severity assessment of knee osteoarthritis. In: Proceedings of IEEE conference ICMLA, pp 951–957
Zhang B, Tan J, Cho K, Chang G, Deniz C (2020) Attention-based CNN for KL grade classification: data from the osteoarthritis initiative. In: IEEE proceeding of ISBI, pp 731–735
Nasser Y, Jennane R, Chetouani A, Lespessailles E, Hassouni M (2020) Discriminative regularized auto-encoder for early detection of knee osteoarthritis: data from the osteoarthritis initiative. IEEE Trans Med Imaging 39(9):2976–2984
Kwon SB et al (2020) Machine learning based automatic classification of knee osteoarthritis severity using gait data and radiographic images. IEEE Access: Pract Innov Open Solut 8:120597–120603
Abedin J, Antony J, McGuinness K et al (2019) Predicting knee osteoarthritis severity: comparative modeling based on patient’s data and plain X-ray images. Sci Rep 9:5761
Tiulpin A, Klein S, Bierma-Zeinstra SMA et al (2019) Multimodal machine learning-based knee osteoarthritis progression prediction from plain radiographs and clinical data. Sci Rep 9:20038
Verma M, Vipparthi S, Singh G, Murala S (2020) LEARNet: dynamic imaging network for micro expression recognition. IEEE Trans Image Process 29:1618–1627
Chen P (2018) Knee osteoarthritis severity grading dataset, Mendeley data, V1. https://doi.org/10.17632/56rmx5bjcr.1
Acknowledgements
This work was supported in part by the SPEV Project “Smart Solutions in Ubiquitous Computing Environments” from the University of Hradec Kralove, Faculty of Informatics and Management, Czech Republic, under Grant UHK-FIM SPEV (2022–2102). We are also grateful for the support of Ph.D. student Michal Dobrovolny for consultations. This work was also supported in part by the DBT Project “Multimodal Non-invasive Image Analysis using Deep Learning Approach for Automated Diagnosis of Arthritis and Prediction of Disease Severity” under sanction order no. and date: BT/PR33087/BID/7/889/2019.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Tewari, R., Bhattacharjee, D., Roy, H., Krejcar, O. (2024). SSANet: Side-by-Side Additive Network for Knee Osteoarthritis Severity Detection from X-Ray Images. In: Kole, D.K., Roy Chowdhury, S., Basu, S., Plewczynski, D., Bhattacharjee, D. (eds) Proceedings of 4th International Conference on Frontiers in Computing and Systems. COMSYS 2023. Lecture Notes in Networks and Systems, vol 974. Springer, Singapore. https://doi.org/10.1007/978-981-97-2611-0_24
Download citation
DOI: https://doi.org/10.1007/978-981-97-2611-0_24
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-97-2610-3
Online ISBN: 978-981-97-2611-0
eBook Packages: EngineeringEngineering (R0)