(46-2) 17 * << * >> * Russian * English * Content * All Issues

Using squeeze-and-excitation blocks to improve an accuracy of automatically grading knee osteoarthritis severity using convolutional neural networks
А.A. Mikhaylichenko 1, Y.М. Demyanenko 1

Southern Federal University, Institute of Mathematics, Mechanics and Computer Science,
Rostov-on-Don, Russia

 PDF, 1062 kB

DOI: 10.18287/2412-6179-CO-897

Pages: 317-325.

Full text of article: Russian language.

In this paper, we investigate the effect of squeeze-and-excitation blocks on improving the classification quality of osteoarthritis using convolutional neural networks of the ResNet and DenseNet families. We show that the use of these blocks improves the quality of osteoarthritis classification according to the Kellgren-Lawrence scale by 1–3 % without a significant modifi-cation of the model structure. We also demonstrate that combining the 0 and 1 classes of the Kellgren-Lawrence scale into one class allows one to increase the accuracy of osteoarthritis grading by 12.74 %, without losing significant information about the disease. The best final ac-curacy attained was 84.66 % when using an ensemble of three convolutional networks with the DenseNet-121 architecture using squeeze-and-excitation blocks, which significantly exceeds the performance of the existing state-of-the-art. The obtained results can be used both for a prelimi-nary automatic diagnosis and as an auxiliary tool.

image processing; automatically grading osteoarthritis severity; convolutional neural network.

Mikhaylichenko AA, Demyanenko YM. Using squeeze-and-excitation blocks to improve an accuracy of automatically grading knee osteoarthritis severity using convolutional neural networks. Computer Optics 2022; 46(2): 317-325. DOI: 10.18287/2412-6179-CO-897.


  1. Balabanova RM. Osteoarthrosis or osteoarthritis? Modern ideas about the disease and its treatment [In Russian]. Modern rheumatology 2013; 3: 67-70.
  2. Doherty M, Doherty J. Clinical examination in rheumatology. Wolfe Pub Ltd; 1992.
  3. Kellgren J, Lawrence J. Radiological assessment of osteoarthrosis. Ann Rheum Dis 1957; 16: 494-502.
  4. Altman R, Gold GE. Atlas of individual radiographic features in osteoarthritis, revised. Osteoarthr Cartil 2007; 15: A1-56.
  5. Altman R. Development of criteria for the classification and reporting of osteoarthritis. Classification of osteoarthritis of the knee. Arthritis Rheum 1986; 29(8): 1039-1049.
  6. Tiulpin A, Klein S, Bierma-Zeinstra S, Thevenot J. Multimodal machine learning-based knee osteoarthritis progression prediction from plain radiographs and clinical data. Sci Rep 2019; 9: 20038.
  7. Mikhaylichenko A, Demyanenko Y. Automatic grading of knee osteoarthritis from plain radiographs using densely connected convolutional networks. Recent trends in analysis of images, social networks and texts (AIST 2020). Commun Comput Inf Sci 2021; 1357: 149-161.
  8. Chan S, Dittakan K. Osteoarthritis stages classification to human joint imagery using texture analysis: A comparative study on ten texture descriptors. Recent Trends in Image Processing and Pattern Recognition 2019; 209-225.
  9. Antony J, McGuinness K, Moran K, O’Connor N. Automatic detection of knee joints and quantification of knee osteoarthritis severity using convolutional neural networks. Machine Learning and Data Mining in Pattern Recognition (MLDM) 2017: 376-390.
  10. Tiulpin A, Thevenot J, Rahtu E, Lehenkari P, Saarakkala S. Automatic knee osteoarthritis diagnosis from plain radiographs: A deep learning-based approach. Sci Rep 2018; 8: 1727.
  11. Tiulpin A, Saarakkala S. Automatic grading of individual knee osteoarthritis features in plain radiographs using deep convolutional neural networks. Osteoarthr Cartil 2020; 28(1): S308. DOI: 10.1016/j.joca.2020.02.480.
  12. Pingjun C, Linlin G, Xiaoshuang S, Kyle A, Lin Y. Fully automatic knee osteoarthritis severity grading using deep neural networks with a novel ordinal loss. Comput Med Imaging Graph 2019; 75: 84-92.
  13. Norman B, Pedoia V, Noworolski A. Applying densely connected convolutional neural networks for staging osteoarthritis severity from plain radiographs. J Digit Imaging 2019; 32: 471-477.
  14. Hu J, Shen L, Sun G. Squeeze-and-excitation networks. 2018 IEEE/CVF Conf on Computer Vision and Pattern Recognition 2018: 7132-7141.
  15. Kingma DP, Ba J. Adam: A method for stochastic optimization. Int Conf on Learning Representations (ICLR) 2015.
  16. Antony J, McGuinness K, Moran K, O’Connor N. Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks. 23rd Int Conf on Pattern Recognition (ICPR) 2016: 1195-1200.
  17. Cheng J, Aurelien B, Mark L. The relative performance of ensemble methods with deep convolutional neural networks for image classification. J Appl Stat 2018; 45: 2800-2818.
  18. Wesseling J, Boers M, Viergever MA, Hilberdink WKHA, Lafeber FPJG, Dekker J, Bijlsma JWJ. Cohort profile: Cohort hip and Cohort knee (CHECK) study. Int J Epidemiol 2016; 45(1): 36-44.
  19. Shamir L, Ling S, Scott W, Orlov N. Knee X-Ray image analysis method for automated detection of osteoarthritis. IEEE Trans Biomed Eng 2009; 56: 407-415.
  20. Kwon SB, Han H, Lee MC, Kim HC. Machine learning-based automatic classification of knee osteoarthritis severity using gait data and radiographic images. IEEE Access 2020; 8: 120597-120603.
  21. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2016: 770-778.
  22. Huang G, Liu Z, Weinberger KQ. Densely connected convolutional networks. IEEE Conf on Computer Vision and Pattern Recognition (CVPR) 2017; 8: 2261-2269.

© 2009, IPSI RAS
151, Molodogvardeiskaya str., Samara, 443001, Russia; E-mail: journal@computeroptics.ru ; Tel: +7 (846) 242-41-24 (Executive secretary), +7 (846) 332-56-22 (Issuing editor), Fax: +7 (846) 332-56-20