Deep learning for early detection of pathological changes in X-ray bone microstructures

Texture features are designed to quantitatively evaluate patterns of the spatial distribution of image pixels for purposes of image analysis and interpretation. Unexplained variations in the texture patterns often lead to misinterpretation and undesirable consequences in medical image analysis. In this paper, we explore the ability of Machine Learning (ML) methods to design a radiology test of Osteoarthritis (OA) at an early stage when the number of patients’ cases is small. In our experiments, we use high-resolution X-ray images of knees in patients which were identified with Kellgren-Lawrence scores progressing from 1. The existing ML methods have provided a limited diagnostic accuracy, whilst the proposed Group Method of Data Handling strategy of Deep Learning has significantly extended the diagnostic test. The comparative experiments demonstrate that the proposed framework using the Zernike-based texture features has significantly improved the diagnostic accuracy on average by 11%. This allows us to conclude that the designed model for early diagnostic of OA will provide more accurate radiology tests, although a new study is required when a large number of patients’ cases will be available.

  • Jakaite, L., Schetinin, V., Hladůvka, J. et al. Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis. Sci Rep11, 2294 (2021). https://doi.org/10.1038/s41598-021-81786-4
  • Schetinin, V. & Schult, J. Learning polynomial networks for classification of clinical electroencephalograms. Soft. Comput.10, 397–403. https://doi.org/10.1186/s12889-018-5381-15 (2006).
  • Schetinin, V., Jakaite, L., Nyah, N., Novakovic, D. & Krzanowski, W. J. Feature extraction with GMDH-type neural networks for EEG-based person identification. Int. J. Neural Syst.28, 1750064:1-1750064:23. https://doi.org/10.1186/s12889-018-5381-16 (2018).
  • Minaev, S., Gerasimenko, I., Kirgizov, I., Shamsiev, A. & Bykov, N. 3D reconstruction in surgery of hydatid cyst of the liver. World J. Surg.41, 3218–3223.  https://doi.org/10.1007/s00268-017-4129-x (2017).
  • Minaev S. V., Gerasimenko I. N., Shchetinin E. V., Schetinin V., Mishvelov A. E., Nuzhnaya R. V., Grigorova A. N., Rubanova M. F. 3D RECONSTRUCTION IN SURGERY OF HYDATID CYST OF THE LIVER. Medical News of North Caucasus. 2019;14(1.2):220-223. DOI – https://doi.org/10.14300/mnnc.2019.14019
  • Minaev SV, Gerasimenko IN, Grigorova AN, Timofeev SV, Doronin FV, Timofeev SI. 3d-technologies in hepatobiliary surgery. Pirogov Russian Journal of Surgery. 2020;(8):103-106. https://doi.org/10.17116/hirurgia2020081103
  • Varganov MV, Nekrasova DA, Ognetov SYu, Ledneva AV. 3D-simulator for studying the structure of the facial nerve channel in othosurgery. Medicinskii Vestnik Severnogo Kavkaza. — Medical News of North Caucasus. 2018;13(1-1):56-58. (In Russ.). https://doi.org/10.14300/mnnc.2018.13016
  • Krauel L, Fenollosa F, Riaza L, Perez M, Tarrado X. Use of 3D prototypes for complex surgical oncologic cases. World Journal of Surgery. 2016;40(4):889-894. https://doi.org/10.1007/s00268-015-3295-y

Leave a Reply