ISSN 0021-3454 (print version)
ISSN 2500-0381 (online version)
Menu

8
Issue
vol 63 / August, 2020
Article

DOI 10.17586/0021-3454-2018-61-2-186-191

UDC 004.056.53

MORPHOLOGICAL ANALYSIS IN THE PROBLEMS OF AUTOMATION OF THE KNEE JOINT IMAGE PROCESSING

A. S. Аntonova
Mоrion Ltd.; technologist


A. O. Kaznacheeva
Saint-Petersburg State University of Information Technologies, Mechanics and Optics; Associate Professor


Read the full article 

Abstract. The possibility of automation of the processes of medical diagnostics and quantitative evaluation of anatomical structures by segmentation of magnetic resonance (MR) images is considered. The values of intensity of MR signals from various tissues of the knee joint are analyzed, weak dependence of contrast of signals on external factors is revealed. The algorithm for the segmentation of cartilage and bone structures based on the calculated contrast of tissues is implemented, including threshold processing, morphological analysis, and the delineation of borders by the Canny method. The results are approved by tomograms of different weights (sequences of rapid spin echo, gradient-echo), and can be used for cartilage mapping and 3D joint modeling.
Keywords: image analysis, tomography, segmentation, morphometry, knee joint, diagnostics

References:
  1. Apprich S., Mamisch T.C., Welsch G.H. et al. European Journal of Radiology, 2012, no. 81, pp. e438-e443. doi: 10.1016/j.ejrad.2011.03.069
  2. Nasnikova I.Yu., Morozov S.P., Filisteev P.A. REJR, 2011, no. 3(1), pp. 75–81. (in Russ.)
  3. Kazankova O.S., Kaznacheeva A.O. REJR, 2012, no. 2(6), pp. 227–229. (in Russ.)
  4. Saenko A.P., Musalimov V.M., Lerm Sh., Lints G. Scientific and Technical Journal of Information Technologies, Mechanics and Optics, 2014, no. 1(89), pp. 93–98. (in Russ.)
  5. Jaremko J.L., Cheng R.W.T., Lambert R.G.W. et al. Osteoarthritis and Cartilage, 2006, no. 14, pp. 914–922. doi: 10.1016/j.joca.2006.03.004
  6. Swanson M.S., Prescott J.W., Best T.M. et al. Osteoarthritis and Cartilage, 2010, no. 3(18), pp. 344–353. doi: 10.1016/j.joca.2009.10.004
  7. Gonzalez R.C., Woods R.E. Digital Image Processing, Prentice Hall, 2008, 954 р.
  8. Sizikov V.S. Obratnye prikladnye zadachi i MatLab (Return Applied Tasks and MatLab), St. Petersburg, 2011. (in Russ.)
  9. Kaznacheeva A.O. Luchevaya diagnostika i terapiya (Diagnostic radiology and radiotherapy), 2010, no. 4, pp. 83–87. (in Russ.)
  10. Kaznacheeva A.O. Razrabotka metodov i sredstv shumopodavleniya v tomografii (Development of Methods and Means of Noise Reduction in Tomography), Candidate’s thesis, St. Petersburg, 2006, 167 р. (in Russ.)
  11. Matveeva A.V. et al. REJR, 2015, no. S2(5), pp. 318–319. (in Russ.)
  12. Antonova A.S., Kaznacheeva A.O., Shostak D.M. REJR, 2014, no. S2(3), pp. 425–426. (in Russ.)
  13. Antonova A.S. Al'manakh sovremennoy nauki i obrazovaniya (Almanac of Modern Science and Education), 2014, no. 10(88), pp. 18–21. (in Russ.)
  14. Nikitin O.R., Pasechnik A.S. Methods and devices of information transmission and processing, 2009, no. 11, pp. 300–309. (in Russ.)
  15. Zakharov A.V., Kol'tsov P.P., Kotovich N.V. et al. Trudy NIISI RAN, 2012, no. 2(2), pp. 87–99. (in Russ.)
  16.  
  17.