Image-Based Method for Knee Ligament Injuries Detection
Anterior cruciate ligament tear is one of the most frequent knee injuries, with reported incidence of 120,000 per year in the US alone. Different forms of everyday activities and contact and noncontact sports associated with pivot shift, dashboard, clip and hyperextension injury may lead to ACL rupture. Various forms of rupture of this important ligament are reported. Among these, the most difficult form to diagnose with imaging methods is reported to be the fan-shaped deformation with fiber discontinuity and no stump formation. Magnetic resonance has proven to be the contemporary gold standard in visualization of the ACL, with specificity and sensitivity reaching 86 and 95%, respectively, in comparison to arthroscopic evaluation. Although high field MRI is very accurate in the evaluation of ACL tears, fatigue and routine of medical professionals is potentially hazardous, and creates the possible risk of overlooking the lesion. Therefore, a semi-automatic diagnostic system is very much awaited by the medical community.
In this paper a new image-based method for the detection of fan-like deformation of acute ACL injury is presented. The developed algorithm is based on digital image processing and analysis. The demonstrated solutions are implemented in the MATLAB environment. The proposed method is investigated and examined on sets of MRI scans with cases of healthy and damaged knee joints. The efficacy of the method is analyzed based on obtained findings, which offered some important conclusions as well.
KeywordsDigital image processing Watershed segmentation Image analysis Knee ligament injuries
The research reported in this paper has been financed from the state budget for science. The authors wish to acknowledge Sebastian Turek for participation in the reported research.
- 2.Anderson, M.J., Browning, W.M., Urband, C.E., Kluczynski, M.A., Bisson, L.J.: A systematic summary of systematic reviews on the topic of the anterior cruciate ligament. Orthop J. Sports Med. 4(3), 2325967116634074 (2016)Google Scholar
- 13.Beucher, S.: The watershed transformation applied to image segmentation. In: 10th Pfefferkorn Conference on Signal and Image Processing in Microscopy and Microanalysis Cambridge, UK, 16–19 September 1991. Scanning Microscopy International, suppl. 6, pp. 299–314 (1992)Google Scholar
- 18.Boniatis, I, Panayiotakis, G, Panagiotopoulos, E.: A computer-based system for the discrimination between normal and degenerated menisci from Magnetic Resonance Images. In: 2008 IEEE International Workshop on Imaging Systems and Techniques, pp. 335–339. (2008)Google Scholar
- 19.Swamy, M.S.M., Holi, M.S.: Knee joint menisci visualization and detection of tears by image processing. In: 2012 International Conference on Computing Communication and Applications, pp. 1–5 (2012)Google Scholar
- 20.Patel, A.J., Modi, H., Patel, H.: Measurement of cartilage thickness in osteoarthritis and visualization of meniscus tear of knee MRI image processing. Int. J. Comput. Sci. Mob. Comput. 5, 39–52 (2016)Google Scholar
- 22.Woods, R., Gonzales, R.: Digital Image Processing. Prentice Hall, Upper Saddle River (2008)Google Scholar