Application of multi feature medical image fusion in biomechanics experimental teaching of sports rehabilitation

  • Zhaoxia Liu Sports College, Taiyuan University of Technology, Taiyuan 030024, China
Keywords: multi feature medical image function; support vector machines; mixed kernel function; biomechanics of sports rehabilitation
Ariticle ID: 197

Abstract

With the increasing demand of society for sports rehabilitation, many colleges and universities have set up the sports rehabilitation biomechanics specialty, which has been listed as a professional basic course in some colleges and universities. However, there are still many problems in the experimental teaching of this course, such as the failure to recognize the human movements in medical images in a timely manner, which makes it impossible to judge whether the movements of motion rehabilitation are standard. However, multi feature medical image fusion can become a new method, which has been widely used in the application and research of medical images, and its position and role in teaching have been further strengthened. Multi feature medical image fusion can not only eliminate redundant information, but also maintain the original image information, and achieve better fusion results. Under the background of multi feature medical image fusion, this paper proposed a support vector machines (SVM) method based on mixed kernel function. This method not only makes the motion recognition of traditional Chinese medical images of motion rehabilitation biomechanics more accurate, but also faster. The experimental results showed that the recognition accuracy and recognition rate of the kernel function were 60.2% and 53.7% when the number of samples was 800. The recognition accuracy and recognition rate of SVM were 65.5% and 53.8%. The recognition accuracy and recognition rate of SVM based on mixed kernel function were 89.9% and 86.7%. This further proved that SVM based on mixed kernel function was superior to the other two methods in recognition accuracy and recognition rate, which proved the superiority of this method in rehabilitation motion recognition.

References

1. Troy KL, Davis IS, Tenforde AS. A narrative review of metatarsal bone stress injury in athletic populations: etiology, biomechanics, and management. PM&R. 2021; 13(11): 1281-1290. doi: 10.1002/pmrj.12518

2. Migel K, Wikstrom E. Gait biomechanics following taping and bracing in patients with chronic ankle instability: a critically appraised topic. Journal of Sport Rehabilitation. 2020; 29(3): 373-376. doi: 10.1123/jsr.2019-0030

3. DiCesare CA. High-risk lower-extremity biomechanics evaluated in simulated Soccer-Specific virtual environments. Journal of Sport Rehabilitation. 2020; 29(3): 294-300. doi: 10.1123/jsr.2018-0237

4. Bonnette S, DiCesare CA, Kiefer AW, et al. Injury risk factors integrated into self-guided real-time biofeedback improves high-risk biomechanics. Journal of sport rehabilitation. 2019; 28(8): 831-839. doi: 10.1123/jsr.2017-0391

5. Arhos EK, Capin JJ, Buchanan TS, et al. Quadriceps strength symmetry does not modify gait mechanics after anterior cruciate ligament reconstruction, rehabilitation, and return-to-sport training. The American Journal of Sports Medicine. 2021; 49(2): 417-425. doi: 10.1177/0363546520980079

6. Quintana C, Hoch M. The relationship between neurocognitive function and biomechanics: a critically appraised topic. Journal of sport rehabilitation. 2020; 30(2): 327-332. doi: 10.1123/jsr.2020-0103

7. Arundale AJH, Capin JJ, Zarzycki R, et al. Functional and patient-reported outcomes improve over the course of rehabilitation: A secondary analysis of the ACL-SPORTS trial. Sports Health. 2018; 10(5): 441-452. doi: 10.1177/1941738118779023

8. Greenberg EM, Greenberg ET, Albaugh J, et al. Rehabilitation practice patterns following anterior cruciate ligament reconstruction: a survey of physical therapists. journal of orthopaedic & sports physical therapy. 2018; 48 (10): 801-811. doi: 10.2519/jospt.2018.8264

9. Shevelev OA, Smolensky AV, Petrova MV, et al. Mechanisms of low-temperature rehabilitation technologies. Sports traumatic brain injury. Physical and rehabilitation medicine, medical rehabilitation. 2022; 4(1): 4-13. doi: 10.36425/rehab88833

10. Kong PW, Yam JW. Shoulder biomechanics of para-table tennis: a case study of a standing class para-athlete with severe leg impairment. BMC Sports Science, Medicine and Rehabilitation. 2022; 14(1): 1-9. doi: 10.1186/s13102-022-00536-9

11. Wang HF, Shankar A, Vivekananda GN. Modelling and simulation of sprinters’ health promotion strategy based on sports biomechanics. Connection Science. 2021; 33(4): 1028-1046. doi: 10.1080/09540091.2020.1807467

12. Edwards N, Dickin C, Wang H. Low back pain and golf: A review of biomechanical risk factors. Sports Medicine and Health Science. 2020; 2(1): 10-18. doi: 10.1016/j.smhs.2020.03.002

13. Jarvis DN, Kulig K. What goes up must come down: Consequences of jump strategy modification on dance leap take-off biomechanics. Journal of Sports Sciences. 2020; 38(16): 1836-1843. doi: 10.1080/02640414.2020.1756710

14. Fotaki A, Triantafyllou A, Papagiannis G, et al. The science of biomechanics can promote dancers’ injury prevention strategies. Physical Therapy Reviews. 2021; 26(2): 94-101. doi: 10.1080/10833196.2020.1832707

15. Demircan E. A pilot study on locomotion training via biomechanical models and a wearable haptic feedback system. Robomech Journal. 2020; 7(1): 1-13. doi: 10.1186/s40648-020-00167-0

16. Kornosenko O, Denysovets T, Danysko O, et al. System of Preparation of Future Fitness Coaches’ for Health-Improving Activity in the Conditions of Rehabilitation Establishments. International Journal of Applied Exercise Physiology. 2020; 9(8): 33-41.

17. Johnston PT, McClelland JA, Webster KE. Lower limb biomechanics during single-leg landings following anterior cruciate ligament reconstruction: a systematic review and meta-analysis. Sports Medicine. 2018; 48(9): 2103-2126. doi: 10.1007/s40279-018-0942-0

18. Keogh JWL. Introduction to a New MDPI Open Access Journal: Biomechanics. Biomechanics. 2021; 1(1): 163-166. doi: 10.3390/biomechanics1010013

19. Vincent HK, Kilgore JE, Chen C, et al. Impact of body mass index on biomechanics of recreational runners. PM&R. 2020; 12(11): 1106-1112. doi: 10.1002/pmrj.12335

20. Nugent FJ, Vinther A, McGregor A, et al. The relationship between rowing-related low back pain and rowing biomechanics: a systematic review. British journal of sports medicine. 2021; 55(11): 616-628. doi: 10.1136/bjsports-2020-102533

21. Wan Z, Dong Y, Yu Z, et al. Semi-Supervised Support Vector Machine for Digital Twins Based Brain Image Fusion. Frontiers in Neuroscience. 2021; 15:705323. doi: 10.3389/fnins.2021.705323

22. Li XF, Sui J, Wang YW. Three-Dimensional Reconstruction of Fuzzy Medical Images Using Quantum Algorithm. IEEE Access. 2020; 8: 218279-218288. doi: 10.1109/ACCESS.2020.3039540

23. Zhang C, Biś D, Liu X, et al. Biomedical word sense disambiguation with bidirectional long short-term memory and attention-based neural networks. BMC Bioinformatics. 2019; 20(Suppl 16): 502. doi: 10.1186/s12859-019-3079-8

24. Jin G, Liu CC, Chen X. An efficient deep neural network framework for COVID-19 lung infection segmentation. Information Sciences. 2021; 612(11): 745-758. doi: 10.1016/j.ins.2022.08.059

25. Settanni M. Design and Implementation of Distributed System Platform Based on Chaos Theory and Encryption Algorithm. Distributed Processing System. 2021; 2(2): 1-8.

Published
2024-08-15
How to Cite
Liu, Z. (2024). Application of multi feature medical image fusion in biomechanics experimental teaching of sports rehabilitation. Molecular & Cellular Biomechanics, 21, 197. https://doi.org/10.62617/mcb.v21.197
Section
Article