A new method of diagnosing athlete's anterior cruciate ligament health status using surface electromyography and deep convolutional neural network

• Autorzy: Hatamzadeh Mehran , Hassannejad Reza , Sharifnezhad Ali

Identyfikatory

DOI

10.1016/j.bbe.2019.05.009

• Języki publikacji: EN

Abstrakty

EN

Anterior cruciate ligament (ACL) injury is one of the most common injuries in high-demand sports. Due to long-term treatment of this injury, diagnosing recovery of ACL becomes important, particularly six months postoperatively. The purpose of this research is to provide a cost-effective and intelligent method to diagnose ACL's health status. For this purpose, 11 healthy and 27 ACL-injured subjects have been selected. In the proposed method, the athlete performs a single-leg landing protocol and surface electromyographic signals (EMG) are taken from eight lower limb muscles. Then, time–frequency distributions of EMG signals in each landing are calculated as an image, using pseudo Wigner–Ville distribution (PWVD), which are the inputs of a deep convolutional neural network (DCNN). By time–frequency analysis, it has been made clear that any change in ACL's health status causes changes in the extent of energy spread in PWVD, distribution volume, frequency content, damping rate and the peak value of EMG signals. In this research, a new relationship between ACL's health status and lower limb muscles activity is introduced through monitoring of PWVD images. The result indicates that the designed expert system is able to diagnose ACL's health status with 95.8% accuracy. In this non-invasive method, PWVD images of EMG signals are chosen as the inputs of DCNN, instead of MRI images, which, in addition to their high accuracy in diagnosing, are safer and much cheaper. The presented method can play an important role in assessing the recovery process, six months postoperatively and after that.

Słowa kluczowe

EN

anterior cruciate ligament; health status; single-leg landing; surface electromyography; pseudo Wigner–Ville distribution; deep convolutional neural network

PL

więzadło krzyżowe przednie; stan zdrowia; elektromiografia powierzchniowa; konwolucyjna sieć neuronowa

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 1
• Strony: 65--76
• Opis fizyczny: Bibliogr. 51 poz., rys., tab.

Twórcy

autor

Hatamzadeh Mehran

• Department of Mechanical Engineering, University of Tabriz, Tabriz, Iran

autor

Hassannejad Reza

• Department of Mechanical Engineering, University of Tabriz, Tabriz, Iran

autor

Sharifnezhad Ali

• Department of Sport Biomechanics and Technology, Sport Sciences Research Institute, Tehran, Iran

Bibliografia

• [1] Perera NS, Joel J, Bunola JA. Anterior cruciate ligament rupture: delay to diagnosis. Injury 2013;44:1862–5. http://dx.doi.org/10.1016/j.injury.2013.07.024.
• [2] Hewett TE, Di Stasi SL, Myer GD. Current concepts for injury prevention in athletes after anterior cruciate ligament reconstruction. Am J Sports Med 2013;41:216–24. http://dx.doi.org/10.1177/0363546512459638.
• [3] Marieswaran M, Jain I, Garg B, Sharma V, Kalyanasundaram D. A review on biomechanics of anterior cruciate ligament and materials for reconstruction. Appl Bionics Biomech 2018;2018:1–14. http://dx.doi.org/10.1155/2018/4657824.
• [4] Saka T. Principles of postoperative anterior cruciate ligament rehabilitation. World J Orthop 2014;5:450. http://dx.doi.org/10.5312/wjo.v5.i4.450.
• [5] Kvist J. Rehabilitation following anterior cruciate ligament injury. Sport Med 2004;34:269–80. http://dx.doi.org/10.2165/00007256-200434040-00006.
• [6] Cascio BM, Culp L, Cosgarea AJ. Return to play after anterior cruciate ligament reconstruction. Clin Sports Med 2004;23:395–408. http://dx.doi.org/10.1016/j.csm.2004.03.004.
• [7] Bollen SR, Scott BW. Rupture of the anterior cruciate ligament – a quiet epidemic? Injury 1996;27:407–9. http://dx.doi.org/10.1016/0020-1383(96)00033-2.
• [8] Arastu MH, Grange S, Twyman R. Prevalence and consequences of delayed diagnosis of anterior cruciate ligament ruptures. Knee Surg Sports Traumatol Arthrosc 2015;23:1201–5. http://dx.doi.org/10.1007/s00167-014-2947-z.
• [9] Louboutin H, Debarge R, Richou J, Selmi TAS, Donell ST, Neyret P, et al. Osteoarthritis in patients with anterior cruciate ligament rupture: a review of risk factors. Knee 2009;16:239–44. http://dx.doi.org/10.1016/j.knee.2008.11.004.
• [10] Liu SH, Osti L, Henry M, Bocchi L. The diagnosis of acute complete tears of the anterior cruciate ligament. J Bone Joint Surg - Br 1995;77:586–8. PubMed PMID: 7615603.
• [11] Hazle C, Duby C. Anterior cruciate ligament injury diagnosis and management in a pediatric patient: a case report. Int J Sports Phys Ther 2012;7:678–90.
• [12] Doi K. Computer-aided diagnosis in medical imaging: historical review, current status and future potential. Comput Med Imaging Graph 2007;31:198–211. http://dx.doi.org/10.1016/j.compmedimag.2007.02.002.
• [13] Liu F, Zhou Z, Samsonov A, Blankenbaker D, Larison W, Kanarek A, et al. Deep learning approach for evaluating knee MR images: achieving high diagnostic performance for cartilage lesion detection. Radiology 2018;289(1):160–9. http://dx.doi.org/10.1148/radiol.2018172986.
• [14] Štajduhar I, Mamula M, Miletic´ D, Ünal G. Semi-automated detection of anterior cruciate ligament injury from MRI. Comput Methods Programs Biomed 2017;140:151–64. http://dx.doi.org/10.1016/j.cmpb.2016.12.006.
• [15] Pedoia V, Norman B, Mehany SN, Bucknor MD, Link TM, Majumdar S. 3D convolutional neural networks for detection and severity staging of meniscus and PFJ cartilage morphological degenerative changes in osteoarthritis and anterior cruciate ligament subjects. J Magn Reson Imaging 2018;1–11. http://dx.doi.org/10.1002/jmri.26246.
• [16] Liu F, Zhou Z, Jang H, Samsonov A, Zhao G, Kijowski R. Deep convolutional neural network and 3D deformable approach for tissue segmentation in musculoskeletal magnetic resonance imaging. Magn Reson Med 2018;79:2379–91. http://dx.doi.org/10.1002/mrm.2684.1.
• [17] Norman B, Pedoia V, Majumdar S. Use of 2D U-Net convolutional neural networks for automated cartilage and meniscus segmentation of knee MR imaging data to determine relaxometry and morphometry. Radiology 2018;288:177–85. http://dx.doi.org/10.1148/radiol.2018172322.
• [18] Salerno S, Granata C, Trapenese M, Cannata V, Curione D, Camilla M, et al. Is MRI imaging in pediatric age totally safe? A critical reprisal. La radiologia medica 2018;123:695–702. http://dx.doi.org/10.1007/s11547-018-0896-1.
• [19] Heydari Z, Farahmand F, Arabalibeik H, Parnianpour M. Adaptive neuro-fuzzy inference system for classification of ACL-ruptured knees using arthrometric data. Ann Biomed Eng 2008;36:1449–57. http://dx.doi.org/10.1007/s10439-008-9532-x.
• [20] Khaiyat OA, Norris J. Electromyographic activity of selected trunk, core, and thigh muscles incommonly used exercises for ACL rehabilitation. J Phys Ther Sci 2018;30:642. http://dx.doi.org/10.1589/jpts.30.642.
• [21] Pincheira PA, Silvestre R, Armijo-Olivo S, Guzman-Venegas R. Ankle perturbation generates bilateral alteration of knee muscle onset times after unilateral anterior cruciate ligament reconstruction. PeerJ 2018;6:e5310. http://dx.doi.org/10.7717/peerj.5310.
• [22] Coats-Thomas MS, Miranda DL, Badger GJ, Fleming BC. Effects of ACL reconstruction surgery on muscle activity of the lower limb during a jump-cut maneuver in males and females. J Orthop Res 2013;31:1890–6. http://dx.doi.org/10.1002/jor.22470.
• [23] Oliver G, Portabella F, Hernandez JA. A comparative study of the neuromuscular response during a dynamic activity after anterior cruciate ligament reconstruction. Eur J Orthop Surg Traumatol 2018. http://dx.doi.org/10.1007/s00590-018-2334-4.
• [24] Drechsler WI, Cramp MC, Scott OM. Changes in muscle strength and EMG median frequency after anterior cruciate ligament reconstruction. Eur J Appl Physiol 2006;98:613–23. http://dx.doi.org/10.1007/s00421-006-0311-9.
• [25] Leporace G, Ribeiro G, Nadal J, Alberto L. Differences in time–frequency representation of lower limbs myoelectric activity during single and double leg landing in male athletes. J Electromyogr Kinesiol 2011;21:506–11. http://dx.doi.org/10.1016/j.jelekin.2010.12.001.
• [26] Riemann BL, Myers JB, Lephart SM. Sensorimotor system measurement techniques. J Athl Train 2002;37(1):85–98. PubMed PMID: 16558672.
• [27] Riemann BL, Lephart SM. The sensorimotor system. Part I. The physiologic basis of functional joint stability. J Athl Train 2002;37(1):71–9. PubMed PMID: 16558670.
• [28] Riemann BL, Lephart SM. The sensorimotor system. Part II. The role of proprioception in motor control and functional joint stability. J Athl Train 2002;37(1):80–4. PubMed PMID: 16558671.
• [29] Uwisengeyimana J, Ibrikci T. Diagnosing knee osteoarthritis using artificial neural networks and deep learning. Biomed Stat Inform 2017;2:95–102. http://dx.doi.org/10.11648/j.bsi.20170203.11.
• [30] Markovic G, Mikulic P. Neuro-musculoskeletal and performance adaptations to lower-extremity plyometric training. Sport Med 2010;40:859–95. http://dx.doi.org/10.2165/11318370-000000000-00000.
• [31] Hewett TE, Zazulak BT, Myer GD, Ford KR. A review of electromyographic activation levels, timing differences, and increased anterior cruciate ligament injury incidence in female athletes. Br J Sports Med 2005;39:347–50. http://dx.doi.org/10.1136/bjsm.2005.018572.
• [32] Davies G, Riemann BL, Manske R. Current concepts of plyometric exercise. Int J Sports Phys Ther 2015;10:760–86. PubMed PMID: 26618058.
• [33] Huang PY, Lin CF. Effects of balance training combined with plyometric exercise in postural control: application in individuals with functional ankle instability. 6th WCB; IFMBE Proc, vol. 31. 2010;p. 232–5. http://dx.doi.org/10.1007/978-3-642-14515-5_60.
• [34] Decker MJ, Torry MR, Wyland DJ, Sterett WI, Steadman JR. Gender differences in lower extremity kinematics, kinetics and energy absorption during landing. Clin Biomech 2003;18:662–9. http://dx.doi.org/10.1016/S0268-0033(03)00090-1.
• [35] Caulfield BM, Garrett M. Functional instability of the ankle: differences in patterns of ankle and knee movement prior to and post landing in a single leg jump. Int J Sports Med 2002;23:64–8. http://dx.doi.org/10.1055/s-2002-19272.
• [36] Laughlin WA, Weinhandl JT, Kernozek TW, Cobb SC, Keenan KG, O'connor KM. The effects of single-leg landing technique on ACL loading. J Biomech 2011;44:1845–51. http://dx.doi.org/10.1016/j.jbiomech.2011.04.010.
• [37] Shin YS, Jeon JJ. Pseudo Wigner–Ville time–frequency distribution and its application to machinery condition monitoring. Shock Vib 1993;1:65–76. http://dx.doi.org/10.3233/SAV-1993-1109.
• [38] Novak P, Novak V. Time/frequency mapping of the heart rate, blood pressure and respiratory signals. Med Biol Eng Comput 1993;31:103–10. http://dx.doi.org/10.1007/BF02446667.
• [39] Hanson AM, Padua DA, Blackburn JT, Prentice WE, Hirth CJ. Muscle activation during side-step cutting maneuvers in male and female soccer athletes. J Athl Train 2008;43:133– 43. http://dx.doi.org/10.4085/1062-6050-43.2.133.
• [40] Shin CS, Chaudhari AM, Andriacchi TP. The influence of deceleration forces on ACL strain during single-leg landing: a simulation study. J Biomech 2007;40:1145–52. http://dx.doi.org/10.1016/j.jbiomech.2006.05.004.
• [41] Sainath TN, Kingsbury B, Saon G, Soltau H, Rahman MA, Dahl G, et al. Deep convolutional neural networks for large-scale speech tasks. Neural Netw 2015;64:39–48. http://dx.doi.org/10.1016/j.neunet.2014.08.005.
• [42] Hubel DH, Wiesel TN. Receptive fields and functional architecture of monkey striate cortex. J Physiol 1968;195:215–43. http://dx.doi.org/10.1113/jphysiol.1968.sp008455.
• [43] Jia F, Lei Y, Lu N, Xing S. Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization. Mech Syst Signal Process 2018;110:349–67. http://dx.doi.org/10.1016/j.ymssp.2018.03.025.
• [44] Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, et al. Recent advances in convolutional neural networks. J Comput Vis Pattern Recognit 2015, arXiv:1512.07108.
• [45] Anaraki AK, Ayati M, Kazemi F. Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms. Biocybern Biomed Eng 2019;39:63–74. http://dx.doi.org/10.1016/j.bbe.2018.10.004.
• [46] Zeiler MD. ADADELTA: an adaptive learning rate method. Mach Learn 2012, arXiv:1212.5701.
• [47] Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 2014;15:1929–58.
• [48] Murugan P, Durairaj S. Regularization and optimization strategies in deep convolutional neural network. Comput Vis Pattern Recognit 2017, arXiv:1712.04711.
• [49] Murugan P. Implementation of deep convolutional neural network in multi-class categorical image classification. Comput Vis Pattern Recognit 2018, arXiv:1801.01397.
• [50] Theisen D, Rada I, Brau A, Gette P, Seil R. Muscle activity onset prior to landing in patients after anterior cruciate ligament injury: a systematic review and meta-analysis. PloS ONE 2016;11(5):e0155277. http://dx.doi.org/10.1371/journal.pone.0155277.
• [51] San Martín-Mohr C, Cristi-Sánchez I, Pincheira PA, Reyes A, Berral FJ, Oyarzo C. Knee sensorimotor control following anterior cruciate ligament reconstruction: a comparison between reconstruction techniques. PloS ONE 2018;13(11): e0205658. http://dx.doi.org/10.1371/journal.pone.0205658.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).

PL

Korekta do artykułu zamieszczona w 2022, Vol. 42, no. 2, s. 736.