PL EN


Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników
Tytuł artykułu

Prediction of displacement in the equine third metacarpal bone using a neural network prediction algorithm

Identyfikatory
Warianty tytułu
Języki publikacji
EN
Abstrakty
EN
Bone is a nonlinear, inhomogeneous and anisotropic material. To predict the behavior of bones expert systems are employed to reduce the computational cost and to enhance the accuracy of simulations. In this study, an artificial neural network (ANN) was used for the prediction of displacement in long bones followed by ex-vivo experiments. Three hydrated third metacarpal bones (MC3) from 3 thoroughbred horses were used in the experiments. A set of strain gauges were distributed around the midshaft of the bones. These bones were then loaded in compression in an MTS machine. The recordings of strains, load, load exposure time, and displacement were used as ANN input parameters. The ANN which was trained using 3,250 experimental data points from two bones predicted the displace-ment of the third bone (R2 ≥ 0.98). It was suggested that the ANN should be trained using noisy data points. The proposed modification in the training algorithm makes the ANN very robust against noisy inputs measurements. The performance of the ANN was evaluated in response to changes in the number of input data points and then by assuming a lack of strain data. A finite element analysis (FEA) was conducted to replicate one cycle of force-displace-ment experimental data (to gain the same accuracy produced by the ANN). The comparison of FEA and ANN displacement predictions indicates that the ANN produced a satisfactory outcome within a couple of seconds, while FEA required more than 160 times as long to solve the same model (CPU time: 5 h and 30 min).
Twórcy
  • Department of Mechanical Engineering, The University of Melbourne, Grattan Street, Parkville, Melbourne 3010, Australia; Department of Veterinary Biosciences The University of Melbourne, Grattan Street, Parkville, Melbourne 3010, Australia
  • Department of Mechanical Engineering, The University of Melbourne, Parkville, Melbourne, Australia
  • Department of Mechanical Engineering, The University of Melbourne, Parkville, Melbourne, Australia
  • Department of Veterinary Biosciences The University of Melbourne, Parkville, Melbourne, Australia
Bibliografia
  • [1] Whitton RC, Ayodele BA, Hitchens PL, Mackie EJ. Subchondral bone microdamage accumulation in distal metacarpus of Thoroughbred racehorses. Equine Vet J 2018;50:766–73.
  • [2] Ziaeipoor H, Martelli S, Pandy M, Taylor M. Efficacy and efficiency of multivariate linear regression for rapid prediction of femoral strain fields during activity. Med Eng Phys 2019;63:88–92.
  • [3] Geraldes DM, Modenese L, Phillips ATM. Consideration of multiple load cases is critical in modelling orthotropic bone adaptation in the femur. Biomech Model Mechanobiol 2016;15:1029–42.
  • [4] Taylor M, Perilli E, Martelli S. Development of a surrogate model based on patient weight, bone mass and geometry to predict femoral neck strains and fracture loads. J Biomech 2017;55:121–7.
  • [5] Martig S, Hitchens PL, Stevenson MA, Whitton RC. Subchondral bone morphology in the metacarpus of racehorses in training changes with distance from the articular surface but not with age. J Anat 2018;232:919–30.
  • [6] Zadpoor AA, Weinans H. Patient-specific bone modeling and analysis: the role of integration and automation in clinical adoption. J Biomech 2015;48:750–60.
  • [7] Lekadir K, Noble C, Hazrati-Marangalou J, Hoogendoorn C, van Rietbergen B, Taylor ZA, et al. Patient-specific biomechanical modeling of bone strength using statistically-derived fabric tensors. Ann Biomed Eng 2016;44:234–46.
  • [8] Taddei F, Cristofolini L, Martelli S, Gill HS, Viceconti M. Subject-specific finite element models of long bones: an in vitro evaluation of the overall accuracy. J Biomech 2006;39:2457–67.
  • [9] Harrison SM, Chris Whitton R, Kawcak CE, Stover SM, Pandy MG. Evaluation of a subject-specific finite-element model of the equine metacarpophalangeal joint under physiological load. J Biomech 2014;47:65–73.
  • [10] Currey J. Measurement of the mechanical properties of bone: a recent history. Clin Orthop Relat Res 2009;467:1948–54.
  • [11] Eskinazi I, Fregly BJ. Surrogate modeling of deformable joint contact using artificial neural networks. Med Eng Phys 2015;37:885–91.
  • [12] Hambli R. Apparent damage accumulation in cancellous bone using neural networks. J Mech Behav Biomed Mater 2011;4:868–78.
  • [13] Hambli R. Numerical procedure for multiscale bone adaptation prediction based on neural networks and finite element simulation. Finite Elem Anal Des 2011;47:835–42.
  • [14] Hambli R. Application of neural networks and finite element computation for multiscale simulation of bone remodeling. J Biomech Eng 2010;132114502.
  • [15] Zadpoor AA, Campoli G, Weinans H. Neural network prediction of load from the morphology of trabecular bone. Appl Math Model 2013;37:5260–76.
  • [16] Gföhler M, Peham C. What can finite element analysis tell us? Equine Vet J 2013;45:265–6.
  • [17] Marr C. Equine Veterinary Journal: recent and future directions. Equine Vet J 2014;46:1–3.
  • [18] Mouloodi S, Khojasteh J, Salehi M, Mohebbi S. Size dependent free vibration analysis of multicrystalline nanoplates by considering surface effects as well as interface region. Int J Mech Sci 2014;85:160–7.
  • [19] Mouloodi S, Mohebbi S, Khojasteh J, Salehi M. Size-dependent static characteristics of multicrystalline nanoplates by considering surface effects. Int J Mech Sci 2014;79:162–7.
  • [20] Shanmuganathan S. Artificial neural network modelling: an introduction. In: Shanmuganathan S, Samarasinghe S, editors. Artificial neural network modelling. Cham: Springer International Publishing; 2016. p. 1–14.
  • [21] Hambli R, Chamekh A, Bel Hadj Salah H. Real-time deformation of structure using finite element and neural networks in virtual reality applications. Finite Elem Anal Des 2006;42:985–91.
  • [22] Ziaeipoor H, Taylor M, Pandy M, Martelli S. A novel training-free method for real-time prediction of femoral strain. J Biomech 2019;86:110–6.
  • [23] Vasundara M, Padmanaban K, Sabareeswaran M, RajGanesh M. Machining fixture layout design for milling operation using FEA, ANN and RSM. Procedia Eng 2012;38:1693–703.
  • [24] Javadi A, Tan T, Zhang M. Neural network for constitutive modelling in finite element analysis. Comput Assisted Mech Eng Sci 2003;10:523–30.
  • [25] Harrison SM, Whitton RC, Kawcak CE, Stover SM, Pandy MG. Evaluation of a subject-specific finite-element model of the equine metacarpophalangeal joint under physiological load. J Biomech 2014;47:65–73.
  • [26] Merritt J, Burvill C, Pandy M, Davies H. Determination of mechanical loading components of the equine metacarpus from measurements of strain during walking. Equine Vet J 2006;38:440–4.
  • [27] Merritt JS, Davies H, Burvill C, Pandy MG. Influence of muscle-tendon wrapping on calculations of joint reaction forces in the equine distal forelimb. Biomed Res Int 2008;2008.
  • [28] McCarty CA, Thomason JJ, Gordon KD, Burkhart TA, Milner JS, Holdsworth DW. Finite-element analysis of bone stresses on primary impact in a large-animal model: the distal end of the equine third metacarpal. PLoS One 2016;11e0159541.
  • [29] Sousa WdS, de Sousa FdA. Rede neural artificial aplicada à previsão de vazão da Bacia Hidrográfica do Rio Piancó. Revista Brasileira de Engenharia Agricola e Ambiental- Agriambi 2010;14.
  • [30] Barron AR. Universal approximation bounds for superpositions of a sigmoidal function. IEEE Trans Inf Theory 1993;39:930–45.
  • [31] Jin D, Lin S. Advances in computer science, intelligent systems and environment. Springer Science & Business Media; 2011.
  • [32] Liang G, Chandrashekhara K. Neural network based constitutive model for elastomeric foams. Eng Struct 2008;30:2002–11.
  • [33] Kopal I, Harnicárová M, Valícek J, Kušnerová M. Modeling the temperature dependence of dynamic mechanical properties and visco-elastic behavior of thermoplastic polyurethane using artificial neural network. Polymers 2017;9:519.
  • [34] Yang X, Behroozi M, Olatunbosun OA. A neural network approach to predicting car tyre micro-scale and macro-scale behaviour. J Intell Learn Syst Appl 2014;6:11.
  • [35] Hornik K. Approximation capabilities of multilayer feedforward networks. Neural Networks 1991;4:251–7.
  • [36] Schöllhorn WI. Applications of artificial neural nets in clinical biomechanics. Clin Biomech 2004;19:876–98.
  • [37] Saini LM. Peak load forecasting using Bayesian regularization, Resilient and adaptive backpropagation learning based artificial neural networks. Electr Power Syst Res 2008;78:1302–10.
  • [38] Demuth H, Beale M. Matlab neural network toolbox user's guide version 6. The MathWorks Inc; 2009.
  • [39] MacKay DJ. Bayesian interpolation. Neural Comput 1992;4:415–47.
  • [40] Fausett LV. Fundamentals of neural networks: architectures, algorithms, and applications. Prentice-Hall Englewood Cliffs; 1994.
  • [41] Mouloodi S, Rahmanpanah H, Burvill C, Davies HM. Accuracy quantification of the reverse engineering and high-order finite element analysis of equine MC3 forelimb. J Equine Vet Sci 2019.
  • [42] Mouloodi S, Rahmanpanah H, Burvill CR, Davies HMS. Converging-diverging shape configuration of the diaphysis of equine third metacarpal bone through computer-aided design. Comparative Exercise Physiology 2019. Accepted for Publication.
  • [43] Nobakhti S, Katsamenis OL, Zaarour N, Limbert G, Thurner PJ. Elastic modulus varies along the bovine femur. J Mech Behav Biomed Mater 2017;71:279–85.
  • [44] Nobakhti S, Shefelbine SJ. On the relation of bone mineral density and the elastic Modulus in healthy and pathologic bone. Curr Osteoporos Rep 2018;1–7.
  • [45] Noh H, You T, Mun J, Han B. Regularizing deep neural networks by noise: its interpretation and optimization. Adv Neural Inf Process Syst 2017;5109–18.
  • [46] Zur RM, Jiang Y, Pesce LL, Drukker K. Noise injection for training artificial neural networks: a comparison with weight decay and early stopping. Med Phys 2009;36:4810–8.
  • [47] Liley H, Zhang J, Firth E, Fernandez J, Besier T. Using partial least squares regression as a predictive tool in describing equine third metacarpal bone shape. Comput Methods Biomech Biomed Engin 2017;20:1609–12.
  • [48] Koivisto J, Kiljunen T, Kadesjö N, Shi X-Q, Wolff J. Effective radiation dose of a MSCT, two CBCT and one conventional radiography device in the ankle region. J Foot Ankle Res 2015;8:8.
  • [49] Semelka RC, Armao DM, Elias J, Huda W. Imaging strategies to reduce the risk of radiation in CT studies, including selective substitution with MRI. J Magn Reson Imaging 2007;25:900–9.
  • 50] Fujita H, Hatanaka Y. Computer-aided diagnosis with retinal fundus images. Medical image analysis and informatics. CRC Press; 2017. p. 59–86.
  • [51] Sun W, Lal P. Recent development on computer aided tissue engineering — a review. Comput Methods Programs Biomed 2002;67:85–103.
  • [52] Rathnayaka K, Momot KI, Noser H, Volp A, Schuetz MA, Sahama T, et al. Quantification of the accuracy of MRI generated 3D models of long bones compared to CT generated 3D models. Med Eng Phys 2012;34:357–63.
  • [53] Merritt JS, Davies HMS, Burvill C, Pandy MG. Influence of muscle-tendon wrapping on calculations of joint reaction forces in the equine distal forelimb. J Biomed Biotechnol 2008.
  • [54] Mouloodi S, Rahmanpanah H, Burvill C, Davies H. Prediction of load in a long bone using an artificial neural network prediction algorithm. J Mech Behav Biomed 2019;103527.
Uwagi
PL
Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).
Typ dokumentu
Bibliografia
Identyfikator YADDA
bwmeta1.element.baztech-6f5364cf-f1a9-410f-bfbe-8f20a74cb086
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.