This study reports the development of an artificial neural network computation model to predict the accumulation of crack density and crack length in cancellous bone under a cyclic load. The model was then applied to conduct a parametric investigation into the effects of load level on fatigue crack accumulation in cancellous bone. The method was built in three steps: (1) conducting finite element simulations to predict fatigue growth of different three-dimensional micro-computed tomography cancellous bone specimens considering input combinations based on a factorial experimental design; (2) performing a training stage of an artificial neural network based on the results of step 1; and (3) applying the trained artificial neural network to rapidly predict the crack density and the crack length growth for cancellous bone under a cyclic loading for a given applied apparent strain, cycle frequency, bone volume fraction, bone density and apparent elastic modulus.
RhoJ-YKuhn-SpearingLZiouposP. Mechanical properties and the hierarchical structure of bone. Med Eng Phys1998; 20(2): 92–102.
2.
RaspantiMCongiuTGuizzardiS. Tapping-mode atomic force microscopy in fluid of hydrated extracellular matrix. Matrix Biol2001; 20(8): 601–604.
3.
HabelitzSBaloochMMarshallSJ, et al. In situ atomic force microscopy of partially demineralized human dentin collagen fibrils. J Struct Biol2002; 138(3): 227–236.
4.
MoussMERekikAZellaguiS, et al. Numerical modeling of the effects hydration and number of hydrogen bonds on the mechanical properties of the tropocollagen molecule. Proc IMechE, Part H: J Engineering in Medicine2020; 234: 299–306.
5.
CarterDCalerW. A cumulative damage model for bone fracture. J Orthop Res1985; 3(1): 84–90.
6.
PattinCCalerWCarterD. Cyclic mechanical property degradation during fatigue loading of cortical bone. J Biomech1996; 29(1): 69–79.
7.
MartinRBBurrDBSharkeyNA, et al. Skeletal tissue mechanics. New York: Springer, 1998.
8.
BurrDBTurnerCHNaickP, et al. Does microdamage accumulation affect the mechanical properties of bone?J Biomech1998; 31(4): 337–345.
9.
ZiouposPCurreyJ. Changes in the stiffness, strength, and toughness of human cortical bone with age. Bone1998; 22(1): 57–66.
10.
FazzalariNKuliwabaJForwoodM. Cancellous bone microdamage in the proximal femur: influence of age and osteoarthritis on damage morphology and regional distribution. Bone2002; 31(6): 697–702.
O’BrienFJTaylorDLeeTC. Microcrack accumulation at different intervals during fatigue testing of compact bone. J Biomech2003; 36(7): 973–980.
13.
HaddockSMYehOCMummaneniPV, et al. Similarity in the fatigue behavior of trabecular bone across site and species. J Biomech2004; 37(2): 181–187.
14.
NagarajaSCouseTLGuldbergRE. Trabecular bone microdamage and microstructural stresses under uniaxial compression. J Biomech2005; 38(4): 707–716.
15.
VashishthD. Hierarchy of bone microdamage at multiple length scales. Int J Fatigue2007; 29(6): 1024–1033.
16.
NormanTLYeniYBrownC, et al. Influence of microdamage on fracture toughness of the human femur and tibia. Bone1998; 23(3): 303–306.
17.
YeniYBrownCNormanTL. Influence of bone composition and apparent density on fracture toughness of the human femur and tibia. Bone1998; 22(1): 79–84.
18.
BurrDB. Remodeling and the repair of fatigue damage. Calcif Tissue Int1993; 53(1): S75–S81.
19.
LinkTM. Osteoporosis imaging: state of the art and advanced imaging. Radiology2012; 263(1): 3–17.
20.
GriffithJFGenantHK. New advances in imaging osteoporosis and its complications. Endocrine2012(1): 39–51.
21.
HambliRSoulatDGasserA, et al. Strain–damage coupled algorithm for cancellous bone mechano-regulation with spatial function influence. Comput Methods Appl Mech Eng2009; 198(33–36): 2673–2682.
22.
RapillardLCharleboisMZyssetPK. Compressive fatigue behavior of human vertebral trabecular bone. J Biomech2006; 39(11): 2133–2139.
23.
TaylorMCottonJZiouposP. Finite element simulation of the fatigue behaviour of cancellous bone. Meccanica2002; 37(4–5): 419–429.
24.
KosmopoulosVSchizasCKellerTS. Modeling the onset and propagation of trabecular bone microdamage during low-cycle fatigue. J Biomech2008; 41(3): 515–522.
25.
PrendergastPTaylorD. Prediction of bone adaptation using damage accumulation. J Biomech1994; 27(8): 1067–1076.
26.
TaylorDLeeT. A crack growth model for the simulation of fatigue in bone. Int J Fatigue2003; 25(5): 387–395.
27.
WaszczyszynZ (ed.). Neural networks in plasticity: some new results and prospects of applications. In: Proceedings of the European congress on computational methods in applied sciences and engineering (ECCOMAS 2000), Barcelona, 11–14 September 2000. Vienna: ECCOMAS.
28.
WaszczyszynZZiemiańskiL. Neural networks in mechanics of structures and materials–new results and prospects of applications. Comput Struct2001; 79(22–25): 2261–2276.
TheocarisPPanagiotopoulosP. Neural networks for computing in fracture mechanics. Methods and prospects of applications. Comput Methods Appl Mech Eng1993; 106(1–2): 213–228.
31.
TheocarisPSPanagiotopoulosP. Generalised hardening plasticity approximated via anisotropic elasticity: a neural network approach. Comput Methods Appl Mech Eng1995; 125(1–4): 123–139.
32.
SidartaDGhaboussiJ. Constitutive modeling of geomaterials from non-uniform material tests. Comput Geotech1998; 22(1): 53–71.
33.
FuQHashashYMJungS, et al. Integration of laboratory testing and constitutive modeling of soils. Comput Geotech2007; 34(5): 330–345.
34.
UngerJFKönkeC. Coupling of scales in a multiscale simulation using neural networks. Comput Struct2008; 86(21–22): 1994–2003.
35.
HambliR. Statistical damage analysis of extrusion processes using finite element method and neural networks simulation. Finite Elem Anal Des2009; 45(10): 640–649.
36.
LefikMBosoDSchreflerB. Artificial neural networks in numerical modelling of composites. Comput Methods Appl Mech Eng2009; 198(21–26): 1785–1804.
HernandezCBeaupreGKellerT, et al. The influence of bone volume fraction and ash fraction on bone strength and modulus. Bone2001; 29(1): 74–78.
39.
HambliRKaterchiHBenhamouC-L. Multiscale methodology for bone remodelling simulation using coupled finite element and neural network computation. Biomech Model Mechanobiol2011; 10(1): 133–145.
40.
ChabocheJ. Continuum damage mechanics: a tool to describe phenomena before crack initiation. Null Eng Des1981; 79: 309–319.
41.
WangXMasseDBLengH, et al. Detection of trabecular bone microdamage by micro-computed tomography. J Biomech2007; 40(15): 3397–3403.
42.
DendorferSMaierHTaylorD, et al. Anisotropy of the fatigue behaviour of cancellous bone. J Biomech2008; 41(3): 636–641.
43.
HambliRBoughattasMHDanielJ-L, et al. Prediction of denosumab effects on bone remodeling: a combined pharmacokinetics and finite element modeling. J Mech Behav Biomed Mater2016; 60: 492–504.
44.
TaiKDaoMSureshS, et al. Nanoscale heterogeneity promotes energy dissipation in bone. Nat Mater2007; 6(6): 454–462.
45.
HambliRLespessaillesEBenhamouC-L. Integrated remodeling-to-fracture finite element model of human proximal femur behavior. J Mech Behav Biomed Mater2013; 17: 89–106.
46.
ZiouposPCasinosA. Cumulative damage and the response of human bone in two-step loading fatigue. J Biomech1998; 31(9): 825–833.
47.
BurrDBForwoodMRFyhrieDP, et al. Bone microdamage and skeletal fragility in osteoporotic and stress fractures. J Bone Miner Res1997; 12(1): 6–15.
48.
HeaneyRP. Nutritional factors in osteoporosis. Annu Rev Nutr1993; 13(1): 287–316.
49.
HarriganTPJastyMMannRW, et al. Limitations of the continuum assumption in cancellous bone. J Biomech1988; 21(4): 269–275.
