Abstract
Inspired by the recent advancement in deep learning (DL) techniques, this study intended to confirm whether DL models could be trained to predict the elastic behavior of trabecular bone, a highly hierarchical biological material, using its dual-energy x-ray absorptiometry (DXA) images. The convolutional neural network, the most successful DL model in imaging-based predictions, was trained using simulated DXA images of trabecular bone samples as input and their apparent elastic modulus (Eapparent) determined using microCT-based finite element simulations as output (label). The results showed that the DL model achieved high fidelity in predicting Eapparent of trabecular bone samples (R2 > 0.86), and its performance appeared to be better than that of histomorphometric parameter-based regression models built using the same bone samples. The outcome of this study suggests that DXA image-based DL techniques can be used for multiscale modeling of trabecular bone to predict its elastic behavior.
Similar content being viewed by others
References
N.C. Wright, A.C. Looker, K.G. Saag, J.R. Curtis, E.S. Delzell, S. Randall, and B. Dawson-Hughes, J. Bone Miner. Res. 29, 2520. (2014).
R. Bouillon, P. Burckhardt, C. Christiansen, H. Fleisch, T. Fujita, C. Gennari, T. Marin, G. Mazzuoli, L. Melton, and J. Ringe, Am. J. Med. 90, 107. (1991).
E.S. Siris, Y.T. Chen, T.A. Abbott, E. Barrett-Connor, P.D. Miller, L.E. Wehren, and M.L. Berger, Arch. Intern. Med. 164, 1108. (2004).
H.K. Genant, K. Engelke, T. Fuerst, C.C. Glüer, S. Grampp, S.T. Harris, M. Jergas, T. Lang, Y. Lu, and S. Majumdar, J. Bone Miner. Res. 11, 707. (1996).
L. Pothuaud, P. Carceller, and D. Hans, Bone 42, 775. (2008).
R. Winzenrieth, A. Heraud, B. Rabier, P. Carceller, L. Pothuaud, and D. Hans, Calcif. Tissue Int. 82, S181. (2008).
G.L. Niebur, M.J. Feldstein, J.C. Yuen, T.J. Chen, and T.M. Keaveny, J. Biomech. 33, 1575. (2000).
B. Borah, G.J. Gross, T.E. Dufresne, T.S. Smith, M.D. Cockman, P.A. Chmielewski, M.W. Lundy, J.R. Hartke, and E.W. Sod, Anat. Rec. Off. Publ. Am. Assoc. Anat. 265, 101. (2001).
M. Bessho, I. Ohnishi, H. Okazaki, W. Sato, H. Kominami, S. Matsunaga, and K. Nakamura, J. Orthop. Sci. 9, 545. (2004).
T. Le Corroller, J. Halgrin, M. Pithioux, D. Guenoun, P. Chabrand, and P. Champsaur, Osteoporos. Int. 23, 163. (2012).
X.L.N. Dong, M. Shirvaikar, and X.D. Wang, Bone 56, 327. (2013).
X.N. Dong, R. Pinninti, A. Tvinnereim, T. Lowe, D. Di Paolo, and M. Shirvaikar, J. Biomech. 48, 2968. (2015).
P. Xiao, T. Zhang, X.N. Dong, Y. Han, Y. Huang, and X. Wang, Bone Rep. 13, 100295. (2020).
A.W. Popp, S. Meer, M.A. Krieg, R. Perrelet, D. Hans, and K. Lippuner, Eur. Spine J. 25, 3432. (2016).
L. Pothuaud, N. Barthe, B. Merino, P. Carceller, and D. Hans, Bone 40, S248. (2007).
A. Esteva, B. Kuprel, R.A. Novoa, J. Ko, S.M. Swetter, H.M. Blau, and S. Thrun, Nature 542, 115. (2017).
Y. Ding, J.H. Sohn, M.G. Kawczynski, H. Trivedi, R. Harnish, N.W. Jenkins, D. Lituiev, T.P. Copeland, M.S. Aboian, and C.M. Aparici, Radiology 290, 456. (2019).
X.Y. Chen, Y.W. Xu, S.C. Yan, D.W.K. Wong, T.Y. Wong, and J. Liu, Medical Image Computing and Computer-Assisted Intervention, Pt Iii. 9351, 669 (2015)
T. Harrigan, and R. Mann, J. Mater. Sci. 19, 761. (1984).
A. Odgaard, Bone 21, 191. (1997).
M.S. Hefzy, and S.P. Singh, Med. Eng. Phys. 19, 50. (1997).
H.J. Leng, X.N. Dong, and X.D. Wang, J. Biomech. 42, 491. (2009).
S.A. Goldstein, J. Biomech. 20, 1055. (1987).
X.N. Dong, Y. Lu, M. Krause, G. Huber, Y. Chevalier, H. Leng, and G. Maquer, J.. Biomech. 77, 223. (2018).
B.C. Khoo, K. Brown, C. Cann, K. Zhu, S. Henzell, V. Low, S. Gustafsson, R.I. Price, and R.L. Prince, Osteoporos. Int. 20, 1539. (2009).
A.J. Burghardt, G.J. Kazakia, T.M. Link, and S. Majumdar, Osteoporos. Int. 20, 2017. (2009).
E. Dall’Ara, D. Pahr, P. Varga, F. Kainberger, and P. Zysset, Osteoporos. Int. 23, 563. (2012).
S. Patil and B. Ravi, International Conference on Computer Aided Design and Computer Graphics 415 (2005)
H. Kandi, D. Mishra, and S.R.K.S. Gorthi, Comput Secur. 65, 247. (2017).
X.S. Liu, X.H. Zhang, K.K. Sekhon, M.F. Adams, D.J. McMahon, J.P. Bilezikian, E. Shane, and X.E. Guo, J. Bone Miner. Res. 25, 746. (2010).
G.Y. Yang, J. Kabel, B. Van Rietbergen, A. Odgaard, R. Huiskes, and S.C. Cowin, J. Elast. 53, 125. (1998).
J. Kabel, A. Odgaard, B. van Rietbergen, and R. Huiskes, Bone 24, 115. (1999).
E. Mittra, C. Rubin, B. Gruber, and Y.-X. Qin, J. Biomech. 41, 368. (2008).
B. Helgason, E. Perilli, E. Schileo, F. Taddei, S. Brynjolfsson, and M. Viceconti, Clin. Biomech. 23, 135. (2008).
V. Boudousq, D.M. Goulart, J.M. Dinten, C.C. de Kerleau, E. Thomas, O. Mares, and P.O. Kotzki, Osteoporos. Int. 16, 813. (2005).
D. Ulrich, B. Van Rietbergen, A. Laib, and P. Ruegsegger, Bone 25, 55. (1999).
S.C. Cowin, Mech. Mater. 4, 137. (1985).
M. Moesen, L. Cardoso, and S.C. Cowin, Mech. Mater. 54, 70. (2012).
R. Moreno, O. Smedby, and D.H. Pahr, Biomech. Model. Mechanobiol. 15, 831. (2016).
B. Van Rietbergen, A. Odgaard, J. Kabel, and R. Huiskes, J. Orthopaed. Res. 16, 23. (1998).
C.H. Turner, S.C. Cowin, J.Y. Rho, R.B. Ashman, and J.C. Rice, J. Biomech. 23, 549. (1990).
J. Kabel, B. van Rietbergen, A. Odgaard, and R. Huiskes, Bone 25, 481. (1999).
C. Yang, Y. Kim, S. Ryu, and G.X. Gu, Mater. Design. 189, 108509. (2020).
C. Yang, Y. Kim, S. Ryu, and G.X. Gu, MRS Commun. 9, 609. (2019).
Acknowledgements
The authors are grateful to Mr. James Schmitz at UT Health San Antonio for technical assistance in the acquisition of microCT scans of human cadaveric proximal femur samples.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of interest
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Xiao, P., Zhang, T., Haque, E. et al. Prediction of Elastic Behavior of Human Trabecular Bone Using A DXA Image-Based Deep Learning Model. JOM 73, 2366–2376 (2021). https://doi.org/10.1007/s11837-021-04704-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11837-021-04704-z