Abstract
Finite element (FE) analysis is an important computational tool in biomechanics. However, its adoption into clinical practice has been hampered by its computational complexity and required high technical competences for clinicians. In this paper we propose a supervised learning approach to predict the outcome of the FE analysis. We demonstrate our approach on clinical CT and X-ray femur images for FE predictions (FEP), with features extracted, respectively, from a statistical shape model and from 2D-based morphometric and density information. Using leave-one-out experiments and sensitivity analysis, comprising a database of 89 clinical cases, our method is capable of predicting the distribution of stress values for a walking loading condition with an average correlation coefficient of 0.984 and 0.976, for CT and X-ray images, respectively. These findings suggest that supervised learning approaches have the potential to leverage the clinical integration of mechanical simulations for the treatment of musculoskeletal conditions.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
J.A. Kanis, Assessment of Osteoporosis at the Primary Health Care Level (World Health, 2007), p. 339
T. Whitmarsh, K.D. Fritscher, L. Humbert, L.M. Del Rio Barquero, T. Roth, C. Kammerlander et~al., A statistical model of shape and bone mineral density distribution of the proximal femur for fracture risk assessment. Med. Image Comput. Comput. Assist. Interv. 14, 393–400 (2011)
N. Sarkalkan, J.H. Waarsing, P.K. Bos, H. Weinans, A.A. Zadpoor, Statistical shape and appearance models for fast and automated estimation of proximal femur fracture load using 2D finite element models. J. Biomech. 47, 3107–3114 (2014). doi:10.1016/j.jbiomech.2014.06.027
E. Dall’Ara, B. Luisier, R. Schmidt, F. Kainberger, P. Zysset, D. Pahr, A nonlinear QCT-based finite element model validation study for the human femur tested in two configurations in vitro. Bone 52, 27–38 (2013). doi:10.1016/j.bone.2012.09.006
S. Poelert, E. Valstar, H. Weinans, A.A. Zadpoor, Patient-specific finite element modeling of bones. Proc. Inst. Mech. Eng. H 227, 464–478 (2013). doi:10.1177/0954411912467884
T. Heimann, H.-P. Meinzer, Statistical shape models for 3D medical image segmentation: a review. Med. Image Anal. 13, 543–563 (2009). doi:10.1016/j.media.2009.05.004
L. Grassi, E. Schileo, C. Boichon, M. Viceconti, F. Taddei, Comprehensive evaluation of PCA-based finite element modelling of the human femur. Med. Eng. Phys. 36, 1246–1252 (2014). doi:10.1016/j.medengphy.2014.06.021
I. Castro-Mateos, J.M. Pozo, T.F. Cootes, J.M. Wilkinson, R. Eastell, A.F. Frangi, Statistical shape and appearance models in osteoporosis. Curr. Osteoporos Rep. 12, 163–173 (2014). doi:10.1007/s11914-014-0206-3
T.F. Cootes, C.J. Taylor, D.H. Cooper, J. Graham, Active shape models-their training and application. Comput. Vis. Image Underst. 61, 38–59 (1995). doi:10.1006/cviu.1995.1004
S. Bonaretti, C. Seiler, C. Boichon, M. Reyes, P. Büchler, Image-based vs. mesh-based statistical appearance models of the human femur: implications for finite element simulations. Med. Eng. Phys. 36, 1626–1635 (2014). doi:10.1016/j.medengphy.2014.09.006
C. Boichon, et~al., Shape indexing of human femur using morphing and principal component analysis. VPH (2010)
A.D. Speirs, M.O. Heller, G.N. Duda, W.R. Taylor, Physiologically based boundary conditions in finite element modelling. J. Biomech. 40, 2318–2323 (2007). doi:10.1016/j.jbiomech.2006.10.038
L. Breiman, Random forests. Mach. Learn. 45, 5–32 (2001). doi:10.1023/A:1010933404324
A. Criminisi, J. Shotton (eds.), Decision Forests for Computer Vision and Medical Image Analysis, vol. 1 (Springer, London, 2013). doi:10.1007/978-1-4471-4929-3
S. Geisser, Predictive Inference (CRC Press, 1993)
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel et~al., Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
G. Zheng, 3D volumetric intensity reconstruction from 2D X-ray images using partial least squares regression, in 2013 IEEE 10th International Symposium on Biomedical Imaging (IEEE, 2013), pp. 1268–1271. doi:10.1109/ISBI.2013.6556762
E. Taghizadeh, G. Maquer, M. Reyes, P. Büchler, Including the Trabecular Anisotropy from Registered microCT Data in Homogenized FE Model Improves the Bone’s Mechanical Predictions (CMBBE, Amsterdam, 2014)
D. Larsson, B. Luisier, M.E. Kersh, E. Dall’ara, P.K. Zysset, M.G. Pandy et~al., Assessment of transverse isotropy in clinical-level CT images of trabecular bone using the gradient structure tensor. Ann. Biomed. Eng. 42, 950–959 (2014). doi:10.1007/s10439-014-0983-y
K. Lekadir, J. Hazrati-Marangalou, C. Hoogendoorn, Z. Taylor, B. van Rietbergen, A.F. Frangi, Statistical estimation of femur micro-architecture using optimal shape and density predictors. J. Biomech. 48, 598–603 (2015). doi:10.1016/j.jbiomech.2015.01.002
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Taghizadeh, E., Kistler, M., Büchler, P., Reyes, M. (2016). Fast Prediction of Femoral Biomechanics Using Supervised Machine Learning and Statistical Shape Modeling. In: Joldes, G., Doyle, B., Wittek, A., Nielsen, P., Miller, K. (eds) Computational Biomechanics for Medicine. Springer, Cham. https://doi.org/10.1007/978-3-319-28329-6_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-28329-6_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-28327-2
Online ISBN: 978-3-319-28329-6
eBook Packages: EngineeringEngineering (R0)