0
Research Papers

Neural Network Optimization of Ligament Stiffnesses for the Enhanced Predictive Ability of a Patient-Specific, Computational Foot/Ankle Model

[+] Author and Article Information
Ruchi D. Chande

Department of Biomedical Engineering,
Virginia Commonwealth University,
401 West Main Street,
PO Box 843067,
Richmond, VA 23284-3067

Jennifer S. Wayne

Department of Biomedical Engineering,
Virginia Commonwealth University,
401 West Main Street,
PO Box 843067,
Richmond, VA 23284-3067
e-mail: jwayne@vcu.edu

1Corresponding author.

Manuscript received December 16, 2016; final manuscript received June 8, 2017; published online July 7, 2017. Assoc. Editor: Guy M. Genin.

J Biomech Eng 139(9), 091003 (Jul 07, 2017) (8 pages) Paper No: BIO-16-1524; doi: 10.1115/1.4037101 History: Received December 16, 2016; Revised June 08, 2017

Computational models of diarthrodial joints serve to inform the biomechanical function of these structures, and as such, must be supplied appropriate inputs for performance that is representative of actual joint function. Inputs for these models are sourced from both imaging modalities as well as literature. The latter is often the source of mechanical properties for soft tissues, like ligament stiffnesses; however, such data are not always available for all the soft tissues nor is it known for patient-specific work. In the current research, a method to improve the ligament stiffness definition for a computational foot/ankle model was sought with the greater goal of improving the predictive ability of the computational model. Specifically, the stiffness values were optimized using artificial neural networks (ANNs); both feedforward and radial basis function networks (RBFNs) were considered. Optimal networks of each type were determined and subsequently used to predict stiffnesses for the foot/ankle model. Ultimately, the predicted stiffnesses were considered reasonable and resulted in enhanced performance of the computational model, suggesting that artificial neural networks can be used to optimize stiffness inputs.

FIGURES IN THIS ARTICLE
<>
Copyright © 2017 by ASME
Your Session has timed out. Please sign back in to continue.

References

Liacouras, P. C. , and Wayne, J. S. , 2007, “ Computational Modeling to Predict Function of Joints: Application to the Lower Leg With Simulation of Two Cadaver Studies,” ASME J. Biomech. Eng., 129(6), pp. 811–817. [CrossRef]
Spratley, E. M. , Matheis, E. A. , Hayes, C. W. , Adelaar, R. S. , and Wayne, J. S. , 2013, “ Validation of a Population of Patient-Specific Adult Acquired Flatfoot Deformity Models,” J. Orthop. Res., 31(12), pp. 1861–1868. [CrossRef] [PubMed]
Lu, Y. , Pulasani, P. R. , Derakhshani, R. , and Guess, T. M. , 2013, “ Application of Neural Networks for the Prediction of Cartilage Stress in a Musculoskeletal System,” Biomed. Signal Process. Control, 8(6), pp. 475–482. [CrossRef] [PubMed]
Iaquinto, J. M. , and Wayne, J. S. , 2011, “ Effects of Surgical Correction for the Treatment of Adult Acquired Flatfoot Deformity: A Computational Investigation,” J. Orthop. Res., 29(7), pp. 1047–1054. [CrossRef] [PubMed]
Cheung, J. T. , Zhang, M. , Leung, A. K. , and Fan, Y. B. , 2005, “ Three-Dimensional Finite Element Analysis of the Foot During Standing—A Material Sensitivity Study,” J. Biomech., 38(5), pp. 1045–1054. [CrossRef] [PubMed]
Anderson, D. D. , Goldsworthy, J. K. , Shivanna, K. , Grosland, N. M. , Pedersen, D. R. , Thomas, T. P. , Tochigi, Y. , Marsh, J. L. , and Brown, T. D. , 2006, “ Intra-Articular Contact Stress Distributions at the Ankle Throughout Stance Phase-Patient-Specific Finite Element Analysis as a Metric of Degeneration Propensity,” Biomech. Model. Mechanobiol., 5(2–3), pp. 82–89. [CrossRef] [PubMed]
Sowmianarayanan, S. , Chandrasekaran, A. , and Kumar, R. K. , 2008, “ Finite Element Analysis of a Subtrochanteric Fractured Femur With Dynamic Hip Screw, Dynamic Condylar Screw, and Proximal Femur Nail Implants—A Comparative Study,” Proc. Inst. Mech. Eng. Part H, 222(1), pp. 117–127. [CrossRef]
Spratley, E. M. , and Wayne, J. S. , 2011, “ Computational Model of the Human Elbow and Forearm: Application to Complex Varus Instability,” Ann. Biomed. Eng., 39(3), pp. 1084–1091. [CrossRef] [PubMed]
Majors, B. J. , and Wayne, J. S. , 2011, “ Development and Validation of a Computational Model for Investigation of Wrist Biomechanics,” Ann. Biomed. Eng., 39(11), pp. 2807–2815. [CrossRef] [PubMed]
Elmore, K. A. , and Wayne, J. S. , 2013, “ Soft Tissue Structures Resisting Anterior Instability in a Computational Glenohumeral Joint Model,” Comput. Methods Biomech. Biomed. Eng., 16(7), pp. 781–789. [CrossRef]
Deland, J. T. , 2008, “ Adult-Acquired Flatfoot Deformity,” J. Am. Acad. Orthop. Surg., 16(7), pp. 399–406. [CrossRef] [PubMed]
Deland, J. T. , 2012, “ Spring Ligament Complex and Flatfoot Deformity: Curse or Blessing?,” Foot Ankle Int., 33(3), pp. 239–243. [CrossRef] [PubMed]
Williams, G. , Widnall, J. , Evans, P. , and Platt, S. , 2013, “ MRI Features Most Often Associated With Surgically Proven Tears of the Spring Ligament Complex,” Skeletal Radiol., 42(7), pp. 969–973. [CrossRef] [PubMed]
Vulcano, E. , Deland, J. T. , and Ellis, S. J. , 2013, “ Approach and Treatment of the Adult Acquired Flatfoot Deformity,” Curr. Rev. Musculoskeletal Med., 6(4), pp. 294–303. [CrossRef]
Deland, J. T. , de Asla, R. J. , Sung, I. H. , Ernberg, L. A. , and Potter, H. G. , 2005, “ Posterior Tibial Tendon Insufficiency: Which Ligaments Are Involved?,” Foot Ankle Int., 26(6), pp. 427–435. [CrossRef] [PubMed]
Younger, A. S. , Sawatzky, B. , and Dryden, P. , 2005, “ Radiographic Assessment of Adult Flatfoot,” Foot Ankle Int., 26(10), pp. 820–825. [CrossRef] [PubMed]
Louie, P. K. , Sangeorzan, B. J. , Fassbind, M. J. , and Ledoux, W. R. , 2014, “ Talonavicular Joint Coverage and Bone Morphology Between Different Foot Types,” J. Orthop. Res., 32(7), pp. 958–966. [CrossRef] [PubMed]
Conti, M. S. , Ellis, S. J. , Chan, J. Y. , Do, H. T. , and Deland, J. T. , 2015, “ Optimal Position of the Heel Following Reconstruction of the Stage II Adult-Acquired Flatfoot Deformity,” Foot Ankle Int., 36(8), pp. 919–927. [CrossRef] [PubMed]
Draves, D. J. , 1986, Anatomy of the Lower Extremity, Williams & Wilkins, Baltimore, MD.
Arangio, G. A. , Wasser, T. , and Rogman, A. , 2006, “ Radiographic Comparison of Standing Medial Cuneiform Arch Height in Adults With and Without Acquired Flatfoot Deformity,” Foot Ankle Int., 27(8), pp. 636–638. [CrossRef] [PubMed]
Spratley, E. M. , Matheis, E. A. , Hayes, C. W. , Adelaar, R. S. , and Wayne, J. S. , 2015, “ Effects of Degrees of Surgical Correction for Flatfoot Deformity in Patient-Specific Computational Models,” Ann. Biomed. Eng., 43(8), pp. 1947–1956. [CrossRef] [PubMed]
Spratley, E. M. , 2013, “ Patient-Specific Modeling of Adult Acquired Flatfoot Deformity Before and After Surgery,” Ph.D. thesis, Virginia Commonwealth University, Richmond, VA. http://scholarscompass.vcu.edu/etd/3278/
Hassoun, M. H. , 1995, Fundamentals of Artificial Neural Networks, The MIT Press, Cambridge, MA.
Haykin, S. , 2009, Neural Networks and Learning Machines, Pearson Prentice Hall, Upper Saddle River, NJ.
Specht, D. F. , 1991, “ A General Regression Neural Network,” IEEE Trans. Neural Networks, 2(6), pp. 568–576. [CrossRef]
Mahfouf, M. , 2006, Intelligent Systems Modeling and Decision Support in Bioengineering, Artech House, Norwood, MA.
Galushkin, A. I. , 2007, Neural Networks Theory, Springer Science & Business Media, Berlin.
Agatonovic-Kustrin, S. , and Beresford, R. , 2000, “ Basic Concepts of Artificial Neural Network (ANN) Modeling and Its Application in Pharmaceutical Research,” J. Pharm. Biomed. Anal., 22(5), pp. 717–727. [CrossRef] [PubMed]
Bas, B. , Ozgonenel, O. , Ozden, B. , Bekcioglu, B. , Bulut, E. , and Kurt, M. , 2012, “ Use of Artificial Neural Network in Differentiation of Subgroups of Temporomandibular Internal Derangements: A Preliminary Study,” J. Oral Maxillofac. Surg., 70(1), pp. 51–59. [CrossRef] [PubMed]
Taghavifar, H. , and Mardani, A. , 2014, “ Application of Artificial Neural Networks for the Prediction of Traction Performance Parameters,” J. Saudi Soc. Agric. Sci., 13(1), pp. 35–43.
Basheer, I. A. , and Hajmeer, M. , 2000, “ Artificial Neural Networks: Fundamentals, Computing, Design, and Application,” J. Microbiol. Methods, 43(1), pp. 3–31. [CrossRef] [PubMed]
Massie, D. D. , and Curtiss, P. S. , 2001, “ Neural Network Fundamentals for Scientists and Engineers,” International Conference on Efficiency, Costs, Optimization, Simulations, and Environmental Impact of Energy Systems (ECOS), Istanbul, Turkey, July 4–6, p. 123. https://pdfs.semanticscholar.org/b45c/a18c5ccceecfad3deb80486ea5cea8e1f575.pdf
Ahmed, F. E. , 2005, “ Artificial Neural Networks for Diagnosis and Survival Prediction in Colon Cancer,” Mol. Cancer, 4(1), p. 29. [CrossRef] [PubMed]
Eskinazi, I. , and Fregly, B. J. , 2013, “ Surrogate Knee Contact Modeling Using Artificial Neural Networks,” ASME Paper No. SBC2013-14581.
Kaufman, J. J. , Chiabrera, A. , Hatem, M. , Hakim, N. Z. , Figueiredo, M. , Nasser, P. , Lattuga, S. , Pilla, A. A. , and Siffert, R. S. , 1990, “ A Neural Network Approach for Bone Fracture Healing Assessment,” IEEE Eng. Med. Biol. Mag., 9(3), pp. 23–30. [CrossRef] [PubMed]
Rae, S. A. , Wang, W. J. , and Partridge, D. , 1999, “ Artificial Neural Networks: A Potential Role in Osteoporosis,” J. R. Soc. Med., 92(3), pp. 119–122. [CrossRef] [PubMed]
Lippman, R. P. , 1987, “ An Introduction to Computing With Neural Nets,” IEEE ASSP Mag., 3, pp. 4–22. [CrossRef]
Lavrenko, V. , 2015, “ Backpropagation: How It Works,” Introductory Applied Machine Learning (Class Lecture), University of Edinburgh, Edinburgh, UK.
Lavrenko, V. , 2015, “ Neural Networks 11: Backpropagation in Detail,” Introductory Applied Machine Learning (Class Lecture), University of Edinburgh, Edinburgh, UK.
Abu-Mostafa, Y. , 2012, “ Lecture 16: Radial Basis Functions,” Learning From Data, Introductory Machine Learning Course (Class Lecture), California Institute of Technology, Pasadena, CA.
Beale, M. H. , Hagan, M. T. , and Demuth, H. B. , 2013, “ Neural Network Toolbox, User's Guide R2013b,” MathWorks, Natick, MA.
Wettschereck, D. , and Dietterich, T. , 1992, “ Improving the Performance of Radial Basis Function Networks by Learning Center Locations,” Advances in Neural Information Processing Systems 4, Morgan Kaufmann, San Francisco, CA.
Masters, T. , 2013, Assessing and Improving Prediction and Classification, Timothy Masters, Fort Collins, CO.
Heath, G. , 2015, “ Tutorial on Neural Net Crossvalidation Design,” MathWorks, Natick, MA, accessed Feb. 8, 2016, https://www.mathworks.com/matlabcentral/newsreader/view_thread/340857
Sarrafian, S. K. , 1993, Anatomy of the Foot and Ankle: Descriptive, Topographic, Functional, Lippincott Williams & Wilkins, Philadelphia, PA.
Ewing, J. A. , Kaufman, M. K. , Hutter, E. E. , Granger, J. F. , Beal, M. D. , Piazza, S. J. , and Siston, R. A. , 2016, “ Estimating Patient-Specific Soft-Tissue Properties in a TKA Knee,” J. Orthop. Res., 34(3), pp. 435–443. [CrossRef] [PubMed]

Figures

Grahic Jump Location
Fig. 1

General artificial neural network architecture, multilayer feedforward network with single hidden layer. Inputs feed into the hidden layer with h hidden neurons; outputs of the hidden layer then feed into the neurons of the output layer. Interconnections among neurons are depicted as arrows with w representing their weights. (Adapted from Ref. 24).

Grahic Jump Location
Fig. 2

Major tasks. The flowchart depicts the major steps implemented in the current work. ANN refers to artificial neural network, and all the relevant ANN steps apply to each type of neural network described in the research (i.e., feedforward network and radial basis function network).

Grahic Jump Location
Fig. 3

Kinematic measures, right foot (medial view—left and dorsal view—right). Measures included talo-first metatarsal (θT1MT) and talonavicular (θTN) angles, and navicular (δNav) and first cuneiform (δ1st-CN) heights.

Grahic Jump Location
Fig. 4

Percent difference, stiffness predictions relative to assigned. Each bar represents the percent difference of a given output element relative to the target (assigned stiffness) values of the original patient-specific, AAFD computational model. The “zero” line represents the target stiffnesses, and the 14 output elements (stiffnesses of AAFD implicated ligaments) are listed along the vertical axis. Absolute maximum differences (indicated by the white and black arrows for the FFN and RBFN, respectively) of approximately 6% and 12% were calculated for the FFN and RBFN, respectively. (Note: Negative percentages indicate a “less stiff” ligament relative to the target).

Grahic Jump Location
Fig. 5

Percent difference, model kinematics relative to patient X-ray. Each bar represents the percent difference of a given kinematic measure relative to the patient-radiograph. The “zero” line represents the X-ray measures; and therefore, the closer a bar is to this line, the more closely the indicated model matches with the X-ray data. (Note: Negative percentages indicate an overprediction of the X-ray measure).

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In