Abstract
The goal of this paper is to predict the micro-architectural parameters of cortical bone such as pore diameter (ϕ) and porosity (ν) from ultrasound attenuation measurements using an artificial neural network (ANN). Slices from a 3-D CT scan of human femur are obtained. The micro-architectural parameters of porosity such as average pore size and porosity are calculated using image processing. When ultrasound waves propagate in porous structures, attenuation is observed due to scattering. Two-dimensional finite-difference time-domain simulations are carried out to obtain frequency dependent attenuation in those 2D structures. An artificial neural network (ANN) is then trained with the input feature vector as the frequency dependent attenuation and output as pore diameter (ϕ) and porosity (ν). The ANN is composed of one input layer, 3 hidden layers and one output layer, all of which are fully connected. 340 attenuation data sets were acquired and trained over 2000 epochs with a batch size of 32. Data was split into train, validation and test. It was observed that the ANN predicted the micro-architectural parameters of the cortical bone with high accuracies and low losses with a minimum R2 (goodness of fit) value of 0.95. ANN approaches could potentially help inform the solution of inverse-problems to retrieve bone porosity from ultrasound measurements. Ultimately, those inverse-problems could be used for the non-invasive diagnosis and monitoring of osteoporosis.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Chen, H., Zhou, X., Fujita, H., Onozuka, M., Kubo, K.Y.: Age-related changes in trabecular and cortical bone microstructure. Int. J. Endocrinol. 2013, 9 (2013)
Kanis, J.A., Kanis, J.A.: Assessment of fracture risk and its application to screening for postmenopausal osteoporosis: synopsis of a WHO report. Osteoporos. Int. 4, 368 (1994)
Yerramshetty, J., Akkus, O.: Changes in cortical bone mineral and microstructure with aging and osteoporosis. In: Silva, M. (eds.) Skeletal Aging and Osteoporosis. SMTEB, vol. 5, pp. 105–131. Springer, Heidelberg (2012). https://doi.org/10.1007/8415_2012_114
McCalden, R.W., McGlough, J.A., Barker, M.B., Court-Brown, C.M.: Age-related changes in the tensile properties of cortical bone. The relative importance of changes in porosity, mineralization and microstructure. J. Bone Jt. Surg. Ser. A 75(8), 1193–1205 (1993)
Schaffler, M.B., Burr, D.B.: Stiffness of compact bone: effects of porosity and density. J. Biomech. 21(1), 13–16 (1988)
Sornay-Rendu, E., Munoz, F., Duboeuf, F., Delmas, P.D.: Rate of forearm bone loss is associated with an increased risk of fracture independently of bone mass in postmenopausal women: the OFELY study. J. Bone Miner. Res. 20, 1929 (2005)
Braithwaite, R.S., Col, N.F., Wong, J.B.: Estimating hip fracture morbidity, mortality and costs. J. Am. Geriatr. Soc. 51, 364–370 (2003)
Schuit, S.C.E., et al.: Fracture incidence and association with bone mineral density in elderly men and women: the Rotterdam Study. Bone 34, 195 (2004)
Mazess, R., Chesnut, C.H., McClung, M., Genant, H.: Enhanced precision with dual-energy x-ray absorptiometry. Calcif. Tissue Int. 51, 14 (1992)
Lewiecki, E.M., Lane, N.E.: Common mistakes in the clinical use of bone mineral density testing. Nat. Clin. Pract. Rheumatol. 4, 667 (2008)
Boutroy, S., Bouxsein, M.L., Munoz, F., Delmas, P.D.: In vivo assessment of trabecular bone microarchitecture by high-resolution peripheral quantitative computed tomography. J. Clin. Endocrinol. Metabol. 90(12), 6508–6515 (2005)
Wehrli, F.W., Song, H.K., Saha, P.K., Wright, A.C.: Quantitative MRI for the assessment of bone structure and function. NMR Biomed. Int. J. Devoted Dev. Appl. Magn. Reson. Vivo 19, 731–764 (2006)
Link, T.M.: Osteoporosis imaging: state of the art and advanced. Radiology 263(1), 3–17 (2012)
Haïat, G., Lhémery, A., Renaud, F., Padilla, F., Laugier, P., Naili, S.: Velocity dispersion in trabecular bone: influence of multiple scattering and of absorption. J. Acoust. Soc. Am. 124, 4047 (2017)
Conoir, J.: Multiple scattering in a trabecular bone: influence of the marrow viscosity on the effective properties. J. Acoust. Soc. Am. 113, 2889–2892 (2003)
Litniewski, J., Wojcik, J., Nowicki, A.: Contribution of multiple scattering to the trabecular bone backscatter - dependence on porosity and frequency. In: 2012 IEEE International Ultrasonics Symposium, pp. 1–4 (2012)
Bennamane, A., Boutkedjirt, T.: Theoretical and experimental study of the ultrasonic attenuation in bovine cancellous bone. Appl. Acoust. 115, 50–60 (2017)
Karjalainen, J.P., Töyräs, J., Riekkinen, O., Hakulinen, M., Jurvelin, J.S.: Ultrasound backscatter imaging provides frequency-dependent information on structure, composition and mechanical properties of human trabecular bone. Ultrasound Med. Biol. 35, 1376 (2009)
Mézière, F., Muller, M., Bossy, E., Derode, A.: Measurements of ultrasound velocity and attenuation in numerical anisotropic porous media compared to Biot’s and multiple scattering models. Ultrasonics 54(5), 1146–1154 (2014)
Anderson, C.C., Bauer, A.Q., Holland, M.R., Pakula, M., Laugier, P., Bretthorst, G.L.: Inverse problems in cancellous bone: estimation of the ultrasonic properties of fast and slow waves using Bayesian probability theory. J. Acoust. soc. Am. 128, 2940 (2010)
Padilla, F., Laugier, P.: Recent developments in trabecular bone characterization using ultrasound. Curr. Osteoporos. Rep. 3, 64 (2005)
Wear, K.A., et al.: Relationships of quantitative ultrasound parameters with cancellous bone microstructure in human calcaneus in vitro. J. Acoust. Sos. Am. 131, 1605 (2017)
Mohanty, K., Blackwell, J., Egan, T., Muller, M.: Characterization of the lung parenchyma using ultrasound multiple scattering. Ultrasound Med. Biol. 43(5), 993–1003 (2017)
Demi, L., Van Hoeve, W., Van Sloun, R.J.G., Soldati, G., Demi, M.: Determination of a potential quantitative measure of the state of the lung using lung ultrasound spectroscopy. Sci. Rep. 7(1), 5–11 (2017)
Zhang, X., et al.: Lung ultrasound surface wave elastography, no. 1, pp. 4–6 (2016)
Moilanen, P., et al.: Ultrasonically determined thickness of long cortical bones: two-dimensional simulations of in vitro experiments. J. Acoust. Soc. Am. 122, 1818 (2007)
Nicholson, P.H.F., Moilanen, P., Laugier, P., Timonen, J., Cheng, S., Talmant, M.: Ultrasonically determined thickness of long cortical bones: three-dimensional simulations of in vitro experiments. J. Acoust. Soc. Am. 122, 2439 (2007)
Foiret, J., Minonzio, J.G., Chappard, C., Talmant, M., Laugier, P.: Combined estimation of thickness and velocities using ultrasound guided waves: a pioneering study on in vitro cortical bone samples. IEEE Trans. Ultrason. Ferroelectr. Freq. Control 61(9), 1478–1488 (2014)
Bossy, E., Talmant, M., Laugier, P.: Three-dimensional simulations of ultrasonic axial transmission velocity measurement on cortical bone models. J. Acoust. Soc. Am. 115(5 Pt 1), 2314–2324 (2004)
Mandarano-Filho, L.G., Bezuti, M.T., Mazzer, N., Barbieri, C.H.: Influence of cortical bone thickness on the ultrasound velocity. Acta Ortop. Bras. 20(3), 184–190 (2012)
Rose, E.C., Hagenmüller, M., Jonas, I.E., Rahn, B.A.: Validation of speed of sound for the assessment of cortical bone maturity. Eur. J. Orthod. 27, 190–195 (2005)
Bosisio, M.R., Talmant, M., Skalli, W., Laugier, P., Mitton, D.: Apparent Young’s modulus of human radius using inverse finite-element method. J. Biomech. 40(9), 2022–2028 (2007)
Sievänen, H., Cheng, S., Ollikainen, S., Uusi-Rasi, K.: Ultrasound velocity and cortical bone characteristics in vivo. Osteoporos. Int. 12, 399 (2001)
Eneh, C.T.M., Jurvelin, J.S., Töyräs, J., Malo, M.K.H., Afara, I.O.: Porosity predicted from ultrasound backscatter using multivariate analysis can improve accuracy of cortical bone thickness assessment. J. Acoust. Soc. Am. 141, 575 (2017)
Zheng, R., Le, L.H., Sacchi, M.D., Ta, D., Lou, E.: Spectral ratio method to estimate broadband ultrasound attenuation of cortical bones in vitro using multiple reflections. Phys. Med. Biol. 52, 5855 (2007)
Yousefian, O., Karbalaeisadegh, Y., Banks, H.T., White, R.D., Muller, M.: The effect of pore size and density on ultrasonic attenuation in porous structures with mono-disperse random pore distribution: a two-dimensional in-silico study. J. Acoust. Soc. Am. 144(2), 709–719 (2018)
Yousefian, O., White, R., Banks, H.T., Muller, M.: Ultrasonic attenuation spectroscopy and dispersion characteristics in cortical bone. In: IEEE International Ultrasonics Symposium, IUS (2017)
Geras, K.J., et al.: High-resolution breast cancer screening with multi-view deep convolutional neural networks, pp. 1–9 (2017)
Ribli, D., Horváth, A., Unger, Z., Pollner, P., Csabai, I.: Detecting and classifying lesions in mammograms with deep learning, pp. 1–7 (2018)
Kourou, K., Exarchos, T.P., Exarchos, K.P., Karamouzis, M.V., Fotiadis, D.I.: Machine learning applications in cancer prognosis and prediction. CSBJ 13, 8–17 (2015)
Chen, J.H., Asch, S.M.: Machine learning and prediction in medicine — beyond the peak of inflated expectations. N. Engl. J. Med. 376, 2507 (2017)
Esteva, A., et al.: Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115 (2017)
Zhou, B., Zhang, X.: Lung mass density analysis using deep neural network and lung ultrasound surface wave elastography. Ultrasonics 89, 173–177 (2018)
Steele, A.J., Denaxas, S.C., Shah, A.D., Hemingway, H.: Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease. Plos One 13, 1–20 (2018)
Bossy, E., Grimal, Q.: Numerical methods for ultrasonic bone characterization. In: Laugier, P., Haïat, G. (eds.) Bone Quantitative Ultrasound, pp. 181–228. Springer, Dordrecht (2011). https://doi.org/10.1007/978-94-007-0017-8_8
Acknowledgement
This work was partially supported by National Institutes of Health grant no. R03EB022743. The authors’ also acknowledge Dr Quentin Grimal, Sorbonne University for providing the high resolution CT scans and Dr Maciej A. Mazurowski, Duke Radiology Dept., for consulting with us during the development of the ANN model.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Mohanty, K., Yousefian, O., Karbalaeisadegh, Y., Ulrich, M., Muller, M. (2019). Predicting Structural Properties of Cortical Bone by Combining Ultrasonic Attenuation and an Artificial Neural Network (ANN): 2-D FDTD Study. In: Karray, F., Campilho, A., Yu, A. (eds) Image Analysis and Recognition. ICIAR 2019. Lecture Notes in Computer Science(), vol 11662. Springer, Cham. https://doi.org/10.1007/978-3-030-27202-9_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-27202-9_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-27201-2
Online ISBN: 978-3-030-27202-9
eBook Packages: Computer ScienceComputer Science (R0)