Abstract
Simulations of ultrasound tomography have demonstrated that artificial neural networks can solve the inverse problem in ultrasound tomography. A highly simplified model of ultrasound propagation was constructed, taking no account of refraction or diffraction, and using only longitudinal wave time of flight (TOF). TOF data was used as the network inputs, and the target outputs were the expected pixel maps, showing defects (grey scale coded) according to the velocity of the wave in the defect.
The effects of varying resolution and defect velocity were explored. It was found that defects could be imaged using time of flight of ultrasonic rays. Further simulations also investigated a configuration that could be implemented experimentally. It was found that in this case the resolution had to be limited to achieve successful reconstructions.
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
Preview
Unable to display preview. Download preview PDF.
References
Stone D.E.W. and Clarke B. Non-destructive evaluation of composites–an overview. In Matthews F.L., Buskell N.C.R., Hodgkinson J.M., and Morton J., editors, 6th International Conference on Composite Materials and 2nd European Conference on Composite Materials, volume 1, pages 2–59, 1987.
Middleton D.H. ed. Composites Materials in Aircraft Structures. Longman Scientific Technical, 1990.
Mueller R.K, Kaveh M, and Wade G. Reconstructive tomography and applications to ultrasonics. IEEE Proceedings, 67: 4: 567–587, 1979.
Greenleaf J.F. and Bahn R.C. Clinical imaging with transmissive ultrasonic computerized tomography. IEEE Trans. Biomed. Eng, 28: 177, 1981.
Eberhard J.W. Ultrasonic tomography for nondestructive evaluation. Ann. Rev. Mater Sci, 12, 1, 1982.
Kak A.C. and Slaney M. Principles of computerized tomographic imaging. IEEE Press, 1988.
Censor Y. Finite series expansion reconstruction techniques. Proc. IEEE, 71: 409419, 1984.
Lippmann R.P. An introduction to computing with neural nets. IEEE ASSP Magazine, 4: 2: 4–22, 1987.
Rumelhart D.E and Hinton G.E and Williams N. Learning internal representations by error propagation (in parallel distributed processing ed rumelhart and mclelland), 1986.
Hecht-Nielson R. Neurocomputing: Picking the human brain. IEEE’ Spectrum, MARCH: 36–41, 1988.
Watanabe S and Yoneyama M. Ultrasonic robot eyes using neural networks. IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control, 37 (3 May): 141–147, 1990.
Conrath B.C, Daft C.M.W, and O’Brien W.D. Applications of neural networks to ultrasound tomography. Ultrasonics Symposium, pages 1007–1010, 1989.
Nikoonahad M and Liu D.C. Medical ultrasound imaging using neural networks. Electronic Letters, 26 (8 Apr 14): 545–546, 1990.
Mann J.M, Schmerr L.W, and Moulder J.C. Neural network inversion of uniform-field eddy current data. Materials Evaluation, Jan: 34–39, 1991.
Gonda T., Kakiuchi H, and Moriya K. In situ observation of internal structures in growing ice crystals by laser scattering tomography. Journal öf Crystal Growth, 102(1–2 Mar-Apr):179–184, 1989.
Obellianne C, Fogelman Soulie F, and Galibourg G. Connectionist models for image processing. In Simon J.C, editor, From pixels to features, COST15 workshop, pages 185–196. Elsevier, 1989.
Platzer H. Optical image processing. In Proc. 2nd Scandinavian conf. on image analysis, pages 128–139, 1981.
Rumelhart D.E and Hinton G.E and Williams N. Learning representations by back-propagating errors. Nature, 323 NO 9: 533–536, 1986.
Chiu W.C. Anthony D.M. Hines E.L. Forno C. Hunt R. And Oldfield S. Selection of the optimal mlp net for photogrammetric target processing. In lasted Conf. Artificial Intelligence App. & Neural Networks. pages 180–183, 1990.
Vogl T.P., Mangis J.K., Rigler A.K., and Zink W.T. and Alkon D.L. Accelerating the convergence of the back-propagation method. Biological Cybernetics, 59: 257–263, 1988.
Todd-Pokropek A.E. The comparison of a black and white and a color display: An example of the use of receiver operating characteristic curves. IEEE Transactions, MI-2: 19–23, 1983.
Swets J.A. Roc analysis applied to the evaluation of medical imaging techniques. Investigative Radiology, 14 PT 2: 109–121, 1979.
Meistrell M.L. Evaluation of neural network performance by receiver operating characteristic (ROC) analysis: examples from the biotechnology domain, pages 73–80. Elsevier, 1990.
Anthony D.M. The Use of Artificial Neural Networks in Classifying Lung Scintigrams. PhD thesis, University of Warwick, 1991.
Sas users’s guide, statistics.
Sankar A and Mammone R.J. Optimal pruning of neural tree networks for improved generalization. In Proc. 5th International Joint Conference on Neural Networks, Seattle, 1991. IEEE.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag London Limited
About this paper
Cite this paper
Anthony, D.M., Hines, E.L., Hutchins, D.A., Mottram, J.T. (1992). Simulated Ultrasound Tomographic Imaging of Defects. In: Taylor, J.G. (eds) Neural Network Applications. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-2003-2_5
Download citation
DOI: https://doi.org/10.1007/978-1-4471-2003-2_5
Publisher Name: Springer, London
Print ISBN: 978-3-540-19772-0
Online ISBN: 978-1-4471-2003-2
eBook Packages: Springer Book Archive