Ultrasound Tomography Imaging of Defects Using Neural Networks

Simulations of ultrasound tomography 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 were used as the network inputs, and the target outputs were the expected pixel maps, showing defects (gray 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.

[1]  W.D. O'Brien,et al.  Applications of neural networks to ultrasound tomography , 1989, Proceedings., IEEE Ultrasonics Symposium,.

[2]  B J Thompson.  Optical image processing. , 1968, Revista latinoamericana de microbiologia y parasitologia.

[3]  T. Gonda,et al.  In situ observation of internal structure in growing ice crystals by laser scattering tomography , 1990 .

[4]  Denis M. Anthony.  The use of artificial neural networks in classifying lung scintigrams , 1991 .

[5]  Lester W. Schmerr,et al.  Neural network inversion of uniform-field eddy current data , 1991 .

[6]  A. E. Todd-Pokropek.  The Intercomparison of a Black and White and a Color Display: An Example of the Use of Receiver Operating Characteristic Curves , 1983, IEEE Transactions on Medical Imaging.

[7]  M. Nikoonahad,et al.  Medical ultrasound imaging using neural networks , 1990 .

[8]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[9]  H. Scudder.  Introduction to computer aided tomography , 1978, Proceedings of the IEEE.

[10]  Richard J. Mammone,et al.  Optimal pruning of neural tree networks for improved generalization , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[11]  S. Watanabe,et al.  Ultrasonic robot eyes using neural networks , 1990, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[12]  M. Kaveh,et al.  Reconstructive tomography and applications to ultrasonics , 1979, Proceedings of the IEEE.

[13]  M L Meistrell,et al.  Evaluation of neural network performance by receiver operating characteristic (ROC) analysis: examples from the biotechnology domain. , 1989, Computer methods and programs in biomedicine.

[14]  J. Swets.  ROC analysis applied to the evaluation of medical imaging techniques. , 1979, Investigative radiology.

[15]  David A. Hutchins,et al.  A neural network approach to ultrasonic tomography , 1992, IEEE 1992 Ultrasonics Symposium Proceedings.