New neural network algorithm for image reconstruction from fan-beam projections

Neural networks have some applications in computerized tomography, in particular to reconstruct an image from projections. The presented paper describes a new practical approach to the reconstruction problem using a Hopfield-type neural network. The methodology of this reconstruction algorithm resembles a transformation formula-the so-called @r-filtered layergram method. The method proposed in this work is adapted for discrete fan beam projections, already used in practice. Performed computer simulations show that the neural network reconstruction algorithm designed to work in this way outperforms conventional methods in obtained image quality, and in perspective of hardware implementation in the speed of the reconstruction process.

[1]  G. N. Ramachandran,et al.  Three-dimensional reconstruction from radiographs and electron micrographs: application of convolutions instead of Fourier transforms. , 1971, Proceedings of the National Academy of Sciences of the United States of America.

[2]  G. Herman,et al.  Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography. , 1970, Journal of theoretical biology.

[3]  Sze Fong Yau,et al.  Limited-angle tomography using artificial neural network , 1996, Electronic Imaging.

[4]  K F King,et al.  Computed tomography scanning with simultaneous patient translation. , 1990, Medical physics.

[5]  J P Kerr,et al.  A statistically tailored neural network approach to tomographic image reconstruction. , 1995, Medical physics.

[6]  Friedrich M. Wahl,et al.  Vector-entropy optimization-based neural-network approach to image reconstruction from projections , 1997, IEEE Trans. Neural Networks.

[7]  Y. Censor.  Finite series-expansion reconstruction methods , 1983, Proceedings of the IEEE.

[8]  R. Lewitt.  Reconstruction algorithms: Transform methods , 1983, Proceedings of the IEEE.

[9]  Andrzej Cichocki,et al.  Neural networks for linear inverse problems with incomplete data especially in applications to signal and image reconstruction , 1995, Neurocomputing.

[10]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[11]  Sim Heng Ong,et al.  Image reconstruction by a Hopfield neural network , 1993, Image Vis. Comput..

[12]  Fa-Long Luo,et al.  Applied neural networks for signal processing , 1997 .

[13]  D. Ingman,et al.  Maximum entropy signal reconstruction with neural networks , 1992, IEEE Trans. Neural Networks.

[14]  J E Bowsher,et al.  An artificial neural network approach to quantitative single photon emission computed tomographic reconstruction with collimator, attenuation, and scatter compensation. , 1994, Medical physics.

[15]  K. Taguchi,et al.  Algorithm for image reconstruction in multi-slice helical CT. , 1998, Medical physics.

[16]  P Knoll,et al.  An artificial neural net and error backpropagation to reconstruct single photon emission computerized tomography data. , 1999, Medical physics.

[17]  A Kannan.  An exposure timer for use with telecobalt units. , 1978, Medical physics.