A neural network method of image reconstruction from projections using grid-"friendly" projection angles

• Autorzy: Cierniak R.
• Języki publikacji: EN

Abstrakty

EN

In this paper an original approach to the reconstruction problem using a recurrent neural network is presented. In our method parallel beam projections is used. To decrease the number of desired projections the grid "friendly" angles of the parallel projections are selected according to the discrete Radon transform (DRT). Performed computer simulations show that the presented neural network reconstruction algorithm outperforms the convolution/back-projection method in the reconstructed image quality.

Słowa kluczowe

EN

image reconstruction from projections; neural networks; discrete Radon transform

• Wydawca: Instytut Telekomunikacji i Informatyki Uniwersytetu Technologiczno-Przyrodniczego w Bydgoszczy
• Czasopismo: Image Processing & Communications
• Rocznik: 2009
• Tom: Vol. 14, no 2-3
• Strony: 51--58
• Opis fizyczny: Bibliogr. 10 poz., rys.

Twórcy

autor

Cierniak R.

• Institute of Computer Engineering, Czestochowa University of Technology, Czestochowa, Armii Krajowej 36,

Bibliografia

• [1] R. Grimmer, M. Oelhafen, U. Elström, M. Kachelrie, Cone-beam CT image reconstruction with extended z range, Medical Physics 36:3363-3370, 2009
• [2] A. Cichocki, R. Unbehauen, M. Lendl, K. Weinzierl, Neural networks for linear inverse problems with incomplete data especially in application to signal and image reconstruction, Neurocomputing, 8:7-41, 1995
• [3] R. Cierniak, A new approach to to-mographic image reconstruction using a Hopfield-type neural network, International Journal Artificial Intelligence in Medicine, 43: 113-125, 2008
• [4] R. Cierniak, New neural network algorithm for image reconstruction from fan-beam projections, Neurocomputing, 43:113-125, 2009
• [5] J. J. Hopfield, D. W. Tank, Neural computation of decision in optimization problems, Biological Cybernetics, 72:3238-3244
• [6] A. C. Kak, M. Slanley, Principles of Computerized Tomographic Imaging, IEEE Press, New York, 1988
• [7] J. P. Kerr, E. B. Barlett, Medical image processing utilizing neural networks trained on a massively parallel computer, Computers in Biology and Medicine, 25:393-403, 1995
• [8] A. Kingston, I. Svalbe, Mapping between digital and continuous projections via the discrete Radon transform in Fourier space, Proc. VIIth Digital Image Computing: Techniques and Applications, Sydney, 263-272, 2003
• [9] Y. Wang, F. M. Wahl, Vector-entropy optimization-based neural-network approach to image reconstruction from projections, IEEE Transaction on Neural Networks, 8:1008-1014, 1997
• [10] R. Cierniak, A Neural Network Method of Image Reconstruction from Fan-Beam Projections Using Grid-“Friendly” Selection of the Projection Angles, In Book: Image Processing & Communications Challenges, Ed. Ryszard S. Choraś and Antoni Zabłudowski, Academy Publishing House EXIT, Warsaw 2009, pp. 334-341