A three-dimentional neural network based approach to the image reconstruction from projections problem

作者: Robert Cierniak

DOI: 10.1007/978-3-642-13208-7_63

关键词:

摘要: This paper presents a novel neural network approach to the problem of image reconstruction from projections obtained by spiral tomography scanner. The process is performed during minimizing energy function in recurrent network. Our method great practical use discrete cone-beam projections. Experimental results show that appropriately designed able reconstruct an with better quality than used commercial conventional algorithms.

参考文章(20)
Robert Cierniak, A New Approach to Image Reconstruction from Projections Using a Recurrent Neural Network International Journal of Applied Mathematics and Computer Science. ,vol. 18, pp. 147- 157 ,(2008) , 10.2478/V10006-008-0014-Y
Fa Long Luo, Rolf Unbehauen, Applied neural networks for signal processing ,(1997)
Robert Cierniak, A Novel Approach to Image Reconstruction Problem from Fan-Beam Projections Using Recurrent Neural Network Artificial Intelligence and Soft Computing – ICAISC 2008. pp. 752- 761 ,(2006) , 10.1007/978-3-540-69731-2_72
John P. Kerr, Eric B. Bartlett, A statistically tailored neural network approach to tomographic image reconstruction Medical Physics. ,vol. 22, pp. 601- 610 ,(1995) , 10.1118/1.597586
V Srinivasan, YK Han, SH Ong, Image reconstruction by a Hopfield neural network Image and Vision Computing. ,vol. 11, pp. 278- 282 ,(1993) , 10.1016/0262-8856(93)90005-2
R.M. Lewitt, Reconstruction algorithms: Transform methods Proceedings of the IEEE. ,vol. 71, pp. 390- 408 ,(1983) , 10.1109/PROC.1983.12597
Robert Cierniak, A 2D approach to tomographic image reconstruction using a Hopfield-type neural network Artificial Intelligence in Medicine. ,vol. 43, pp. 113- 125 ,(2008) , 10.1016/J.ARTMED.2008.03.003
Marc Kachelrieß, Stefan Schaller, Willi A. Kalender, Advanced single-slice rebinning in cone-beam spiral CT Medical Physics. ,vol. 27, pp. 754- 772 ,(2000) , 10.1118/1.598938