Optimization of Projections for Parallel-Ray Transmission Tomography Using Genetic Algorithm
In this work, a Hybrid Continuous Genetic Algorithm (HCGA) based methodology has been used for the optimization of number of projections for parallel-beam transmission tomography. Image quality has been measured using root-mean-squared error, Euclidean error and peak signal-to-noise ratio. The sensitivity of the reconstructed image quality has been analyzed with the number of projections used for the estimation of the inverse Radon transform. The number of projections has resulted in the maximization of image quality while minimizing the radiation hazard involved. The results have been compared with the intensity levels of the original phantom and the image reconstructed by the Filtered Back-Projection (FBP) technique, by using Matlab ® functions radon and iradon. For the 8 × 8 Head and Lung phantoms, HCGA and FBP have resulted in PSNR values of 40.47 & 8.28 dB and 26.38 & 12.98 dB respectively with the optimum number of projections.
KeywordsGenetic Algorithm Inverse Radon Transform Filtered Back-Projection Transmission Tomography
Unable to display preview. Download preview PDF.
- 1.Kak, A.C., Slaney, M.: Principles of Computerized Tomographic Imaging. IEEE Press, New York (1988)Google Scholar
- 4.Press, W.H., Teukolsky, S.A., Vetterling, W.T., Flannery, B.P.: Numerical recipes in C: The art of scientific computing. Cambridge University Press, New York (2002)Google Scholar
- 8.Qureshi, S.A., Mirza, S.M., Arif, M.: Hybrid Simulated Annealing Image Reconstruction for Parallel-Ray Transmission Tomography. Inverse Problems in Science and Engineering (in press, 2008)Google Scholar
- 10.Holland, J.H.: Adaptation in natural and artificial systems. University of Michigan Press, Ann Arbor (1975)Google Scholar
- 12.Cheng, K.-S., Chen, B.-H., Tong, H.-S.: Electrical Impedance image reconstruction using the genetic algorithm. In: 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Amsterdam, pp. 768–769 (1996)Google Scholar
- 14.Christopher, R.H., Jeffery, A.J., Michael, G.K.: A genetic algorithm for function optimization: A Matlab implementation. Technical Report, Raleigh: NSCU, pp. 1–14 (1995)Google Scholar
- 17.Qureshi, S.A., Mirza, S.M., Arif, M.: Quality of inverse Radon transform-based image reconstruction using various frequency domain filters in parallel beam transmission tomography. Science International 18(3), 181–186 (2006)Google Scholar
- 18.Shepp, L.A., Logan, B.F.: The Fourier reconstruction of a head section. IEEE Trans. Nucl. Sci. NS-21, 21–43 (1974)Google Scholar
- 19.White, D.R., Wambersie, A.: Tissue Substitutes in Radiation Dosimetry and Measurement. Technical Report, International Commission on Radiation Units and Measurements, pp. 1–132 (1999)Google Scholar
- 20.Qureshi, S.A., Mirza, S.M., Arif, M.: A Template Based Continuous Genetic Algorithm for Image Reconstruction. In: Proc. of the 11th IEEE INMIC 2007, ISBN: 1-4244-1552-7 (Conference Print Version), IEEE Catalog Number: 07EX2000, Library of Congress: 2007905117, Lahore, pp. 8–13 (2007)Google Scholar
- 25.Qureshi, S.A., Mirza, S.M., Arif, M.: Effect of number of projections on inverse Radon transform-based image reconstruction by using filtered back-projection for parallel beam transmission tomography. Science International 19(1), 5–10 (2007)Google Scholar