Performance Evaluation of PET Image Reconstruction Using Radial Basis Function Networks

  • T. Arunprasath
  • M. Pallikonda Rajasekaran
  • S. Kannan
  • Shaeba Mariam George
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 324)


In this paper, for the reconstruction of the positron emission tomography (PET) images, Artificial Neural Network (ANN) method and Artificial Neural Network-Radial Basis Function (ANN-RBF) method are pursued. ANN is a dominant tool for demonstrating, exclusively when the essential data relationship is unfamiliar. ANN imitates the learning process of the human brain and can process problems involving nonlinear and complex data even if the data are imprecise and noisy. But, ANN calls for high processing time and its architecture needs to be emulated. So, ANN-RBF method is implemented which is a two-layer feed-forward network in which the hidden nodes implement a set of radial basis functions. Thus, the learning process is very fast. By the image quality parameter of peak signal-to-noise ratio (PSNR) value, the ANN method and the ANN-RBF method are compared and it was clinched that better results are obtained from ANN with RBF method.


ANN ANN-RBF PSNR value Positron emission tomography Radial basis function 



We thank Anderson Diagnostics and Lab, Chennai for providing PET images for our research and Department of Instrumentation and Control Engineering of Kalasalingam University (Kalasalingam Academy of Research and Education), Tamil Nadu, India for permitting to use the computational facilities available in biomedical Laboratory which was setup with the support of the Department of Science and Technology (DST), New Delhi under FIST Program.


  1. 1.
    G. Tarantola, F. Zito, P. Gerundini, PET instrumentation and reconstruction algorithms in whole-body applications. J. Nucl. Med. 44, 756–769 (2003)Google Scholar
  2. 2.
    G.T. Herman, Image Reconstruction from Projections: The Fundamentals of Computerized Tomography (Academic Press, New York, 1980)MATHGoogle Scholar
  3. 3.
    V.Y. Panin, F. Kehren, C. Michel, M. Casey, Fully 3-D PET reconstruction with system matrix derived from point source measurements. IEEE Trans. Med. Imag. 25(7), 907–921 (2006)CrossRefGoogle Scholar
  4. 4.
    A.J. Rockmore, A. Macovski, A maximum likelihood approach to emission image reconstruction from projection. IEEE Trans. Nucl. Sci. 23(4), 1428–1432 (1976)CrossRefGoogle Scholar
  5. 5.
    S. Vandenberghe, S. Staelens, C.L. Byrne, E.J. Soares, I. Lemahieu, S.J. Glick, Reconstruction of 2D PET data with Monte Carlo generated system matrix for generalized natural pixels. Phys. Med. Biol. 51(12), 3105–3125 (2006)CrossRefGoogle Scholar
  6. 6.
    M. Rafecas, B. Mosler, M. Dietz, M. Pögl, A. Stamatakis, D.P. McElroy, S.I. Ziegler, Use of a Monte Carlo based probability matrix for 3D iterative reconstruction of MADPETII data. IEEE Trans. Nucl. Sci. 51(5), 2597–2605 (2004)CrossRefGoogle Scholar
  7. 7.
    R.D.L. Prieta, An accurate and parallelizable geometric projector/backprojector for 3D PET image reconstruction. Lect. Notes Comput. Sci. 3337, 27–38 (2004)CrossRefGoogle Scholar
  8. 8.
    P. Chawla, R. Mittal, K. Grewal, Hybrid filtering technique for image denoising using artificial neural network. Int. J. Eng. Adv. Techno. (IJEAT) 1(3), 36–40 (2012)Google Scholar
  9. 9.
    D.B. Mantri, S.N. Kulkarni, S.S. Katre, Image compression using ebp with neural network. J. Inf. Knowl. Res. Electron. Commun. Eng. 1 (2011)Google Scholar
  10. 10.
    Z. Shi1, L. He, Application of neural networks in medical image processing, in Proceedings of the Second International Symposium on Networking and Network Security (ISNNS’10) (2010), pp. 2–4Google Scholar
  11. 11.
    J. Jiang, P. Trundle, J. Ren, Medical image analysis with artificial neural networks. Comput. Med. Imaging Graph. 34, 617–631 (2010) (Elsevier)Google Scholar
  12. 12.
    D.C. Durairaj, M.C. Krishna, R. Murugesan, A neural network approach for image reconstruction in electron magnetic resonance tomography. Comput. Methods Programs Biomed. 37, 1492–1501(2007) (Elsevier)Google Scholar
  13. 13.
    K.H. Su, L.C. Wu, J.S. Lee, R.S. Liu, J.C. Chen, A novel method to improve image quality for 2-D small animal PET reconstruction by correcting a Monte Carlo-simulated system matrix using an artificial neural network. IEEE Trans. Nucl. Sci. 56(3), 704–714 (2009)Google Scholar
  14. 14.
    M.T. Munley, C.E. Floyd, J.E. Bowsher, R.E. Coleman, A spatially-variant SPECT reconstruction scheme using artificial neural networks, in Proceedings of Conference on Record of IEEE Nuclear Science Symposium and Medical Imaging Conference, vol. 2 (1992), pp. 1279–1281Google Scholar
  15. 15.
    M. Niranjan, F. Fallside, Neural network and radial basis function in classifying static speech patterns. Comput. Speech Lang. 4, 275–289 (1990)CrossRefGoogle Scholar
  16. 16.
    W. Hong, W. Chen, R. Zhang, The application of neural network in the technology of image processing, in Proceedings of International Multi Conference of Engineers and Computer Scientists, vol. 1 (2009), pp. 18–20Google Scholar
  17. 17.
    E. Floyd, An artificial neural network for SPECT image reconstruction. IEEE Trans. Med. Imag. 10(3), 485–487 (1991)CrossRefGoogle Scholar
  18. 18.
    T. ArunPrasath, M.P. Rajasekaran, S. Kannan, V.A. Kalasalingam, Reconstruction of PET brain image using conjugate gradient algorithm, in Second World Congress on Information and Communication Technologies (WICT 2012), Trivandrum, India (2012)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  • T. Arunprasath
    • 1
  • M. Pallikonda Rajasekaran
    • 1
  • S. Kannan
    • 1
  • Shaeba Mariam George
    • 1
  1. 1.Kalasalingam UniversityVirudhunagarIndia

Personalised recommendations