Bayesian Reconstruction for Transmission Tomography with Scale Hyperparameter Estimation

  • Antonio López
  • Rafael Molina
  • Aggelos K. Katsaggelos
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3523)


In this work we propose a new method to estimate the scale hyperparameter for transmission tomography in Nuclear Medicine image reconstruction problems. Within the Bayesian paradigm, Evidence Analysis and circulant preconditioners are used to obtain the scale hyperparameter. For the prior distribution, we use Generalized Gaussian Markov Random Fields (GGMRF), a nonquadratic function that preserves the edges in the reconstructed image. The experimental results indicate that the proposed method produces satisfactory reconstructions.


Partition Function Evidence Analysis Bayesian Paradigm Attenuation Correction Factor Transmission Tomography 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Belge, M., Kilmer, M.E., Miller, E.L.: Wavelet Domain Image Restoration with Adaptative Edge-Preserving Regularization. IEEE Tr. Im. Proc. 9, 597–608 (2000)zbMATHCrossRefGoogle Scholar
  2. 2.
    Bouman, C.A., Sauer, K.: A Generalized Gaussian Image Model for Edge- Preserving Map Estimation. IEEE Tr. Im. Proc. 2, 296–310 (1993)CrossRefGoogle Scholar
  3. 3.
    Cho, Z.H., Jones, J.P., Singh, M.: Foundation of medical imaging. John Wiley and Sons, Chichester (1993)Google Scholar
  4. 4.
    Erdogan, H., Fessler, J.A.: Monotonic Algorithms for Transmission Tomography. IEEE Tr. Me. Im. 18, 801–814 (1999)CrossRefGoogle Scholar
  5. 5.
    Fessler, J.A.: ASPIRE (A Sparse Precomputed Iterative Reconstruction Library),
  6. 6.
    Fessler, J.A., Booth, S.D.: Conjugate-Gradient Preconditioning Methods for Shift Variant PET Image Reconstruction. IEEE Tr. Im. Proc. 8, 688–699 (1999)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Hsiao, I., Rangarajan, A., Gindi, G.: Joint MAP Bayesian Tomographic Reconstruction with a Gamma-mixture Prior. IEEE Tr. Im. Proc. 11, 1466–1477 (2002)CrossRefGoogle Scholar
  8. 8.
    López, A., Molina, R., Katsaggelos, A.K.: Scale Hyperparameter Estimation for GGMRF Prior Models with Application to SPECT Images. In: Proc. of IEEE Int. Conf. on Digital Signal Processing, vol. 2, pp. 521–524 (2002)Google Scholar
  9. 9.
    López, A., Molina, R., Katsaggelos, A.K., Rodriguez, A., López, J.M., Llamas, J.M.: Parameter Estimation in Bayesian Reconstruction of SPECT Images: An Aid in Nuclear Medicine Diagnosis. Int. J. Imaging Syst. Technol. 14, 21–27 (2004)CrossRefGoogle Scholar
  10. 10.
    Mumcuoglu, E.U., Leahy, R., Cherry, S.R., Zhou, Z.: Fast Gradient-based Methods for Bayesian Reconstruction of Transmission and Emission PET Images. IEEE Tr. Me. Im. 13, 687–701 (1993)CrossRefGoogle Scholar
  11. 11.
    Saquib, S.S.: Edge-preserving Models and Efficient Algorithms for ill-osed Inverse Problems in Image Processing. Ph.D. thesis, University of Purdue (1997) Google Scholar
  12. 12.
    Yu, D.F., Fessler, J.A.: Edge-preserving Tomographic Reconstruction with Nonlocal Regularization. IEEE Tr. Me. Im. 21, 159–173 (2002)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Antonio López
    • 1
  • Rafael Molina
    • 2
  • Aggelos K. Katsaggelos
    • 3
  1. 1.Universidad de Granada, Departamento de Lenguajes y Sistemas InformáticosGranadaSpain
  2. 2.Departamento de Ciencias de la Computación e I.AUniversidad de GranadaGranadaSpain
  3. 3.Department of Electrical and Computer EngineeringNorthwestern UniversityEvaston

Personalised recommendations