Skip to main content
SpringerLink
Log in

Reconstruction Of SPECT Data Using an Artificial Neural Network

  • Conference paper
Radioactive Isotopes in Clinical Medicine and Research XXIII

Part of the book series: Advances in Pharmacological Sciences ((APS))

  • 103 Accesses

Abstract

At present, algorithms used in nuclear medicine to reconstruct single photon emission computerized tomography (SPECT) data are usually based on one of two principles: filtered back projection and iterative methods. In this paper a different algorithm, applying an artificial neural network (multilayer perceptron) and error backpropagation as training method are used to reconstruct transaxial slices from SPECT data. The algorithm was implemented on an Elscint XPERT workstation (i486,50 MHz) used as routine digital image processing tool in our departments. Reconstruction time for a 64×64 matrix is approximately 10 seconds per transaxial slice. The algorithm has been validated by a mathematical model and tested on heart and Jaszczak phantoms. The very first results show in comparison with filtered back projection an improvement in image quality.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. H. Luig, W. Eschner, M. Bähre, E. Voth, G. Nolte: Eine iterative Strategie zur Bestimmung der Quellverteilung bei der Einzelphotonentomographie mit einer rotierenden Gammakamera. Nucl.-Med 1988;27:140–146

    CAS  Google Scholar 

  2. K. Hornik, M. Stinchcombe, H. White: Multilayer feedforward networks are universal Approximators. Neural networks 2 (1989): 359–366

    Article  Google Scholar 

  3. D. Hamilton, D. O’Mahony, J. Coffey, J. Murphy: Comparison of artificial neural network and discrement analysis for the classification of mild alzheimer’s disease using SPECT data.Eur. J. Nucl. Med 24,8,1997

    Google Scholar 

  4. J. Rudzka, K. Rudzki, S. Nowak: Application of artificial neural network in analysis of renal dynamic studies. Eur. J. Nucl. Med. 24,8,1997

    Google Scholar 

  5. Kaiman, B. L., Kwasny, S. C.: Why tanh? Choosing a sigmoidial function. International conference on neural networks, Baltimore, M.D.

    Google Scholar 

  6. Knoll P., Mirzaei S., Koriska K., Köhn H.: Modifizierter iterativer Rekonstruktionsalgorithmus für SPECT Daten Nukl. Med. 1997;36

    Google Scholar 

  7. Kinnebrock W.: Neuronale Netze: Grundlagen, Anwendungen, Beispiele Oldenburg Verlag, München 1992

    Google Scholar 

  8. Karayiannis N, Venetsanopolus A: Fast learning algorithm for neural networks Artificial neural networks, Elsevier Science Publishers B.V. (north Holland), 1991,1141–1144

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Dept. of Nuclear Medicine, Wilhelminenspital, University of Vienna, Vienna, Austria

    Peter Knoll, Siroos Mirzaei & Horst Köhn

  2. Dept. of Nuclear Medicine, Kaiserin Elisabeth Spital, University of Vienna, Vienna, Austria

    Peter Knoll & Karl Koriska

  3. Dept. of Nuclear Medicine, Institute of Experimental Physics, University of Vienna, Vienna, Austria

    Peter Knoll & Martin Neumann

Authors
  1. Peter Knoll
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Siroos Mirzaei
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Martin Neumann
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Karl Koriska
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Horst Köhn
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Institut für Biomedizinische Technik und Physik, Allgemeines Krankenhaus Wien, Währinger Gürtel 18-20, A-1090, Wien, Austria

    Helmar Bergmann

  2. Institut für Nuklearmedizin, Wilhelminenspital, Montleartstrasse 37, A-1171, Wien, Austria

    Horst Köhn

  3. Universitäts-Klinik für Nuklearmedizin, Allgemeines Krankenhaus Wien, Währinger Gürtel 18-20, A-1090, Wien, Austria

    Helmut Sinzinger

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer Basel AG

About this paper

Cite this paper

Knoll, P., Mirzaei, S., Neumann, M., Koriska, K., Köhn, H. (1999). Reconstruction Of SPECT Data Using an Artificial Neural Network. In: Bergmann, H., Köhn, H., Sinzinger, H. (eds) Radioactive Isotopes in Clinical Medicine and Research XXIII. Advances in Pharmacological Sciences. Birkhäuser, Basel. https://doi.org/10.1007/978-3-0348-8782-3_47

Download citation

  • DOI: https://doi.org/10.1007/978-3-0348-8782-3_47

  • Publisher Name: Birkhäuser, Basel

  • Print ISBN: 978-3-0348-9772-3

  • Online ISBN: 978-3-0348-8782-3

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics

Search

Navigation