Advertisement

Improved functional imaging through network based parallel processing

  • F. Munz
  • T. Stephan
  • U. Maier
  • T. Ludwig
  • A. Bode
  • S. Ziegler
  • S. Nekolla
  • P. Bartenstein
  • M. Schwaiger
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1362)

Abstract

This paper deals with currently used algorithms for the reconstruction of functional images which run up to 60 hours or more on a single workstation and deal with hundreds of megabyte of data. A parallel implementation with high efficiency and almost linear speedup of a sophisticated iterative algorithm is given and its applicability to other reconstruction methods is shown. Whereas running this application on a high performance parallel computer is straightforward, there are more issues under production conditions as they are enforced by daily routine in a clinic. We adress the topic of fault tolerant parallelizing and batch queuing of programs which are typically written in a high level language like IDL or MATLAB and show how load balancing can preserve the ownership of workstations in a network of workstations (NOW) which is used for distributed computing during office hours.

Keywords

functional imaging parallel image reconstruction load balancing batch queing network of workstations 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Fessler, J. A. ASPIRE 3.0 users guide. Tech. rep., University of Michigan, 1995.Google Scholar
  2. 2.
    Fessler, J. A. Positron Emission Tomography. IEEE Signal Processing Magazine, 1 (January 1997), 43–55.Google Scholar
  3. 3.
    Leffler, S., McKusick, K., Karels, M., and Quarterman, J. The Design and Implementation of the 4.3 BSD UNIX Operating System. Addison-Wesley, Mai 1989.Google Scholar
  4. 4.
    Maier, U., and Stellner, G. Distributed Resource Management for Parallel Applications in Networks of Workstations. In HPCN Europe 1997 (1997), vol. 1225 of Lecture Notes in Computer Science, Springer-Verlag, pp. 462–471.Google Scholar
  5. 5.
    Maier, U., Stellner, G., and Zoraja, I. Batch Queuing and Resource Management for PVM Applications in a Network of Workstations. In ARGS'97: Architektur von Rechensystemen 1997 (1997), UniversitÄt Rostock, pp. 179–188.Google Scholar
  6. 6.
    Munz, F. Parallele Rekonstruktion von PET Volumendaten. Diplomarbeit, Institut für Informatik, Technische UniversitÄt München, September 1995.Google Scholar
  7. 7.
    Shepp, L., and Vardi, Y. Maximum Likelihood Reconstruction for Emission Tomography. IEEE Transaction on Medical Imaging (1982).Google Scholar
  8. 8.
    Stellner, G. Methoden zur Sicherungspunkterzeugung in parallelen und verteilten Systemen. Dissertation, Institut für Informatik, Technische UniversitÄt München, Juni 1996.Google Scholar
  9. 9.
    Stellner, G., and Pruyne, J. Resource Management and Checkpointing for P.VM. In Proceedings of the 2nd European PVM Users' Group Meeting (Lyon, Sept. 1995), Editions Hermes, pp. 131–136.Google Scholar
  10. 10.
    Stephan, T. Erweiterung eines parallelen Rekonstruktionsprogramms von PET Volumendaten um Komponenten zur Stapelverarbeitung und Lastverwaltung. Diplomarbeit, Institut für Informatik, Technische UniversitÄt München, Mai 1997.Google Scholar
  11. 11.
    Sunderam, V. S., Geist, G. A., Dongarra, J., and Mancher, R. The PVM Concurrent Computing System: Evolution, Experiences, and Trends. Parallel Computing, Vol. 20 (4) (1993).Google Scholar
  12. 12.
    Townsend, D. W., and Defrise, M. Image Reconstruction Methods in Positron Tomography. Tech. rep., CERN European Organization for Nuclear Research, 1993.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1998

Authors and Affiliations

  • F. Munz
    • 1
  • T. Stephan
    • 2
  • U. Maier
    • 2
  • T. Ludwig
    • 2
  • A. Bode
    • 2
  • S. Ziegler
    • 1
  • S. Nekolla
    • 1
  • P. Bartenstein
    • 1
  • M. Schwaiger
    • 1
  1. 1.Nuklearmedizinische Klinik und Poliklinik des Klinikums rechts der IsarDeutschland
  2. 2.Lehrstuhl für Rechnertechnik und RechnerorganisationTechnische UniversitÄt München (TUM)Deutschland

Personalised recommendations