Model Based Analysis of Scintigraphic Image Sequences of the Human Heart

  • H. Bunke
  • G. Sagerer
  • H. Niemann
Conference paper
Part of the NATO ASI Series book series (volume 2)


A system for the automatic analysis of scintigraphic image sequences of the human heart is described in this paper. The aim of the system is the automatic detection of motion abnormalities. The system has a modular structure consisting of four components, namely ‘Methods’, ‘Model’, ‘Instances’, and ‘Control’. The Module ‘Methods’ comprises several routines for image preprocessing and segmentation. The knowledge needed for analyzing an image sequence is contained in the module ‘Model’. The model is represented by means of a semantic network. Instances of model concepts are kept separately from the model. Each instance has the same structure as its corresponding concept. The ‘Control’ module has two principal concerns. First, it provides some means for communication between user and system. Secondly, it controls the analysis of an image sequence based on the model creating instances of model concepts.


Image Sequence Human Heart Semantic Network Computer Vision System Semantic Component 
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]
    J.K. Tsotsos, H.D. Convey, S. Zucker: A Framework For Visual Motion Understanding, in IEEE Trans. PAMI, Vol.2, 1980, 563–573Google Scholar
  2. [2]
    Protocol of the 2nd session of the working group ‘Cardiovascular Medicine’ of the German Association for Nuclear Medicine, Frankfurt/Main, 1981Google Scholar
  3. [3]
    H. Geffers, W.E. Adam, F. Bitter, H. Sigel, H. Kampmann: Data Processing and Functional Imaging in Radionuclide Ventriculographies in Information Processing in Medical Imaging. Proc. 5th Int. Conf., Nashville, 1978, 322–331Google Scholar
  4. [4]
    H. Niemann: Pattern Analysis, Springer-Verlag 1981MATHGoogle Scholar
  5. [5]
    N.V. Findler (ed.): Associative Networks. New York, 1979MATHGoogle Scholar
  6. [6]
    A.R. Hanson, M.E. Riseman: A Computer System for Interpreting Scenes, in Hanson, Riseman (ed.): Computer Vision Systems, New York, 1978, 303–333Google Scholar
  7. [7]
    J.M. Lester, J.F. Brenner, W.D. Sellers: Local Transforms for Biomedical Image Analysis, Computer Graphics and Image Processing 13, 1980, 17–30CrossRefGoogle Scholar
  8. [8]
    G.J. Yang, T.S. Huang: Median Filters and Their Applications to Image Processing. Technical Report TR-EE 80-1. Purdue University, 1980Google Scholar
  9. [9]
    C.K.Chow, T. Kaneko: Automatic Boundary Detection of the Left Ventricle from Cineangiograms. Computers and Biomedical Research 5, 1972, 388–410CrossRefGoogle Scholar
  10. [10]
    A. Rosenfeld, J.L. Pfaltz: Distance Functions on Digital Pictures, Vol.1, 1968, 38–61MathSciNetGoogle Scholar
  11. [11]
    H. Levesque, J. Mylopoulos: A Procedural Semantics for Semantic Networks, in /5/Google Scholar
  12. [12]
    B.W. Kernighan, P.J. Plaugher: Software Tools, Reading, Massachussets, 1976MATHGoogle Scholar
  13. [13]
    D.H. Ballard, CM. Brown, J.A. Feldman: An Approach to Knowledge-Directed Image Analysis, in /6/, 271–281Google Scholar
  14. [14]
    J.N. Nilsson: Principles of Artificial Intelligence, Palo Alto, California, 1980MATHGoogle Scholar
  15. [15]
    L.A. Zadeh, K.S. Fu, K. Tanaka, M. Shimura (ed.): Fuzzy Sets and Their Application to Cognitive and Decision Processes. Academic Press, 1975Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1983

Authors and Affiliations

  • H. Bunke
    • 1
  • G. Sagerer
    • 1
  • H. Niemann
    • 1
  1. 1.Lehrstuhl für Informatik 5 (Mustererkennung)Universität Erlangen-NürnbergErlangenF. R. Germany

Personalised recommendations