Advertisement

A fuzzy model for the processing and recognition of MR pathological images

  • Dellepiane S 
  • Venturi G 
  • Vernazza G 
8. Rule Based Systems And Learning
Part of the Lecture Notes in Computer Science book series (LNCS, volume 511)

Abstract

The methodologies for the generation of model describing two echoes of MR pathological images of the head are presented. A vocabulary set has been chosen and formalized consisting of attributes and relations for the characterization of the organs and tissues contained in the image. The analitic study of a training set of images, associated with expert aid for medical aspects has permitted the creation of the model whose robustness has been proved on a set of test images. The most important and innovative characteristics of the model are the hierarchical subdivision between organ-father and sub-organs, together with the distinction between anatomical and acquisition-dependent properties of the image.

The results obtained by utilizing the model inside the system IBIS, devoted to image recognition, are presented. The same model has been used for various patients, thus proving its ability to face individual variabilities. For each patient the cerebrum, the pars ossea, the cutis, and the pathological area (where present) have been recognized with sufficient accuracy, while the ventricle has often been identified with lower precision.

Keywords

Knowledge-based systems propositional models segmentation model matching visual data symbolic data numerical data 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Dellepiane S, Regazzoni C, Serpico SB and Vernazza G (1988). Extension of IBIS for 3D organ recognition in NMR multislices. Pattern Recognition Letters Vo8:65–72.Google Scholar
  2. Dellepiane S, Regazzoni C, Serpico SB, Vernazza G (1989). An application-independent knowledge-based framework for complex image recognition. IAPR Positano 5th Int. Conf. Image Analysis and Processing Proc., World Scientific Pub., pp.309–316.Google Scholar
  3. Dellepiane S, Leonardi M, Venturi G and Vernazza G (1990). Automatic recognition for 3D organ visualization from CT spatial sequences. Riv. di Neuroradiologia Vo3:81–93.Google Scholar
  4. COVIRA-Computer Vision in Radiology, Project A1011 of the AIM programme (Advanced Informatics in Medicine) of the European Community. Consortium partners: Philips Medical Systems (Prime Contractor), IBM UK Scientific Center, DIBE University of Genova (Italy), University of Hamburg (FRG), G. Maranon General Hospital Madrid (Spain) (1990).Google Scholar
  5. Hanson AM and Riseman ER (1988). Vision, Brain and Cooperative Computation. Academic Press, New York.Google Scholar
  6. Menhardt W and Schmidt KH (1988). Computer Vision on Magnetic Resonance. Pattern Recognition Letters Vo8:73–85.Google Scholar
  7. Ronco M, Vio R, Dellepiane S and Vernazza G (1990). Hierarchical image segmentation: a K-B system using fuzzy functions. Signal Processing V (Theories and Applications) Proc. of EUSIPCO-90, Elsevier Science Pub., 1735–1738.Google Scholar
  8. Vernazza G, Serpico SB and Dellepiane SG (1987). A knowledge-based system for biomedical image processing and recognition. IEEE Trans. on Circuits & Systems, CAS-34:1399–1416.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1991

Authors and Affiliations

  • Dellepiane S 
    • 1
  • Venturi G 
    • 1
  • Vernazza G 
    • 1
  1. 1.Department of Biophysical and Electronic EngineeringUniversity of GenoaGenovaItaly

Personalised recommendations