Tissue Differentiation in MRI by Means of Pattern Recognition

  • R. Bachus
  • H. König
  • G. Lenz
  • M. Deimling
  • E. R. Reinhardt

Abstract

The major aims in tissue characterization are the differentiation between normal, benign and malignant (primary, metastatic) tissues, the determination of prognostic information (e.g. tumor growth rate) and the detection of early stages or precursors of tumors. At the present time, mainly the anatomical information of standard SE images as well as the MR parameters T1, T2, and spin density are used for the clinical diagnosis In many cases, however, the measurement accuracy and selectivity of these parameters do not suffice for a detailed analysis. In addition to Bo generate images of the magnetic susceptibility and the diffusion coefficient as well as images of fat and water separately In spite of the large number of parameters the problem of tissue characterization is quite difficult. The open questions are: Which of these parameters contain the relevant information ? How could the relevant information be extracted ? Is it necessary to calculate images of each of these parameters or are special combinations of these parameters required ?

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. /1/.
    A. Rosenfeld, A.C. Kak, Digital Picture Processing, Academic Press 76.Google Scholar
  2. /2/.
    J. Sch{rmann, Polynomklassifikatoren f{r die Zeichenerkennung, Oldenburg 77.Google Scholar
  3. /3/.
    H. Niemann, Klassifikation von Mustern, Springer 83.Google Scholar

Copyright information

© Springer-Verlag, Berlin, Heidelberg 1985

Authors and Affiliations

  • R. Bachus
    • 1
  • H. König
    • 1
  • G. Lenz
    • 1
  • M. Deimling
    • 1
  • E. R. Reinhardt
    • 1
  1. 1.SIEMENS Medical DivisionErlangenGermany

Personalised recommendations