High-Precision Computer-Assisted Segmentation of Multispectral MRI Data Sets in Patients with Multiple Sclerosis by a Flexible Machine Learning Image Analysis Approach

  • Axel Wismüller
  • Johannes Behrends
  • Oliver Lange
  • Miriana Jukic
  • Klaus Hahn
  • Maximilian Reiser
  • Dorothee Auer
Part of the Informatik aktuell book series (INFORMAT)

Abstract

Automatic brain segmentation is an issue of specific clinical relevance in both diagnosis and therapy control of patients with demyelinating diseases such as Multiple Sclerosis (MS). We present a complete system for high-precision computer-assisted image analysis of multispectral MRI data based on a flexible machine learning approach. Careful quality evaluation shows that the system outperforms conventional threshold-based techniques w.r.t. inter-observer agreement levels for the quantification of relevant clinical parameters, such as white matter lesion load and brain parenchyma volume.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Filippi M, Horsfield M, Tofts P, et al.: Quantitative assessment of MRI lesion load in monitoring the evolution of multiple sclerosis. Brain, 118:1601–1612, 1995.CrossRefGoogle Scholar
  2. 2.
    Ge Y, Grossman RI, Udupa JK, et al.: Brain athrophy in relapsing-remitting multiple sclerosis and secondary progressive multiple sclerosis: longitudinal quantitative analysis. Radiology, 214:665–670, 2000.Google Scholar
  3. 3.
    Kurtzke JF: Rating neurologic impairment in multiple sclerosis: an expanded disability status scale EDSS. Neurology 33:300–311, 1983.Google Scholar
  4. 4.
    Wismüller A, Vietze F, Dersch DR: Segmentation with neural networks. In: Bankman I, et al. (eds.), Handbook of Medical Imaging, Academic Press, ISBN 0-12-077790-8, 2000.Google Scholar
  5. 5.
    Wismüller A, Behrends J, Lange O, et al.: Automatic segmentation of cerebral contours in multispectral MRI data sets of the human brain by self-organizing neural networks. Radiology 221(P):461, 2001.Google Scholar
  6. 6.
    British Standards Institution: Precision of test methods. Part I. Guide for the determination of “reproducibility” for a standard test method by inter-laboratory tests. BS 5497. 1987.Google Scholar
  7. 7.
    Wicks D, Tofts P, et al.: Volume measurement of multiple sclerosis lesions with magnetic resonance images: a preliminary study. Neuroradiology 34:475–479, 1992.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Axel Wismüller
    • 1
  • Johannes Behrends
    • 1
  • Oliver Lange
    • 1
  • Miriana Jukic
    • 1
  • Klaus Hahn
    • 2
  • Maximilian Reiser
    • 1
  • Dorothee Auer
    • 3
  1. 1.Institut für Klinische Radiologie, Klinikum der Universität MünchenLudwig-Maximilians-Universität MünchenMünchen
  2. 2.Klinik und Poliklinik für Nuklearmedizin, Klinikum der Universität MünchenLudwig-Maximilians-Universität MünchenMünchen
  3. 3.Max-Planck-Institut für PsychiatrieMünchen

Personalised recommendations