Assessment of Renal Function from 3D Dynamic Contrast Enhanced MR Images Using Independent Component Analysis

  • Frank G. Zöllner
  • Marek Kocinski
  • Arvid Lundervold
  • Jarle Rørvik
Conference paper

DOI: 10.1007/978-3-540-71091-2_48

Part of the Informatik aktuell book series (INFORMAT)
Cite this paper as:
Zöllner F.G., Kocinski M., Lundervold A., Rørvik J. (2007) Assessment of Renal Function from 3D Dynamic Contrast Enhanced MR Images Using Independent Component Analysis. In: Horsch A., Deserno T.M., Handels H., Meinzer HP., Tolxdorff T. (eds) Bildverarbeitung für die Medizin 2007. Informatik aktuell. Springer, Berlin, Heidelberg

Abstract

In this paper we present an automated, unsupervised, data-driven approach to assess renal function from 3D DCE-MR images. Applying independent component analysis to four different data sets acquired at different field strengths and with different measurement techniques, we show that functional regions in the human kidney can be recovered by a subset of independent components. Time intensity curves, reflecting perfusion in the kidney can be extracted from the processed data. The procedure may allow non-invasive, local assessment of renal function (e.g. glomerular filtration rate, GFR) from the image time series in future.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2007

Authors and Affiliations

  • Frank G. Zöllner
    • 1
    • 2
  • Marek Kocinski
    • 3
  • Arvid Lundervold
    • 2
  • Jarle Rørvik
    • 1
  1. 1.Department for RadiologyUniversity of BergenBergenNorway
  2. 2.Department of BiomedicineUniversity of BergenBergenNorway
  3. 3.Institute of ElectronicsTechnical University of LodzLodzPoland

Personalised recommendations