Advertisement

Motion-Compensation of Cardiac Perfusion MRI Using a Statistical Texture Ensemble

  • Mikkel B. Stegmann
  • Henrik B. W. Larsson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2674)

Abstract

This paper presents a novel method for segmentation of cardiac perfusion MRI. By performing complex analyses of variance and clustering in an annotated training set off-line, the presented method provides real-time segmentation in an on-line setting. This renders the method feasible for e.g. analysis of large image databases or for live non-rigid motion-compensation in modern MR scanners. Changes in image intensity during the bolus passage is modelled by an Active Appearance Model augmented with a cluster analysis of the training set and priors on pose and shape. Preliminary validation of the method is carried out using 250 MR perfusion images, acquired without breath-hold from five subjects. Quantitative and qualitative results show high accuracy, given the limited number of subjects.

Keywords

Myocardial Perfusion Myocardial Perfusion Imaging Right Ventricle Segmentation Result Active Appearance Model 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    R. Beichel, S. Mitchell, E. Sorantin, F. Leberl, A. Goshtasby, and M. Sonka. Shape-and appearance-based segmentation of volumetric medical images. IEEE International Conference on Image Processing, 2:589–592, 2001.Google Scholar
  2. 2.
    L.M. Bidaut and J.P. Vallee. Automated registration of dynamic MR images for the quantification of myocardial perfusion. Magn Reson Imag, 13(4):648–655, 2001.CrossRefGoogle Scholar
  3. 3.
    J.G. Bosch, S.C. Mitchell, B.P. Lelieveldt, F. Nijland, O. Kamp, M. Sonka, and J.H. Reiber. Fully automated endocardial contour detection in time sequences of echocardiograms by three-dimensional active appearance models. Medical Imaging 2002: Image Processing, San Diego CA, SPIE, pages 452–462, 2002.Google Scholar
  4. 4.
    T.F. Cootes, G.J. Edwards, and C.J. Taylor. Active appearance models. In Proc. European Conf. on Computer Vision, volume 2, pages 484–498. Springer, 1998.Google Scholar
  5. 5.
    T.F. Cootes, G.J. Edwards, and C.J. Taylor. Active appearance models. IEEE Trans. on Pattern Recognition and Machine Intelligence, 23(6):681–685, 2001.CrossRefGoogle Scholar
  6. 6.
    T.F. Cootes and C.J. Taylor. Statistical Models of Appearance for Computer Vision. Tech. Report. Feb 2000, University of Manchester, 2000.Google Scholar
  7. 7.
    G.J. Edwards, C.J. Taylor, and T. F. Cootes. Interpreting face images using active appearance models. In Proc. 3rd IEEE Int. Conf. on Automatic Face and Gesture Recognition, pages 300–5. IEEE Comput. Soc, 1998.Google Scholar
  8. 8.
    E. Forgey. Cluster analysis of multivariate data. Biometrics, 21:768, 1965.Google Scholar
  9. 9.
    HenrikB.W. Larsson, Thomas Fritz-Hansen, Egill Rostrup, Lars Søndergaard, Poul Ring, and Ole Henriksen. Myocardial perfusion modeling using MRI. Magnetic Resonance in Medicine, 35:716–726, 1996.CrossRefGoogle Scholar
  10. 10.
    S. Mitchell, B. Lelieveldt, R. Geest, H. Bosch, J. Reiber, and M. Sonka. Time continuous segmentation of cardiac MR image sequences using active appearance motion models. In Medical Imaging 2001: Image Processing, San Diego CA, SPIE, volume 1, pages 249–256. SPIE, 2001.Google Scholar
  11. 11.
    S. Mitchell, B. Lelieveldt, R. Geest, J. Schaap, J. Reiber, and M. Sonka. Segmentation of cardiac MR images: An active appearance model approach. In Medical Imaging 2000: Image Processing, San Diego CA, SPIE, volume 1. SPIE, 2000.Google Scholar
  12. 12.
    L. Spreeuwers and M. Breeuwer. Automatic detection of the myocardial boundaries of the right and left ventricle in mr cardio perfusion scans. Proceedings of SPIE-The International Society for Optical Engineering, 4322(3):1207–1217, 2001.Google Scholar
  13. 13.
    M.B. Stegmann and R.H. Davies. Corpus callosum analysis using MDL-based sequential models of shape and appearance. In Medical Image Computing and Computer-Assisted Intervention-MICCAI., LNCS. Springer, 2003 (submitted).Google Scholar
  14. 14.
    M.B. Stegmann, B K. Ersbøll, and R. Larsen. FAME-a flexible appearance modelling environment. IEEE Trans. on Medical Imaging, 2003 (to appear).Google Scholar
  15. 15.
    M.B. Stegmann, R. Fisker, and B.K. Ersbøll. Extending and applying active appearance models for automated, high precision segmentation in diffierent image modalities. In Proc. 12th Scandinavian Conference on Image Analysis-SCIA 2001, volume 1, pages 90–97, 2001.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Mikkel B. Stegmann
    • 1
    • 2
  • Henrik B. W. Larsson
    • 2
    • 3
  1. 1.Informatics and Mathematical ModellingTechnical University of DenmarkDenmark
  2. 2.Danish Research Centre for Magnetic ResonanceH:S Hvidovre HospitalDenmark
  3. 3.MR-Senteret, St. Olavs HospitalTrondheim UniversityNorway

Personalised recommendations