Advertisement

Comprehensive Segmentation of Cine Cardiac MR Images

  • Maxim Fradkin
  • Cybèle Ciofolo
  • Benoit Mory
  • Gilion Hautvast
  • Marcel Breeuwer
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5241)

Abstract

A typical Cardiac Magnetic Resonance (CMR) examination includes acquisition of a sequence of short-axis (SA) and long-axis (LA) images covering the cardiac cycle. Quantitative analysis of the heart function requires segmentation of the left ventricle (LV) SA images, while segmented LA views allow more accurate estimation of the basal slice and can be used for slice registration. Since manual segmentation of CMR images is very tedious and time-consuming, its automation is highly required. In this paper, we propose a fully automatic 2D method for segmenting LV consecutively in LA and SA images. The approach was validated on 35 patients giving mean segmentation error smaller than one pixel, both for LA and SA, and accurate LV volume measurements.

Keywords

Cardiac Magnetic Resonance Active Contour Active Appearance Model Medical Image Analysis Statistical Shape 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.

Supplementary material

Supplementary Material (953 KB)

Supplementary Material (1,024 KB)

References

  1. 1.
    Weaver, A., et al.: Magnitude and causes of interobserver discrepancies in CMR volumme measurements: critical importance of choice of the basal slice. Journal of Cardiovascular Magnetic Resonance 1, 82–83 (2006)Google Scholar
  2. 2.
    Anderson, J., et al.: Normal cardiac magnetic resonance measurements and interobserver discrepancies in volumes and mass using the papillary muscle inclusion method. The Open General and Internal Medicine Journal 1, 6–12 (2007)Google Scholar
  3. 3.
    van Geuns, R., et al.: Automatic quantitative left ventricular analysis of cine MR images by using threedimensional information for contour detection. Radiology 240(1), 215–221 (2006)CrossRefGoogle Scholar
  4. 4.
    Mitchell, S.C., et al.: Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images. IEEE Trans. Med. Imag. 20(5), 415–423 (2001)CrossRefGoogle Scholar
  5. 5.
    Kaus, M.R., et al.: Automated segmentation of the left ventricle in cardiac MRI. Medical Image Analysis 8(3), 245–254 (2004)CrossRefGoogle Scholar
  6. 6.
    Niessen, W.J., et al.: Geodesic deformable models for medical image analysis. IEEE Trans. Med. Imag. 17(4), 634–641 (1998)CrossRefGoogle Scholar
  7. 7.
    Paragios, N.: A variational approach for the segmentation of the left ventricle in cardiac image analysis. Int. J. Comp. Vision 50(3), 345–362 (2002)zbMATHCrossRefGoogle Scholar
  8. 8.
    Jolly, M.P.: Automatic segmentation of the left ventricle in cardiac MR and CT images. Int. J. Comp. Vision 70(2), 151–163 (2006)CrossRefGoogle Scholar
  9. 9.
    Lelieveldt, B., et al.: Multi-view active appearance models for consistent segmentation of multiple standard views: application to long- and short-axis cardiac MR images. In: Int. Congress Series, vol. 1256, pp. 1141–1146 (2003)Google Scholar
  10. 10.
    Lotjonen, J., et al.: Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Medical Image Analysis (8), 371–386 (2004)Google Scholar
  11. 11.
    van Assen, H., et al.: SPASM: A 3D-ASM for segmentation of sparse and arbitrarily oriented cardiac MRI data. Medical Image Analysis 10, 286–303 (2006)CrossRefGoogle Scholar
  12. 12.
    Moore, J., et al.: A high resolution dynamic heart model based on averaged MRI data. In: Ellis, R.E., Peters, T.M. (eds.) MICCAI 2003. LNCS, vol. 2878, pp. 549–555. Springer, Heidelberg (2003)CrossRefGoogle Scholar
  13. 13.
    Lotjonen, J., et al.: Correction of movement artifacts from 4-d cardiac short- and long-axis MR data. In: Barillot, C., Haynor, D.R., Hellier, P. (eds.) MICCAI 2004. LNCS, vol. 3217, pp. 405–412. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  14. 14.
    Perperidis, D., et al.: Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Medical Image Analysis 9(8), 441–456 (2005)CrossRefGoogle Scholar
  15. 15.
    Hautvast, G., Cocosco, C., Kedenburg, G., Breeuwer, M.: Alignment of short axis and long axis cine cardiac MR images. In: CARS 2006, vol. 1, pp. 59–60 (2006)Google Scholar
  16. 16.
    Slomka, P.J., et al.: Automated registration of multiple single breath-hold cardiac MRI images. Intl. Soc. Mag. Reson. Med. 14, 1207 (2006)Google Scholar
  17. 17.
    Li, T., Denney, T.: Registration of short and long-axis images in cine cardiac MRI. Intl. Soc. Mag. Reson. Med. 14, 1208 (2006)Google Scholar
  18. 18.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: active contour models. Int. J. Comp. Vision 1(4), 321–331 (1987)CrossRefGoogle Scholar
  19. 19.
    Menet, S., Saint-Marc, P., Medioni, G.B.: BSnakes: implementation and application to stereo. In: Image Understanding Workshop, Pittsburgh, PA, pp. 720–726 (1990)Google Scholar
  20. 20.
    Williams, D.J., Shah, M.: A fast algorithm for active contours and curvature estimation. CVGIP: Image Understanding 55(1), 14–26 (1992)zbMATHCrossRefGoogle Scholar
  21. 21.
    Breeuwer, M., Hautvast, G., Mory, B., Fradkin, M.: Automatic segmentation of short-axis cine cardiac magnetic resonance. In: CARS 2008 (2008)Google Scholar
  22. 22.
    Hautvast, G., et al.: Automatic contour propagation in cine cardiac magnetic resonance images. IEEE Trans. Med. Imag. 25(11), 1472–1482 (2006)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2008

Authors and Affiliations

  • Maxim Fradkin
    • 1
  • Cybèle Ciofolo
    • 1
  • Benoit Mory
    • 1
  • Gilion Hautvast
    • 2
  • Marcel Breeuwer
    • 2
  1. 1.Medisys Research LabPhilips HealthcareSuresnesFrance
  2. 2.Healthcare InformaticsPhilips HealthcareBestThe Netherlands

Personalised recommendations