Advertisement

Factors Affecting Optical Flow Performance in Tagging Magnetic Resonance Imaging

  • Patricia Márquez-Valle
  • Hanne Kause
  • Andrea Fuster
  • Aura Hernàndez-Sabaté
  • Luc Florack
  • Debora Gil
  • Hans C. van  Assen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8896)

Abstract

Changes in cardiac deformation patterns are correlated with cardiac pathologies. Deformation can be extracted from tagging Magnetic Resonance Imaging (tMRI) using Optical Flow (OF) techniques. For applications of OF in a clinical setting it is important to assess to what extent the performance of a particular OF method is stable across different clinical acquisition artifacts. This paper presents a statistical validation framework, based on ANOVA, to assess the motion and appearance factors that have the largest influence on OF accuracy drop. In order to validate this framework, we created a database of simulated tMRI data including the most common artifacts of MRI and test three different OF methods, including HARP.

Keywords

Optical flow Performance evaluation Synthetic database ANOVA Tagging magnetic resonance imaging 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Zerhouni, E., Parish, D., Rogers, W., et al.: Human heart: Tagging with MR imaging-a method for noninvasive assessment of myocardial motion. Radiology 169(1), 59–63 (1988)CrossRefGoogle Scholar
  2. 2.
    Axel, L., Dougherty, L.: MR imaging of motion with spatial modulation of magnetization. Radiology 171(3), 841–845 (1989)CrossRefGoogle Scholar
  3. 3.
    Mirsky, I., Pfeffer, J., Pfeffer, M., Braunwald, E.: The contractile state as the major determinant in the evolution of left ventricular dysfunction in the spontaneously hypertensive rat 53, 767–778 (1983)Google Scholar
  4. 4.
    Götte, M., van Rossum, A., Twisk, J., et al.: Quantification of regional contractile function after infarction: Strain analysis superior to wall thickening analysis in discriminating infarct from remote myocardium. JACC 37, 808–817 (2001)CrossRefGoogle Scholar
  5. 5.
    Delhaas, T., Kotte, J., van der Toorn, A., et al.: Increase in left ventricular torsion-to-shortening ratio in children with valvular aorta stenosis 51, 135–139 (2004)Google Scholar
  6. 6.
    Horn, B., Schunck, B.: Determining optical flow. AI 17, 185–203 (1981)Google Scholar
  7. 7.
    Osman, N., Kerwin, W., McVeigh, E., Prince, J.: Cardiac motion tracking using CINE HARP magnetic resonance imaging 42(6), 1048–1060 (1999)Google Scholar
  8. 8.
    Prince, J., McVeigh, E.: Motion estimation from tagged MR image sequences 11(2), 238–249 (1992)Google Scholar
  9. 9.
    Florack, L., van Assen, H.: A new methodology for multiscale myocardial deformation and strain analysis based on tagging MRI (2010)Google Scholar
  10. 10.
    Xavier, M., Lalande, A., Walker, P., et al.: An adapted optical flow algorithm for robust quantification of cardiac wall motion from standard cine-MR examinations. Inf. Tech. in Biomed. 16(5), 859–868 (2012)CrossRefGoogle Scholar
  11. 11.
    Garcia-Barnes, J., Gil, D., Pujades, S., Carreras, F.: Variational framework for assessment of the left ventricle motion. Math. Mod. of Nat. Phen. 3(6), 76–100 (2008)CrossRefGoogle Scholar
  12. 12.
    Becciu, A., van Assen, H., Florack, L., et al.: A multi-scale feature based optic flow method for 3D cardiac motion estimation. In: SSVM, pp. 588–599 (2009)Google Scholar
  13. 13.
    Gupta, S., Prince, J.: On variable brightness optical flow for tagged MRI, pp. 323–334 (1995)Google Scholar
  14. 14.
    Carranza-Herrezuelo, N., Bajo, A., Sroubek, F., et al.: Motion estimation of tagged cardiac magnetic resonance images using variational techniques. Comp. Med. Im. and Graph. 34(6), 514–522 (2010)CrossRefGoogle Scholar
  15. 15.
    Alessandrini, M., Basarab, A., Liebgott, H., Bernard, O.: Myocardial motion estimation from medical images using the monogenic signal. IEEE Transactions on Image Processing 22(3), 1084–1095 (2013)CrossRefMathSciNetGoogle Scholar
  16. 16.
    Arts, T., Prinzen, F., Delhaas, T., et al.: Mapping displacement and deformation of the heart with local sine-wave modeling 29(5) (2010)Google Scholar
  17. 17.
    Smal, I., Carranza-Herrezuelo, N., Klein, S., et al.: Reversible jump MCMC methods for fully automatic motion analysis in tagged MRI. Medical Image Analysis 16(1), 301–324 (2012)CrossRefGoogle Scholar
  18. 18.
    Arnold, S.: The theory of linear models and multivariate observations. Wiley (1997)Google Scholar
  19. 19.
    Jap, B., Lal, S., Fischer, P., Bekiaris, E.: Using eeg spectral components to assess algorithms for detecting fatigue. Expert Systems with Applications 36(2), 2352–2359 (2009)CrossRefGoogle Scholar
  20. 20.
    Arts, T., Hunter, W., Douglas, A., et al.: Description of the deformation of the left ventricle by a kinematic model. Journal Biomechanics 25(10), 1119–1127 (1992)CrossRefGoogle Scholar
  21. 21.
    Tukey, L.: Comparing individual means in the analysis of variance. Biometrics 5, 99–114 (1949)CrossRefMathSciNetGoogle Scholar
  22. 22.
    Waks, E., Prince, J., Douglas, A.: Cardiac motion simulator for tagged MRI. In: MMBIA-Workshops, pp. 182–191 (1996)Google Scholar
  23. 23.
    Gutberlet, M., Schwinge, K., Freyhardt, P., et al.: Influence of high magnetic field strengths and parallel acquisition strategies on image quality in cardiac 2D CINE magnetic resonance imaging. Eur. Radiol. 15(8), 1586–1597 (2005)CrossRefGoogle Scholar
  24. 24.
    Baker, S., Scharstein, D., Lewis, J., et al.: A database and evaluation methodology for optical flow. IJCV 92(1), 1–31 (2011)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Patricia Márquez-Valle
    • 1
  • Hanne Kause
    • 2
  • Andrea Fuster
    • 3
    • 4
  • Aura Hernàndez-Sabaté
    • 1
  • Luc Florack
    • 3
    • 4
  • Debora Gil
    • 1
  • Hans C. van  Assen
    • 2
  1. 1.Computer Vision CenterAutonomous University of BarcelonaBarcelonaSpain
  2. 2.Department of Electrical EngineeringEindhoven University of TechnologyEindhovenThe Netherlands
  3. 3.Department of Biomedical EngineeringEindhoven University of TechnologyEindhovenThe Netherlands
  4. 4.Department of Mathematics and Computer ScienceEindhoven University of TechnologyEindhovenThe Netherlands

Personalised recommendations