Journal of Digital Imaging

, Volume 26, Issue 5, pp 898–908 | Cite as

Cardiac MRI Segmentation Using Mutual Context Information from Left and Right Ventricle

Article

Abstract

In this paper, we propose a graphcut method to segment the cardiac right ventricle (RV) and left ventricle (LV) by using context information from each other. Contextual information is very helpful in medical image segmentation because the relative arrangement of different organs is the same. In addition to the conventional log-likelihood penalty, we also include a “context penalty” that captures the geometric relationship between the RV and LV. Contextual information for the RV is obtained by learning its geometrical relationship with respect to the LV. Similarly, RV provides geometrical context information for LV segmentation. The smoothness cost is formulated as a function of the learned context which helps in accurate labeling of pixels. Experimental results on real patient datasets from the STACOM database show the efficacy of our method in accurately segmenting the LV and RV. We also conduct experiments on simulated datasets to investigate our method’s robustness to noise and inaccurate segmentations.

Keywords

Mutual context information LV RV Segmentation Cardiac MRI Graph cuts 

References

  1. 1.
    Allender S: European Cardiovascular Disease Statistics. European Heart Network. 2008Google Scholar
  2. 2.
    A.F. Frangi, W.J. Niessen, and M.A. Viergever, “Three dimensional modeling for functional analysis of cardiac images: a review,” IEEE Trans Med. Imag, vol. 20, no. 1, pp. 2–25, 2001CrossRefGoogle Scholar
  3. 3.
    C. Petitjean and J-N. Dacher, “A review of segmentation methods in short axis cardiac mr images,” Med. Imag. Anal., vol. 15, no. 2, pp. 169–184, 2011Google Scholar
  4. 4.
    S. Shors, C. Fung, C. Francois, P. Finn, and D. Fieno, “Accurate quantification of right ventricular mass at MR imaging by using cine true fast imaging with steady state precession: study in dogs.,” Radiology, vol. 230, no. 2, pp. 383–388, 2004PubMedCrossRefGoogle Scholar
  5. 5.
    Jolly MP: Automatic recovery of the left ventricle blood pool in cardiac cine MR images. In: MICCAI, 2008, pp 110–118Google Scholar
  6. 6.
    N. Paragios, “A variational approach for the segmentation of the left ventricle in cardiac image analysis,” Intl. J. Comp. Vis., vol. 50, no. 3, pp. 345–362, 2002CrossRefGoogle Scholar
  7. 7.
    M. Lynch, O. Ghita, and P. Whelan, “Left ventricle myocardium segmentation using a coupled level set with a-priori knowledge,” Comput. Med. Imag. Graph., vol. 30, no. 4, pp. 255–262, 2006CrossRefGoogle Scholar
  8. 8.
    Lin X, Cowan B, and Young A: Model based graph cut method for segmentation of the left ventricle. In In Proc: EMBC, 2005, pp 3059–3062Google Scholar
  9. 9.
    Mahapatra D and Sun Y: Orientation histograms as shape priors for left ventricle segmentation using graph cuts. In Proc: MICCAI, 2011, pp 420–427Google Scholar
  10. 10.
    Mahapatra D: Cardiac image segmentation from cine cardiac MRI using graph cuts and shape priors. Journal of Digital Imaging. doi:10.1007/s10278-012-9548-5, 2013
  11. 11.
    J. Cousty, L. Najman, M. Couprie, S. Clment-Guinaudeau, T. Goissen, and J. Garot, “Segmentation of 4-D cardiac MRI: automated method based on spatio temporal watershed cuts.,” Image and Vis. Comput., vol. 28, no. 8, pp. 1229–1243, 2010CrossRefGoogle Scholar
  12. 12.
    C. Cocosco, W. Niessen, T. Netsch, E-J. Vonken, G. Lund, A. Stork, and M. Viergever.,“Automatic image driven segmentation of the ventricles in cardiac cine MRI.,” J. magn. Reson. Imag., vol. 28, no. 2, pp. 366–374, 2008Google Scholar
  13. 13.
    Mahapatra D, and Sun Y: Joint registration and segmentation of dynamic cardiac perfusion images using mrfs. In In Proc: MICCAI, 2010, pp 493–501Google Scholar
  14. 14.
    D. Mahapatra and Y. Sun, “Integrating segmentation information for improved elastic registration of perfusion images using an mrf framework,” IEEE Trans. Imag. Proc., vol. 21, no. 1, pp. 170–183, 2012CrossRefGoogle Scholar
  15. 15.
    Mahapatra D: Joint segmentation and groupwise registration of cardiac perfusion images using temporal information. Journal of Digital ImagingGoogle Scholar
  16. 16.
    D. Mahapatra: Groupwise registration of dynamic cardiac perfusion images using temporal dynamics and segmentation information", SPIE Medical Imaging 2012, SPIE Vol 8314, pp 1–7Google Scholar
  17. 17.
    M.R. Kaus, J. von Berg, J. Weese, W. Niessen, and V. Pekar, “Automated segmentation of the left ventricle in cardiac MRI,” Med Image Anal., vol. 8, no. 3, pp. 245–254, 2004PubMedCrossRefGoogle Scholar
  18. 18.
    Zhu Y, Papademetris X, Sinusas A, and Duncan J.S: Segmentation of left ventricle from 3d cardiac mr image sequence using a subject specific dynamic model. In Proc.IEEE CVPR, 2008, pp 1–8Google Scholar
  19. 19.
    Sun W, Setin M, Chan R, Reddy V, Holmvang G, Ch V, and Willsky A: segmenting and tracking of the left ventricle by learning the dynamics in cardiac images. In Proc. IPMI, 2005, pp 553–565Google Scholar
  20. 20.
    R. H. Davies, C. J. Twining, T. F. Cootes, J. C. Waterton, and C. J. Taylor, “A minimum description length approach to statistical shape modelling,” IEEE Trans. Med. Imag., vol. 21, pp. 525–537, 2002CrossRefGoogle Scholar
  21. 21.
    Perperidis D, Mohiaddin R, and Rueckert D: Construction of a 4d statistical atlas of the cardiac anatomy and its use in classification. In MICCAI, 2005, pp 402–410Google Scholar
  22. 22.
    Besbes A, Komodakis N, and Paragios N: Graph-based knowledge-driven discrete segmentation of the left ventricle. In IEEE ISBI, 2009, pp 49–52Google Scholar
  23. 23.
    S.C. Mitchell, B.P.F. Lelieveldt, R.J. van der Geest, H.G. Bosch, J.H.C Reiver, and M. Sonka, “Multistage hybrid active appearance models: segmentation of cardiac MR and ultrasound images,” IEEE Trans Med. Imag, vol. 20, no. 5, pp. 415–423, 2001Google Scholar
  24. 24.
    H. Zhang, A. Wahle, R. Johnson, T. Scholz, and M. Sonka, “4-D cardiac MR image analysis: left and right ventricular morphology and function.,” IEEE Trans Med. Imag, vol. 29, no. 2, pp. 350–364, 2010CrossRefGoogle Scholar
  25. 25.
    Zambal S, Hladuvka J, and Buhler K: Improving segmentation of the left ventricle using a two component statistical model. In MICCAI, 2006, pp 151–158Google Scholar
  26. 26.
    Lelieveldt B, Mitchell S, Bosch J, van der Geest R, Sonka M, and Reiber J: Time continuous segmentation of cardiac image sequences using active appearance motion models. In IPMI, 2001, pp 446–452Google Scholar
  27. 27.
    C. Pluempitiwiriyawej, J.M.F. Moura, Y.L.Wu, and C. Ho, “STACS: new active contour scheme for cardiac MR image segmentation,” IEEE Trans. Med. Imag., vol. 24, no. 5,pp. 593–603, 2005Google Scholar
  28. 28.
    Billet F, Sermeanst M, Delingette H, and Ayache N: Cardiac motion recovery and boundary conditions estimation by coupling an electromechanical model and cine-MRI data. In Functional imaging and modeling of the heart (FMIH), 2009, pp 376–385Google Scholar
  29. 29.
    J. Ltjnen, S. Kivist, J. Koikkalainen, D. Smutek, and K. Lauerma, “Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images,” Med Image Anal., vol. 8, no. 3, pp. 371–386, 2004CrossRefGoogle Scholar
  30. 30.
    S. Geman and D. Geman, “Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images.,” IEEE Trans. Patt. Anal. Mach. Intell., vol. 6, no. 6, pp. 721–741, 1984CrossRefGoogle Scholar
  31. 31.
    Kumar S and Hebert M: Discriminative random fields: a discriminative framework for contextual interaction in classification. In Proc. ICCV, 2003, pp 1150–1157Google Scholar
  32. 32.
    S. Belongie, J. Malik, and J. Puzicha, “Shape matching and object recognition using shape contexts,” IEEE Trans. Patt. Anal. Mach. Intell., vol. 24, no. 24, pp. 509–522, 2002CrossRefGoogle Scholar
  33. 33.
    Hoiem D, Efros AA, and Hebert M: Putting objects in perspective. In Proc. CVPR, 2006, pp 2137–2144Google Scholar
  34. 34.
    He X, Zemel RS, and Carreira-Perpinan MA: Multiscale conditional random fields for image labeling. In Proc. CVPR, 2004, pp 695–702Google Scholar
  35. 35.
    Murphy K, Torralba A and Freeman WT: Graphical model for recognizing scenes and objects. In Proc. NIPSGoogle Scholar
  36. 36.
    Z. Tu and X. Bai, “Auto-context and its application to high-level vision tasks and 3d brain image segmentation,” IEEE Trans. Patt. Anal. Mach. Intell., vol. 32, no. 10, pp. 1744 – 1757, 2010CrossRefGoogle Scholar
  37. 37.
    Li W, Liao S, Feng Q, Chen W, and Shen D: Learning image context for segmentation of prostate in ct-guided radiotherapy. In MICCAI, 2011, pp 570–578Google Scholar
  38. 38.
    Delong A and Boykov Y: Globally optimal segmentation of multi-region objects. In ICCV, 2009, pp 285–292Google Scholar
  39. 39.
    Ben Ayed I, Punithakumar K, Garvin G, Romano W, and Li S: Graph cuts withinvariant object-interaction priors: Application to intervertebral disc segmentation. In IPMI, 2011, pp 221–232Google Scholar
  40. 40.
    Song Q, Chen M, Bai J, Sonka M, and Wu X: Surface-region context in optimal multi-object graph based segmentation: robust delineation of pulmonary tumors. In IPMI, 2011, pp 61–72Google Scholar
  41. 41.
    Y. Boykov and O. Veksler, “Fast approximate energy minimization via graph cuts,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 23, pp. 1222–1239, 2001CrossRefGoogle Scholar
  42. 42.
    V. Chalana and Y. Kim, “A methodology for evaluation of boundary detection algorithms on medical images,” IEEE Trans. Med. Imag., vol. 16, no. 5, pp. 642–652, 1997CrossRefGoogle Scholar
  43. 43.
    D.P. Huttenlocher, G.A. Klanderman, and W.J. Rucklidge, “Comparing images using the hausdorff distance,” IEEE Trans. Pattern Anal. Machine Intell., vol. 15, no. 9, pp. 850–863, 1993CrossRefGoogle Scholar
  44. 44.
    C.G. Fonseca, M. Backhaus, D.A. Bluemke, R.D. Britten, J.D. Chung, B.R. Cowan, I.D. Dinov, J.P. Finn, P.J. Hunter, A.H. Kadish, D.C. Lee, J.A.C. Lima, P. Medrano-Gracia, K. Shivkumar, A. Suinesiaputra, W. Tao, and A.A. Young., “The cardiac atlas project an imaging database for computational modeling and statistical atlases of the heart.,” Bioinformatics, vol. 27, no. 16, pp. 2288–2295, 2011PubMedCrossRefGoogle Scholar
  45. 45.
    A.H. Kadish, D. Bello, J.P. Finn, R.O. Bonow, A. Schaechter, H. Subacius, C. Albert, J.P. Daubert, C.G. Fonseca, and J.J. Goldberger., “Rationale and design for the defribrillators to reduce risk by magnetic resonance imaging evaluation (determine) trial.,” J. Cardiovascular Electrophysiology, vol. 20, no. 9, pp. 982–987, 2009CrossRefGoogle Scholar
  46. 46.
    A. Elen, J. Hermans, J. Ganame, D. Loeckx, J. Bogaert, F. Maes, and P. Suetens., “Automatic 3-d breath-hold related motion correction of dynamic multislice mri.,” IEEE Trans. Med. Imag., vol. 29, no. 3, pp. 868–878, 2010CrossRefGoogle Scholar
  47. 47.
    A.A. Young, B.R. Cowan, S.F. Thrupp, W.J. Hedley, and L.J. DellItalia., “Left ventricular mass and volume: fast calculation with guide-point modeling on mr images.,” Radiology, vol. 202, no. 2, pp. 597–602, 2000Google Scholar
  48. 48.
    Suinesiaputra A and et al: Left ventricular segmentation challenge from cardiac mri: a collation study. In STACOM 2011, 2011, pp 88–97Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2013

Authors and Affiliations

  1. 1.Department of Computer ScienceSwiss Federal Institute of Technology (ETH) ZurichZurichSwitzerland

Personalised recommendations