Journal of Digital Imaging

, Volume 26, Issue 4, pp 721–730 | Cite as

Cardiac Image Segmentation from Cine Cardiac MRI Using Graph Cuts and Shape Priors

  • Dwarikanath Mahapatra


In this paper, we propose a novel method for segmentation of the left ventricle, right ventricle, and myocardium from cine cardiac magnetic resonance images of the STACOM database. Our method incorporates prior shape information in a graph cut framework to achieve segmentation. Poor edge information and large within-patient shape variation of the different parts necessitates the inclusion of prior shape information. But large interpatient shape variability makes it difficult to have a generalized shape model. Therefore, for every dataset the shape prior is chosen as a single image clearly showing the different parts. Prior shape information is obtained from a combination of distance functions and orientation angle histograms of each pixel relative to the prior shape. To account for shape changes, pixels near the boundary are allowed to change their labels by appropriate formulation of the penalty and smoothness costs. Our method consists of two stages. In the first stage, segmentation is performed using only intensity information which is the starting point for the second stage combining intensity and shape information to get the final segmentation. Experimental results on different subsets of 30 real patient datasets show higher segmentation accuracy in using shape information and our method's superior performance over other competing methods.


Segmentation Shape priors Orientation histograms Graph cuts Cine cardiac MRI 


  1. 1.
    S. Allender., European cardiovascular disease statistics. European Heart Network, 2008Google Scholar
  2. 2.
    Frangi AF, Niessen WJ, Viergever MA: Three dimensional modeling for functional analysis of cardiac images: a review. IEEE Trans Med. Imag 20(1):2–25, 2001CrossRefGoogle Scholar
  3. 3.
    Petitjean C, Dacher J-N: A review of segmentation methods in short axis cardiac MR images. Med Imag Anal 15(2):169–184, 2011CrossRefGoogle Scholar
  4. 4.
    Shors S, Fung C, Francois C, Finn P, Fieno D: Accurate quantification of right ventricular mass at MR imaging by using cine true fast imaging with steady state precession: study in dogs. Radiology 230(2):383–388, 2004PubMedCrossRefGoogle Scholar
  5. 5.
    Frangi AF, Niessen WJ, Hoogeveen R, van Walsum T, Viergever MA: Model based quantization of 3-D magnetic resonance angiographic images. IEEE Trans Med Imag 18(10):946–956, 1999CrossRefGoogle Scholar
  6. 6.
    Selle D, Preim B, Schnek A, Peitgen H: “Analysis of vasculature for liver surgical planning. IEEE Trans Med Imag 21(11):1344–1357, 2002CrossRefGoogle Scholar
  7. 7.
    Keegan J, Horkaew P, Buchanan T, Smart T, Yang G, Firmin D: Intra and interstudy reproducibility of coronary artery diameter measurements in magnetic resonance coronary angiography. J Magn Reson Imag 20(1):160–166, 2004CrossRefGoogle Scholar
  8. 8.
    Kolipaka A, Chatzimavroudis G, White R, O’Donnell T, Setser R: Segmentation of non-viable myocardium in delayed magnetic resonance images. Int J Cadiovasc Imag 21(2):303–311, 2005CrossRefGoogle Scholar
  9. 9.
    Noble N, Hill D, Breeuwer M et al: The automatic identification of hibernating myocardium. In: Proc. Intl. Conf. Med. Image Computing and Computer-Assisted Intervent (MICCAI), 2004, pp 890–898Google Scholar
  10. 10.
    Schwitter J: Myocardial perfusion. J Magn Reson Imag 24(5):953–963, 2006CrossRefGoogle Scholar
  11. 11.
    Di Bella E, Sitek A et al: Time curve analysis techniques for dynamic contrast MRI studies. In: Intl. Conf Inf. Process. Med. Imag. (IPMI), 2001, pp 211–217Google Scholar
  12. 12.
    Perperidis D, Mohiaddin R, Rueckert D: Construction of a 4D statistical atlas of the cardiac anatomy and its use in classification. In: MICCAI, 2005, pp 402–410Google Scholar
  13. 13.
    Besbes A, Komodakis N, Paragios N: Graph-based knowledge-driven discrete segmentation of the left ventricle. In: ISBI, 2009, pp 49–52Google Scholar
  14. 14.
    Zhu Y, Papademetris X, Sinusas A et al: Segmentation of left ventricle from 3D cardiac mr image sequence using a subject specific dynamic model. In: Proc. CVPR, 2009, pp 1–8Google Scholar
  15. 15.
    Sun W, Setin M, Chan R et al: Segmenting and tracking of the left ventricle by learning the dynamics in cardiac images. In: Proc. IPMI, , 2005, pp 553–565Google Scholar
  16. 16.
    Davies RH, Twining CJ, Cootes TF, Waterton JC, Taylor CJ: A minimum description length approach to statistical shape modelling. IEEE Trans Med Imag 21:525–537, 2002CrossRefGoogle Scholar
  17. 17.
    Kaus MR, von Berg J, Weese J, Niessen W, Pekar V: Automated segmentation of the left ventricle in cardiac MRI. Med Image Anal 8(3):245–254, 2004PubMedCrossRefGoogle Scholar
  18. 18.
    Jolly MP et al: Automatic recovery of the left ventricle blood pool in cardiac cine MR images. In: MICCAI, 2008, pp 110–118Google Scholar
  19. 19.
    Lorenzo-Valdes M, Sanchez-Ortiz GI, Elkington AG, Mohiaddin RH, Rueckert D: Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Med Image Anal 8(3):255, 2004PubMedCrossRefGoogle Scholar
  20. 20.
    Niessen WJ, Romeny BMTH, Viergever MA: Geodesic deformable models for medical image analysis. IEEE Trans Med Imag 17(4):634–41, 1998CrossRefGoogle Scholar
  21. 21.
    Paragios N: A variational approach for the segmentation of the left ventricle in cardiac image analysis. Intl J Comp Vis 50(3):345–362, 2002CrossRefGoogle Scholar
  22. 22.
    Jolly MP: Automatic segmentation of the left ventricle in cardiac MR and CT images. Int J Comp Vision 70(2):151–163, 2006CrossRefGoogle Scholar
  23. 23.
    Ltjnen J, Kivist S, Koikkalainen J, Smutek D, Lauerma K: Statistical shape model of atria, ventricles and epicardium from short- and long-axis MR images. Med Image Anal 8(3):371–386, 2004CrossRefGoogle Scholar
  24. 24.
    van Assen C, Danilouchkine MG, Frangi AF, Ords S, Westenberg JJ, Reiber JH, Lelieveldt BP: pasm: a 3D-asm for segmentation of sparse and arbitrarily oriented cardiac MRI data. Med Image Anal 10(2):286–303, 2006PubMedCrossRefGoogle Scholar
  25. 25.
    Mahapatra D, Sun Y: Joint registration and segmentation of dynamic cardiac perfusion images using MRFs. In: Proc. MICCAI, 2010, pp 493–501Google Scholar
  26. 26.
    Mahapatra D, Sun Y: Integrating segmentation information for improved MRF based elastic image registration. IEEE Trans Imag Proc 21(1):170–183, 2012CrossRefGoogle Scholar
  27. 27.
    Mitchell SC, Lelieveldt BPF, et al: Multistage hybrid active appearance models: segmentation of cardiac MR and ultrasound images. IEEE Trans Med. Imag 20(5):415–423, 2001CrossRefGoogle Scholar
  28. 28.
    Goshtasby A, Turner D: Segmentation of cardiac cine MR images for extraction of right and left ventricular chambers. IEEE Trans Med Imag 14(1):56–64, 1995CrossRefGoogle Scholar
  29. 29.
    Weng J, Singh A, Chiu M: Learning based ventricle detection from cardiac MR and CT images. IEEE Trans Med Imag 16(4):378–391, 1997CrossRefGoogle Scholar
  30. 30.
    Katouzian A, Konofagau E, Prakash A: A new automated technique for left and right ventricular segmentation in magnetic resonance imaging in IEEE. In: EMBS, 2006, pp 3074–3077Google Scholar
  31. 31.
    Gering D: Automatic segmentation of cardiac MRI. In: MICCAI, 2003, pp 524–532Google Scholar
  32. 32.
    Cocosco C, Niessen W, Netsch T, Vonken E-J, Lund G, Stork A, Viergever M: “Automatic image driven segmentation of the ventricles in cardiac cine MRI. J Magn Reson Imag 28(2):366–374, 2008CrossRefGoogle Scholar
  33. 33.
    Battani R, Corsi C, Sarti A et al: Estimation of right ventricular volume without geometrical assumptions utilizing cardiac magnetic resonance data. In: Comput Cardiol, 2003, pp 81–84Google Scholar
  34. 34.
    Pluempitiwiriyawej C, Moura JMF, Wu YL, Ho C: STACS: new active contour scheme for cardiac MR image segmentation. IEEE Trans Med Imag 24(5):593–603, 2005CrossRefGoogle Scholar
  35. 35.
    Sermeanst M, Moireau P, Camara O, Sainte-Marie J, Adriantsimiavona R, Cimrman R, Hill DL, Chapelle D, Razavi R: Cardiac function estimation from MRI using a heart model and data assimilation: advances and difficulties. Med Image Anal. 10(4):642–656, 2006CrossRefGoogle Scholar
  36. 36.
    Billet F, Sermeanst M,Delingette H et al: 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
  37. 37.
    Ordas S, Boisrobert L, Huguet M et al: Active shape models with invariant optimal features (IOFASM)—application to cardiac MRI segmentation. In: Comput Cardiol, 2003, pp 633–636Google Scholar
  38. 38.
    Lorenzo-Valdes M, Sanchez-Ortis G, Mohiaddin R et al: Atlas based segmentation and tracking of 3D cardiac MR images using non-rigid registration. In: MICCAI, 2002, pp 642–650Google Scholar
  39. 39.
    Cremers D, Tischhauser F, Weickert J, Schnorr C: Diffusion snakes: introducing statistical shape knowledge into the Mumford–Shah functional. Intl J Comp Vis 50(3):295–313, 2002CrossRefGoogle Scholar
  40. 40.
    Chang H, Yang Q, Parvin B: Bayesian approach for image segmentation with shape priors. In: CVPR, 2008, pp 1–8Google Scholar
  41. 41.
    Freedman D, Zhang T: Interactive graph cut based segmentation with shape priors. In CVPR, 2005, pp 755–762Google Scholar
  42. 42.
    Slabaugh G, Unal G: Graph cuts segmentation using an elliptical shape prior. In: ICIP, 2005, pp 1222–1225Google Scholar
  43. 43.
    Mahapatra D, Sun Y: Orientation histograms as shape priors for left ventricle segmentation using graph cuts. In: Proc MICCAI, 2011, pp 420–427Google Scholar
  44. 44.
    Boykov Y, Veksler O: Fast approximate energy minimization via graph cuts. IEEE Trans Pattern Anal Mach Intell 23:1222–1239, 2001CrossRefGoogle Scholar
  45. 45.
    Vu N, Manjunath BS: Shape prior segmentation of multiple objects with graph cuts. in CVPR 2008Google Scholar
  46. 46.
    Chittajallu DR, Shah SK, Kakadiaris IA: A shape driven MRF model for the segmentation of organs in medical images. In: CVPR, 2010, pp 3233–3240Google Scholar
  47. 47.
    Veksler O: Star shape prior for graph cut segmentation. In: ECCV, 2008, pp 454–467Google Scholar
  48. 48.
    Zhu-Jacquot J, Zabih R: Segmentation of the left ventricle in cardiac mr images using graph cuts with parametric shape priors. In: ICASSP, 2008, pp 521–524Google Scholar
  49. 49.
    Ben Ayed I, Punithakumar K, Li S et al: Left ventricle segmentation via graph cut distribution matching. In: MICCAI 2009, pp 901–909Google Scholar
  50. 50.
    Ali AM, Farag AA, El-Baz AS: Graph cuts framework for kidney segmentation with prior shape constraints. In: MICCAI 2007Google Scholar
  51. 51.
    Mahapatra D, Sun Y: Registration of dynamic renal mr images using neurobiological model of saliency. In: Proc. ISBI, 2008, pp 1119–1122Google Scholar
  52. 52.
    Belongie S, Malik J, Puzicha J: Shape matching and object recognition using shape contexts. IEEE PAMI 24(24):509–522, 2002CrossRefGoogle Scholar
  53. 53.
    Chalana V, Kim Y: A methodology for evaluation of boundary detection algorithms on medical images. IEEE Trans Med Imag 16(5):642–652, 1997CrossRefGoogle Scholar
  54. 54.
    Huttenlocher DP, Klanderman GA, Rucklidge WJ: Comparing images using the Hausdorff distance. IEEE Trans Pattern Anal Machine Intell 15(9):850–863, 1993CrossRefGoogle Scholar
  55. 55.
    Fonseca CG: The cardiac atlas project an imaging database for computational modeling and statistical atlases of the heart. Bioinformatics 27(16):2288–2295, 2011PubMedCrossRefGoogle Scholar
  56. 56.
    Kadish AH, Bello D, Finn JP, Bonow RO, Schaechte A, Subacius H, Albert C, Daubert JP, Fonseca CG, Goldberger JJ: Rationale and design for the defribrillators to reduce risk by magnetic resonance imaging evaluation (determine) trial. J Cardiovascular Electrophysiology 20(9):982–987, 2009CrossRefGoogle Scholar
  57. 57.
    Elen A, Hermans J, Ganame J, Loeckx D, Bogaert J, Maes F, Suetens P: Automatic 3-D breath-hold related motion correction of dynamic multislice MRI. IEEE Trans Med Imag 29(3):868–878, 2010CrossRefGoogle Scholar
  58. 58.
    Young AA, Cowan BR, Thrupp SF, Hedley WJ, DellItalia LJ: Left ventricular mass and volume: fast calculation with guide-point modeling on MR images. Radiology 202(2):597–602, 2000Google Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2013

Authors and Affiliations

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

Personalised recommendations