Multi-compartment heart segmentation in CT angiography using a spatially varying gaussian classifier

  • S. MurphyEmail author
  • A. Akinyemi
  • J. Steel
  • Y. Petillot
  • I. Poole
Original Article



A fully automated and efficient method for segmenting ten major structures within the heart in Cardiac CT Angiography data for the purposes of display or cardiac functional analysis.

Materials and methods

A spatially varying Gaussian classifier is a flexible model for segmentation, combining the advantages of atlas-based frameworks, with supervised intensity models. It is composed of an independent Gaussian classifier at each voxel and uses non-rigid registration for the initial spatial alignment. We show how this large model can be trained efficiently and present a novel smoothing technique based on normalised convolution to mitigate inherent overfitting issues. The 30 datasets used in this study are selected from a variety of different scanners in order to test the robustness and stability of the algorithm. The datasets were manually segmented by a trained clinician.


The method was evaluated in a leave-one-out fashion, and the results were compared to other state of the art methods in the field, with a mean surface-to-surface distance of between 0.61 and 2.12 mm for different compartments.


The accuracy of this method is comparable to other state of the art methods in the field. Its benefits lie in its conceptual simplicity and its general applicability. Only one non-rigid registration is required, giving it a speed advantage over multi-atlas approaches. Further accuracy may be achievable through the incorporation of an explicit shape model.


Image analysis Computed tomography angiography Atlas-based segmentation Classification Probabilistic modelling 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Fritz D, Daniel R, Unterhinninghofen R, Dillmann R, Scheuering M (2005) Automatic segmentation of the left ventricle and computation of diagnostic parameters using region growing and a statistical model. In Proc. SPIE, 5747: 1844–1854 CiteseerCrossRefGoogle Scholar
  2. 2.
    Cootes TF, Hill A, Taylor CJ, Haslam J (1994) The use of active shape models for locating structures in medical images. Distribution 12(6): 355–366Google Scholar
  3. 3.
    Cootes TF, Edwards GJ, Taylor CJ (2001) Active appearance models. IEEE Trans Pattern Anal Mach Intell 23(6): 681–685CrossRefGoogle Scholar
  4. 4.
    Stegmann MB (2005) Bi-temporal 3D active appearance models with applications to unsupervised ejection fraction estimation. In: Proceedings of SPIE, vol 5747, pp 336–350. SPIE, 2005Google Scholar
  5. 5.
    Mitchell SC, Lelieveldt BP, van der Geest RJ, Bosch HG, Reiber JH, Sonka M (2001) Multistage hybrid active appearance model matching: segmentation of left and right ventricles in cardiac MR images. IEEE Trans Med Imaging 20(5): 415–423PubMedCrossRefGoogle Scholar
  6. 6.
    McInerney T, Terzopoulos D (1996) Deformable models in medical image analysis: a survey. Med Image Anal 1(2): 91–108PubMedCrossRefGoogle Scholar
  7. 7.
    McInerney T, Terzopoulos D (1994) A dynamic finite element surface model for segmentation and tracking in multidimensional medical images with application to cardiac 4D image analysis. Comput Med Imaging Graph Off J Comput Med Imaging Soc 19(1): 69–83CrossRefGoogle Scholar
  8. 8.
    Ecabert O, Peters J, Schramm H, Lorenz C, von Berg J, Walker MJ, Vembar M, Olszewski ME, Subramanyan K, Lavi G, Weese J (2008) Automatic model-based segmentation of the heart in CT images. IEEE Trans Med Imaging 27(9): 1189–1201PubMedCrossRefGoogle Scholar
  9. 9.
    Ecabert O, Peters J, Walker MJ, Ivanc T, Lorenz C, von Berg J, Lessick J, Vembar M, Weese J (2011) Segmentation of the heart and great vessels in CT images using a model-based adaptation framework. Med Image Anal 15(6): 863–876PubMedCrossRefGoogle Scholar
  10. 10.
    Zheng Y, Barbu A, Georgescu B, Scheuering M, Comaniciu D (2008) Four-chamber heart modeling and automatic segmentation for 3-D cardiac CT volumes using marginal space learning and steerable features. IEEE Trans Med Imaging 27(11): 1668–1681PubMedCrossRefGoogle Scholar
  11. 11.
    Lorenzo-Valdés M, Sanchez-Ortiz G, Mohiaddin R, Rueckert D (2002) Atlas-based segmentation and tracking of 3D cardiac MR images using non-rigid registration. In: Dohi T, Kikinis R (eds) Medical image computing and computer-assisted intervention–MICCAI 2002. Lecture notes in computer science, vol 2488. Springer-Verlag, Berlin Heidelberg, pp 642–650Google Scholar
  12. 12.
    Lorenzo-Valdez M, Sanchez-Ortiz G, Elkington AG, Mohiaddin RH, Rueckert D (2004) Segmentation of 4D cardiac MR images using a probabilistic atlas and the EM algorithm. Med Image Anal 8: 255–265CrossRefGoogle Scholar
  13. 13.
    Kirisli HA, Schaap M, Klein S, Papadopoulou SL, Bonardi M, Chen CH, Weustink AC, Mollet NR, Vonken EJ, van der Geest RJ, vanWalsum T, Niessen WJ (2010) Evaluation of a multi-atlas-based method for segmentation of cardiac CTA data: a large-scale, multicenter, and multivendor study. Med Phys 37(12): 6279PubMedCrossRefGoogle Scholar
  14. 14.
    Warfield SK, Zou KH, Wells WM (2004) Simultaneous truth and performance level estimation (STAPLE): an algorithm for the validation of image segmentation. IEEE Trans Med Imaging 23(7): 903–921PubMedCrossRefGoogle Scholar
  15. 15.
    Depa M, Holmvang G, Schmidt EJ, Golland P, Sabuncu MR (2011) Towards efficient label fusion by pre-alignment of training data. MICCAI 2011 workshop on multi-atlas labeling and statistical fusion, pp 1–9Google Scholar
  16. 16.
    Fischl B, Salat DH, Busa E, Albert M, Dieterich M, Haselgrove C, van der Kouwe A, Killiany R, Kennedy D, Klaveness S, Montillo A, Makris N, Rosen B, Dale AM (2002) Whole brain segmentation: automated labeling of neuroanatomical structures in the human brain. Neuron 33(3): 341–355PubMedCrossRefGoogle Scholar
  17. 17.
    Knutsson H, Westin CF (1993) Normalised and differential convolution: methods for interpolation and filtering of incomplete and uncertain data. In: Proceedings of computer vision and pattern recognition, New York City, USA, IEEEGoogle Scholar
  18. 18.
    Gelman A (2006) Prior distributions for variance parameters in hierarchical models. Bayesian Anal 34(3): 377–390Google Scholar
  19. 19.
    Powell MJD (1964) An efficient method for finding the minimum of a function of several variables without calculating derivatives. Comput J 7(2): 155CrossRefGoogle Scholar
  20. 20.
    Crum WR, Griffin LD, Hawkes DJ (2003) Zen and the art of medical image registration: correspondence, homology, and quality. In Pract 20: 1425–1437Google Scholar

Copyright information

© CARS 2012

Authors and Affiliations

  • S. Murphy
    • 1
    Email author
  • A. Akinyemi
    • 1
  • J. Steel
    • 1
  • Y. Petillot
    • 2
  • I. Poole
    • 1
  1. 1.Toshiba Medical Visualization Systems EuropeEdinburghUK
  2. 2.Heriot-Watt UniversityEdinburghUK

Personalised recommendations