Unsupervised Myocardial Segmentation for Cardiac MRI

  • Anirban Mukhopadhyay
  • Ilkay Oksuz
  • Marco Bevilacqua
  • Rohan Dharmakumar
  • Sotirios A. Tsaftaris
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9351)


Though unsupervised segmentation was a de-facto standard for cardiac MRI segmentation early on, recently cardiac MRI segmentation literature has favored fully supervised techniques such as Dictionary Learning and Atlas-based techniques. But, the benefits of unsupervised techniques e.g., no need for large amount of training data and better potential of handling variability in anatomy and image contrast, is more evident with emerging cardiac MR modalities. For example, CP-BOLD is a new MRI technique that has been shown to detect ischemia without any contrast at stress but also at rest conditions. Although CP-BOLD looks similar to standard CINE, changes in myocardial intensity patterns and shape across cardiac phases, due to the heart’s motion, BOLD effect and artifacts affect the underlying mechanisms of fully supervised segmentation techniques resulting in a significant drop in segmentation accuracy. In this paper, we present a fully unsupervised technique for segmenting myocardium from the background in both standard CINE MR and CP-BOLD MR. We combine appearance with motion information (obtained via Optical Flow) in a dictionary learning framework to sparsely represent important features in a low dimensional space and separate myocardium from background accordingly. Our fully automated method learns background-only models and one class classifier provides myocardial segmentation. The advantages of the proposed technique are demonstrated on a dataset containing CP-BOLD MR and standard CINE MR image sequences acquired in baseline and ischemic condition across 10 canine subjects, where our method outperforms state-of-the-art supervised segmentation techniques in CP-BOLD MR and performs at-par for standard CINE MR.


Unsupervised Segmentation Dictionary Learning BOLD CINE MRI 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Aharon, M., et al.: K-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation. TSP 54(11), 4311–4322 (2006)Google Scholar
  2. 2.
    Bai, W., et al.: Multi-atlas segmentation with augmented features for cardiac MR images. MIA, 98–109 (2015)Google Scholar
  3. 3.
    Glocker, B., et al.: Dense image registration through MRFs and efficient linear programming. MIA 12(6), 731–741 (2008)Google Scholar
  4. 4.
    Huang, X., et al.: Contour tracking in echocardiographic sequences via sparse representation and dictionary learning. MIA 18, 253–271 (2014)Google Scholar
  5. 5.
    Jolly, M.-P., Xue, H., Grady, L., Guehring, J.: Combining registration and minimum surfaces for the segmentation of the left ventricle in cardiac cine MR images. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009, Part II. LNCS, vol. 5762, pp. 910–918. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  6. 6.
    Lin, X., Cowan, B.R., Young, A.A.: Automated detection of left ventricle in 4D MR images: Experience from a large study. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 728–735. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  7. 7.
    Liu, C.: Beyond Pixels: Exploring New Representations and Applications for Motion Analysis. Doctoral Thesis MIT (2009)Google Scholar
  8. 8.
    Lynch, M., et al.: Segmentation of the left ventricle of the heart in 3D+t MRI data using an optimised non-rigid temporal model. TMI 27(2), 195–203 (2008)Google Scholar
  9. 9.
    Mukhopadhyay, A., Oksuz, I., Bevilacqua, M., Dharmakumar, R., Tsaftaris, S.A.: Data-driven feature learning for myocardial segmentation of CP-BOLD MRI. In: van Assen, H., Bovendeerd, P., Delhaas, T. (eds.) FIMH 2015. LNCS, vol. 9126, pp. 189–197. Springer, Heidelberg (2015)CrossRefGoogle Scholar
  10. 10.
    Papazoglou, A., et al.: Fast object segmentation in unconstrained video. In: ICCV (2013)Google Scholar
  11. 11.
    Pednekar, A., et al.: Automated left ventricular segmentation in cardiac MRI. TBME 53(7), 1425–1428 (2006)Google Scholar
  12. 12.
    Petitjean, C., et al.: A review of segmentation methods in short axis cardiac MR images. MIA 15(2), 169–184 (2011)Google Scholar
  13. 13.
    Ramirez, I., et al.: Classification and clustering via dictionary learning with structured incoherence and shared features. In: CVPR, pp. 3501–3508 (2010)Google Scholar
  14. 14.
    Rusu, C., et al.: Synthetic generation of myocardial blood-oxygen-level-dependent MRI time series via structural sparse decomposition modeling. TMI, 1422–1433 (2014)Google Scholar
  15. 15.
    Scholkopf, B., et al.: Estimating the support of a high-dimensional distribution. Neural Computation 13(7), 1443–1471 (2001)MathSciNetCrossRefzbMATHGoogle Scholar
  16. 16.
    Tong, T., et al.: Segmentation of MR images via discriminative dictionary learning and sparse coding: Application to hippocampus labeling. NeuroImage, 11–23 (2013)Google Scholar
  17. 17.
    Tropp, J., et al.: Signal recovery from random measurements via orthogonal matching pursuit. T. Inf. Theo. 53(12), 4655–4666 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  18. 18.
    Tsaftaris, S.A., et al.: A dynamic programming solution to tracking and elastically matching left ventricular walls in cardiac CINE MRI. In: ICIP, pp. 2980–2983 (2008)Google Scholar
  19. 19.
    Tsaftaris, S.A., et al.: Detecting Myocardial Ischemia at Rest With Cardiac Phase-Resolved Blood Oxygen Level-Dependent Cardiovascular Magnetic Resonance. Circ. Card. Imag. 6(2), 311–319 (2013)CrossRefGoogle Scholar
  20. 20.
    Vercauteren, T., Pennec, X., Perchant, A., Ayache, N.: Non-parametric diffeomorphic image registration with the demons algorithm. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007, Part II. LNCS, vol. 4792, pp. 319–326. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  21. 21.
    Wright, J., et al.: Sparse representation for computer vision and pattern recognition. Proc. IEEE 98(6), 1031–1044 (2010)CrossRefGoogle Scholar
  22. 22.
    Zhen, X., Wang, Z., Islam, A., Bhaduri, M., Chan, I., Li, S.: Direct estimation of cardiac Bi-ventricular volumes with regression forests. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014, Part II. LNCS, vol. 8674, pp. 586–593. Springer, Heidelberg (2014)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Anirban Mukhopadhyay
    • 1
  • Ilkay Oksuz
    • 1
  • Marco Bevilacqua
    • 1
  • Rohan Dharmakumar
    • 2
  • Sotirios A. Tsaftaris
    • 1
    • 3
  1. 1.IMT Institute for Advanced Studies LuccaLuccaItaly
  2. 2.Biomedical Imaging Research InstituteCedars-Sinai MedicalLos AngelesUSA
  3. 3.Department of Electrical Engineering and Computer ScienceNorthwestern UniversityEvanstonUSA

Personalised recommendations