Data-Driven Feature Learning for Myocardial Segmentation of CP-BOLD MRI

  • Anirban Mukhopadhyay
  • Ilkay OksuzEmail author
  • Marco Bevilacqua
  • Rohan Dharmakumar
  • Sotirios A. Tsaftaris
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9126)


Cardiac Phase-resolved Blood Oxygen-Level-Dependent (CP-BOLD) MR is capable of diagnosing an ongoing ischemia by detecting changes in myocardial intensity patterns at rest without any contrast and stress agents. Visualizing and detecting these changes require significant post-processing, including myocardial segmentation for isolating the myocardium. But, changes in myocardial intensity pattern and myocardial shape due to the heart’s motion challenge automated standard CINE MR myocardial segmentation techniques resulting in a significant drop of segmentation accuracy. We hypothesize that the main reason behind this phenomenon is the lack of discernible features. In this paper, a multi scale discriminative dictionary learning approach is proposed for supervised learning and sparse representation of the myocardium, to improve the myocardial feature selection. The technique is validated on a challenging dataset of CP-BOLD MR and standard CINE MR acquired in baseline and ischemic condition across 10 canine subjects. The proposed method significantly outperforms standard cardiac segmentation techniques, including segmentation via registration, level sets and supervised methods for myocardial segmentation.


Dictionary learning CP-BOLD MR CINE MR Segmentation 



This work was supported by the National Institutes of Health under Grant 2R01HL091989-05.


  1. 1.
    Aharon, M., et al.: K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE TSP 54(11), 4311–4322 (2006)Google Scholar
  2. 2.
    Bai, W., et al.: A probabilistic patch-based label fusion model for multi-atlas segmentation with registration refinement: application to cardiac MR images. IEEE TMI 32(7), 1302–1315 (2013)Google Scholar
  3. 3.
    Chan, T.F., et al.: Active contours without edges. IEEE TIP 10(2), 266–277 (2001)zbMATHGoogle Scholar
  4. 4.
    Chang, L.-H., et al.: Achievable angles between two compressed sparse vectors under norm/distance constraints imposed by the restricted isometry property: a plane geometry approach. IEEE T Inf. Theory 59(4), 2059–2081 (2013)CrossRefGoogle Scholar
  5. 5.
    Glocker, B., et al.: Dense image registration through MRFs and efficient linear programming. MIA 12(6), 731–741 (2008)Google Scholar
  6. 6.
    Huang, X., et al.: Contour tracking in echocardiographic sequences via sparse representation and dictionary learning. MIA 18, 253–271 (2014)Google Scholar
  7. 7.
    Li, C., et al.: Distance regularized level set evolution and its application to image segmentation. IEEE TIP 19(12), 3243–3254 (2010)Google Scholar
  8. 8.
    Ramirez, I., et al.: Classification and clustering via dictionary learning with structured incoherence and shared features. In: IEEE CVPR, pp. 3501–3508 (2010)Google Scholar
  9. 9.
    Rusu, C., et al.: Synthetic generation of myocardial bloodoxygen-level-dependent MRI time series via structural sparse decomposition modeling. IEEE TMI 7(33), 1422–1433 (2014)Google Scholar
  10. 10.
    Tavakoli, V., et al.: A survey of shape-based registration and segmentation techniques for cardiac images. CVIU 117, 966–989 (2013)Google Scholar
  11. 11.
    Tong, T., et al.: Segmentation of MR images via discriminative dictionary learning and sparse coding: application to hippocampus labeling. NeuroImage 76, 11–23 (2013)CrossRefGoogle Scholar
  12. 12.
    Tropp, J.A., et al.: Signal recovery from random measurements via orthogonal matching pursuit. IEEE T Inf. Theory 53(12), 4655–4666 (2007)zbMATHMathSciNetCrossRefGoogle Scholar
  13. 13.
    Tsaftaris, S.A., et al.: A dynamic programming solution to tracking and elastically matching left ventricular walls in cardiac CINE MRI. In: IEEE ICIP, pp. 2980–2983 (2008)Google Scholar
  14. 14.
    Tsaftaris, S.A., et al.: Detecting myocardial ischemia at rest with cardiac phaseresolved blood oxygen leveldependent cardiovascular magnetic resonance. Circ.: Cardiovasc. Imaging 6(2), 311–319 (2013)Google Scholar
  15. 15.
    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
  16. 16.
    Wright, J., et al.: Sparse representation for computer vision and pattern recognition. Proc. IEEE 98(6), 1031–1044 (2010)CrossRefGoogle Scholar
  17. 17.
    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
    Email author
  • 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