Cardiac Motion Scoring with Segment- and Subject-Level Non-local Modeling

  • Wufeng Xue
  • Gary Brahm
  • Stephanie Leung
  • Ogla Shmuilovich
  • Shuo Li
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11071)


Motion scoring of cardiac myocardium is of paramount importance for early detection and diagnosis of various cardiac disease. It aims at identifying regional wall motions into one of the four types including normal, hypokinetic, akinetic, and dyskinetic, and is extremely challenging due to the complex myocardium deformation and subtle inter-class difference of motion patterns. All existing work on automated motion analysis are focused on binary abnormality detection to avoid the much more demanding motion scoring, which is urgently required in real clinical practice yet has never been investigated before. In this work, we propose Cardiac-MOS, the first powerful method for cardiac motion scoring from cardiac MR sequences based on deep convolution neural network. Due to the locality of convolution, the relationship between distant non-local responses of the feature map cannot be explored, which is closely related to motion difference between segments. In Cardiac-MOS, such non-local relationship is modeled with non-local neural network within each segment and across all segments of one subject, i.e., segment- and subject-level non-local modeling, and lead to obvious performance improvement. Besides, Cardiac-MOS can effectively extract motion information from MR sequences of various lengths by interpolating the convolution kernel along the temporal dimension, therefore can be applied to MR sequences of multiple sources. Experiments on 1440 myocardium segments of 90 subjects from short axis MR sequences of multiple lengths prove that Cardiac-MOS achieves reliable performance, with correlation of 0.926 for motion score index estimation and accuracy of 77.4% for motion scoring. Cardiac-MOS also outperforms all existing work for binary abnormality detection. As the first automatic motion scoring solution, Cardiac-MOS demonstrates great potential in future clinical application.


  1. 1.
    Afshin, M., et al.: Regional assessment of cardiac left ventricular myocardial function via MRI statistical features. IEEE TMI 33, 481–494 (2014)Google Scholar
  2. 2.
    Afshin, M., et al.: Assessment of regional myocardial function via statistical features in MR images. In: Fichtinger, G., Martel, A., Peters, T. (eds.) MICCAI 2011. LNCS, vol. 6893, pp. 107–114. Springer, Heidelberg (2011). Scholar
  3. 3.
    Bjørnstad, K., Al Amri, M., Lingamanaicker, J., Oqaili, I., Hatle, L.: Interobserver and intraobserver variation for analysis of left ventricular wall motion at baseline and during low-and high-dose dobutamine stress echocardiography in patients with high prevalence of wall motion abnormalities at rest. J. Am. Soc. Echocardiogr. 9(3), 320–328 (1996)CrossRefGoogle Scholar
  4. 4.
    Lang, R.M., et al.: Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American society of echocardiography and the european association of cardiovascular imaging. Eur. Hear. J. Cardiovasc. Imaging 16(3), 233–271 (2015)CrossRefGoogle Scholar
  5. 5.
    Leung, K.Y.E., Bosch, J.G.: Localized shape variations for classifying wall motion in echocardiograms. In: Ayache, N., Ourselin, S., Maeder, A. (eds.) MICCAI 2007. LNCS, vol. 4791, pp. 52–59. Springer, Heidelberg (2007). Scholar
  6. 6.
    Lu, Y., Radau, P., Connelly, K., Dick, A., Wright, G.: Pattern recognition of abnormal left ventricle wall motion in cardiac MR. In: Yang, G.-Z., Hawkes, D., Rueckert, D., Noble, A., Taylor, C. (eds.) MICCAI 2009. LNCS, vol. 5762, pp. 750–758. Springer, Heidelberg (2009). Scholar
  7. 7.
    Mantilla, J., et al.: Classification of LV wall motion in cardiac MRI using kernel dictionary learning with a parametric approach. In: EMBC, pp. 7292–7295 (2015)Google Scholar
  8. 8.
    Paetsch, I., Jahnke, C., Ferrari, V.A., Rademakers, F.E., Pellikka, P.A., Hundley, W.G.: Determination of interobserver variability for identifying inducible left ventricular wall motion abnormalities during dobutamine stress magnetic resonance imaging. Eur. Hear. J. 27(12), 1459–1464 (2006)CrossRefGoogle Scholar
  9. 9.
    Punithakumar, K., Ayed, I.B., Islam, A., Goela, A., Li, S.: Regional heart motion abnormality detection via multiview fusion. In: Ayache, N., Delingette, H., Golland, P., Mori, K. (eds.) MICCAI 2012. LNCS, vol. 7511, pp. 527–534. Springer, Heidelberg (2012). Scholar
  10. 10.
    Punithakumar, K., et al.: Regional heart motion abnormality detection: an information theoretic approach. Med. Image Anal. 17(3), 311–324 (2013)CrossRefGoogle Scholar
  11. 11.
    Punithakumar, K., Ben Ayed, I., Islam, A., Ross, I.G., Li, S.: Regional heart motion abnormality detection via information measures and unscented Kalman filtering. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6361, pp. 409–417. Springer, Heidelberg (2010). Scholar
  12. 12.
    Punithakumar, K., Ayed, I.B., Ross, I.G., Islam, A., Chong, J., Li, S.: Detection of left ventricular motion abnormality via information measures and bayesian filtering. IEEE Trans. Inf. Technol. Biomed. 14(4), 1106–1113 (2010)CrossRefGoogle Scholar
  13. 13.
    Qian, Z., Liu, Q., Metaxas, D.N., Axel, L.: Identifying Regional cardiac abnormalities from myocardial strains using spatio-temporal tensor analysis. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008. LNCS, vol. 5241, pp. 789–797. Springer, Heidelberg (2008). Scholar
  14. 14.
    Qian, Z., Liu, Q., Metaxas, D.N., Axel, L.: Identifying regional cardiac abnormalities from myocardial strains using nontracking-based strain estimation and spatio-temporal tensor analysis. IEEE TMI 30(12), 2017–2029 (2011)Google Scholar
  15. 15.
    Suinesiaputra, A., et al.: Automated detection of regional wall motion abnormalities based on a statistical model applied to multislice short-axis cardiac MR images. IEEE TMI 28(4), 595–607 (2009)Google Scholar
  16. 16.
    Viera, A.J., Garrett, J.M.: Understanding interobserver agreement: the kappa statistic. Fam Med 37(5), 360–363 (2005)Google Scholar
  17. 17.
    Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. arXiv preprint arXiv:1711.07971 (2017)

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Wufeng Xue
    • 1
    • 2
  • Gary Brahm
    • 1
  • Stephanie Leung
    • 1
  • Ogla Shmuilovich
    • 1
  • Shuo Li
    • 1
  1. 1.Department of Medical ImagingWestern UniversityLondonCanada
  2. 2.National-Regional Key Technology Engineering Laboratory for Medical Ultrasound, School of Biomedical Engineering, Health Science CenterShenzhen UniversityShenzhenChina

Personalised recommendations