Classification of Myocardial Infarcted Patients by Combining Shape and Motion Features

  • Wenjia BaiEmail author
  • Ozan Oktay
  • Daniel Rueckert
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9534)


Myocardial infarction changes both the shape and motion of the heart. In this work, cardiac shape and motion features are extracted from shape models at ED and ES phases and combined to train a SVM classifier between myocardial infarcted cases and asymptomatic cases. Shape features are characterised by PCA coefficients of a shape model, whereas motion features include wall thickening and wall motion. Evaluated on the STACOM 2015 challenge dataset, the proposed method achieves a high accuracy of 97.5 % for classification, which shows that shape and motion features can be useful biomarkers for myocardial infarction, which provide complementary information to late-gadolinium MR assessment.


Support Vector Machine Classifier Motion Feature Shape Model Statistical Shape Modelling Abnormality Detection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Sutton, M.G.S.J., Sharpe, N.: Left ventricular remodeling after myocardial infarction pathophysiology and therapy. Circulation 101(25), 2981–2988 (2000)CrossRefGoogle Scholar
  2. 2.
    Mandapaka, S., DAgostino, R., Hundley, W.G.: Does late gadolinium enhancement predict cardiac events in patients with ischemic cardiomyopathy? Circulation 113(23), 2676–2678 (2006)CrossRefGoogle Scholar
  3. 3.
    Medrano-Gracia, P., Cowan, B.R., Bluemke, D.A., Finn, J.P., Kadish, A.H., Lee, D.C., Lima, J.A.C., Suinesiaputra, A., Young, A.A.: Atlas-based analysis of cardiac shape and function: correction of regional shape bias due to imaging protocol for population studies. J. Cardiovasc. Magn. Reson. 15, 80 (2013)CrossRefGoogle Scholar
  4. 4.
    Perperidis, D., Mohiaddin, R.H., Rueckert, D.: Construction of a 4D statistical atlas of the cardiac anatomy and its use in classification. In: Duncan, J.S., Gerig, G. (eds.) MICCAI 2005. LNCS, vol. 3750, pp. 402–410. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  5. 5.
    Suinesiaputra, A., Frangi, A.F., Kaandorp, T., Lamb, H.J., Bax, J.J., Reiber, J., Lelieveldt, B.P.F.: Automated detection of regional wall motion abnormalities based on a statistical model applied to multislice short-axis cardiac MR images. IEEE Trans. Med. Imaging 28(4), 595–607 (2009)CrossRefGoogle Scholar
  6. 6.
    Duchateau, N., Giraldeau, G., Gabrielli, L., Fernández-Armenta, J., Penela, D., Evertz, R., Mont, L., Brugada, J., Berruezo, A., Sitges, M., et al.: Quantification of local changes in myocardial motion by diffeomorphic registration via currents: Application to paced hypertrophic obstructive cardiomyopathy in 2D echocardiographic sequences. Med. Image Anal. 19(1), 203–219 (2015)CrossRefGoogle Scholar
  7. 7.
    McLeod, K., Sermesant, M., Beerbaum, P., Pennec, X.: Spatio-temporal tensor decomposition of a polyaffine motion model for a better analysis of pathological left ventricular dynamics. In: MICCAI, pp. 501–508. Springer (2013)Google Scholar
  8. 8.
    Fonseca, C.G., Backhaus, M., Bluemke, D.A., Britten, R.D., Chung, J.D., Cowan, B.R., Dinov, I.D., Finn, J.P., Hunter, P.J., Kadish, A.H.: The cardiac atlas project-an imaging database for computational modeling and statistical atlases of the heart. Bioinformatics 27(16), 2288–2295 (2011)CrossRefGoogle Scholar
  9. 9.
    Young, A.A., Cowan, B.R., Thrupp, S.F., Hedley, W.J., DellItalia, L.J.: Left ventricular mass and volume: fast calculation with guide-point modeling on MR images. Radiology 216(2), 597–602 (2000)CrossRefGoogle Scholar
  10. 10.
    Petitjean, C., Rougon, N., Cluzel, P.: Assessment of myocardial function: a review of quantification methods and results using tagged MRI. J. Cardiovasc. Magn. Reson. 7(2), 501–516 (2005)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Biomedical Image Analysis Group, Department of ComputingImperial College LondonLondonUK

Personalised recommendations