Detecting Regional Abnormal Cardiac Contraction in Short-Axis MR Images Using Independent Component Analysis
Regional myocardial motion analysis is used in clinical routine to inspect cardiac contraction in myocardial diseases such as infarction or hypertrophy. Physicians/radiologists can recognize abnormal cardiac motion because they have knowledge about normal heart contraction. This paper explores the potential of Independent Component Analysis (ICA) to extract local myocardial contractility patterns and to use them for the automatic detection of regional abnormalities. A qualitative evaluation was performed using 42 healthy volunteers to train the ICA model and 6 infarct patients to test the detection and localization. This experiment shows that the evaluation results correlate very well to the clinical gold standard: delayed-enhancement MR images.
KeywordsIndependent Component Analysis Shape Variation Independent Component Analysis Cardiac Contraction Shape Vector
- 4.Üzümcü, M., Frangi, A.F., Reiber, J.H., Lelieveldt, B.P.: Independent Component Analysis in Statistical Shape Models. In: Sonka, M., Fitzpatrick, J.M. (eds.) Proc. of SPIE, vol. 5032, pp. 375–383 (2003)Google Scholar
- 5.Hyvärinen, A.: Survey on Independent Component Analysis. Neural Computing Surveys 2, 94–128 (1999)Google Scholar
- 6.Dryden, I.L., Mardia, K.V.: Statistical Shape Analysis. John Wiley & Sons, Chichester (2002)Google Scholar
- 8.Hyvärinen, A., Särelä, J., Vígario, R.: Bumps and Spikes: Artifacts Generated by Independent Component Analysis with Insufficient Sample Size. In: Proc. Int. Workshop on ICA and BSS, pp. 425–249 (1999)Google Scholar
- 9.Cardoso, J., Souloumiac, A.: Blind Beamforming for Non Gaussian Signals. IEEE Proceedings -F 140, 362–370 (1993)Google Scholar