Automatic Prediction of Myocardial Contractility Improvement in Stress MRI Using Shape Morphometrics with Independent Component Analysis ⋆ A. Suinesiaputra 1 , A.F. Frangi 2 , H.J. Lamb 1 , J.H.C. Reiber 1 , B.P.F. Lelieveldt 1 1 Department of Radiology, Leiden University Medical Center, Leiden, the Netherlands 2 Computational Imaging Lab, Dept. of Technology, Pompeu Fabra University, Barcelona, Spain Abstract. An important assessment in patients with ischemic heart dis- ease is whether myocardial contractility may improve after treatment. The prediction of myocardial contractility improvement is generally per- formed under physical or pharmalogical stress conditions. In this paper, we present a technique to build a statistical model of healthy myocardial contraction using independent component analysis. The model is used to detect regions with abnormal contraction in patients both during rest and stress. 1 Introduction Ischemic heart disease is a major heart disease in the western world. Non-invasive diagnosis of ischemia has been developed in recent years (see [1] for the survey of different imaging techniques). Among others, Magnetic Resonance Imaging (MRI) has attracted many clinicians due to its excellent spatial and temporal resolution, high-contrast of soft tissue, accurate and reproducible global and regional ventricular function, flow and perfusion during rest and pharmacological stress, and the possibility of using paramagnetic contrast agent to enhance the intensity of myocardial infarction areas [2, 3]. One crucial assessment in ischemic heart disease is to determine whether hibernating or stunning myocardium occurs. This is viable but dysfunctional myocardium, which may improve its function after treatment [1]. The prediction of improvement of myocardial contraction is only possible during physical or ⋆ This work is supported by the Dutch Science Foundation (NWO), under an inno- vational research incentive grant, vernieuwingsimpuls 2001. This work was also sup- ported in part by a grant from Fundaci´on MAPFRE Medicina and grants TIC2002- 04495-C02 from the MEyC, and FIS-PI040676 and G03/185 from ISCIII. The work of A.F. Frangi was supported in part by a Ramon y Cajal Research Fellowship from the Spanish MEyC.