We developed a method for automated quantification of myocardial perfusion from cardiac magnetic resonance (CMR) images. Our approach uses region-based and edge-based level set techniques for endocardial and epicardial border detection combined with non-rigid registration achieved by a 2D multi-scale cross-correlation and contour adaptation. This method was tested on 66 short-axis image sequences (Philips 1.5T) obtained in 11 patients at rest and during vasodilator stress at 3 levels of the left ventricle during first pass of a Gadolinium-DTPA bolus. Myocardial ROIs were automatically defined and contrast enhancement curves were constructed throughout the image sequence. Analysis of one sequence required <;1 min and resulted in endo- and epicardial boundaries that were judged accurate. Curves obtained during stress showed the typical pattern of first-pass perfusion with SNR of 19±4, as well as increased contrast inflow rate (0.031±0.013 vs 0.014±0.004 sec-1) and higher peak-to-peak amplitude (0.20±0.05 vs 0.14±0.03) compared to resting curves. Despite the extreme dynamic nature of contrast enhanced image sequences and respiratory motion, fast automated detection of myocardial segments and quantification of tissue contrast results in time curves with excellent noise levels, which reflect the expected effects of stress.