AUTOMATED MYOCARDIAL EDGE-DETECTION ON MR-IMAGES - ACCURACY IN CONSECUTIVE SUBJECTS

The authors previously demonstrated the feasibility of graph-searching -based automated edge detection in cardiac magnetic resonance (MR) ima ging. To further assess the clinical utility of this method, unselecte d images from 11 consecutive subjects undergoing clinically indicated (except for one healthy volunteer) short-axis spin-echo MR imaging wer e analyzed. A total of 142 images from the 11 subjects, encompassing t he left ventricle from apex to outflow tract, were analyzed. The compu ter algorithm correctly identified complete endocardial and epicardial contours in 121 of 142 images (85%). Correlations between observer-tr aced and computer-derived epicardial areas for all images were good (r = .71 for epicardium, r = .83 for endocardium); they improved for a s ubset of higher-quality images (r = .82 for epicardium, r = .92 for en docardium). The authors conclude that the current data further support the usefulness of computer digital image processing in geometric anal ysis of cardiac MR image data.