Evaluation of a new method for automated detection of left ventricular boundaries in time series of magnetic resonance images using an active appearance motion model

The purpose of this study was the evaluation of a computer algorithm for the automated detection of endocardial and epicardial boundaries of the left ventricle in time series of short-axis magnetic resonance images based on an Active Appearance Motion Model (AAMM). In 20 short-axis MR examinations, manual contours were defined in multiple temporal frames (from end-diastole to end-systole) in multiple slices from base to apex. Using a leave-one-out procedure, the image data and contours were used to build 20 different AAMMs giving a statistical description of the ventricular shape, gray value appearance, and cardiac motion patterns in the training set. Automated contour detection was performed by iteratively deforming the AAMM within statistically allowed limits until an optimal match was found between the deformed AAMM and the underlying image data of the left-out subject. Global ventricular function results derived from automatically detected contours were compared with results obtained from manually traced boundaries. The AAMM contour detection method was successful in 17 of 20 studies. The three failures were excluded from further statistical analysis. Automated contour detection resulted in small, but statistically nonsignificant, underestimations of ventricular volumes and mass: differences for end-diastolic volume were 0.3%±12.0%, for end-systolic volume 2.0%±23.4% and for left ventricular myocardial mass 0.73%±14.9% (mean±SID). An excellent agreement was observed in the ejection fraction: difference of 0.1%±6.7%. In conclusion, the presented fully automated contour detection method provides assessment of quantitative global function that is comparable to manual analysis.