Rationale and objectives: Gated cardiac cine magnetic resonance imaging provides accurate dynamic data of the left ventricular function. However, the manual extraction of important physiologic parameters such as myocardium wall thickness and left ventricular volumes is invariably time consuming and subjective. To reduce the variability and time constraints inherent in observer contour tracing, the authors developed an automatic left ventricle contour-detection method.
Methods: The purpose was to apply fuzzy logic-based automatic contour detection to identification of endocardial and epicardial borders in short-axis magnetic resonance images. The automatic contouring was compared with manual tracing using the calculated ejection fraction as the comparison criterion.
Results: A good correlation was found between the two approaches (r2 = 0.98).
Conclusions: The ejection fraction can be obtained using this automatic contouring method.