Improved automatic left ventricular border detection in cineangiograms using dynamic spider models

Dynamic spider models were used for automated left ventricular border detection in biplane angiograms. The model consists of a set of medial involution chords of a confined region which encompasses the contraction area of a left ventricular silhouette. To identify a left ventricular silhouette is to find a congruence transformation so that a deformity measure between the mapped model and an image is minimized. The left ventricular border can then be determined within the aligned confined region of the model. The current algorithm is simpler, faster, and more robust than previously reported solutions. Clinical evaluation in 50 patients has shown distinct improvements. The accuracy rate in model registration was 93% versus 80%, and in border determination 74% versus 70%