Automatic 3D left ventricular border detection using active appearance models

Abstract

A fully automated segmentation for 3D echocardiography (3DE) using 3D Active Appearance Models (AAM) was developed and evaluated on end-diastolic (ED) and end-systolic (ES) images of 99 patients. The method used ultrasound specific grey value normalization and employed both regular matching and jacobian tuning. The 3D AAM detected the endocardial contours accurately, even in the presence of large variations in left ventricular appearance and shape. Matching was successful in 87% of patients and resulted in good median point-to-surface errors of 2.65 mm for ED and 3.21 for ES, and good volume regressions (ED: y = −3.2 +1.01×, r=0.95; ES: y = −4.6 +1.01×, r=0.92). Results show that fully automated AAM analysis is practically feasible in 3DE datasets of mixed origin and quality.