CONSTRAINED DETECTION OF LEFT-VENTRICULAR BOUNDARIES FROM CINE CT IMAGES OF HUMAN HEARTS

Detection of the left ventricular (LV) endocardial (inner) and epicardial (outer) boundaries in cardiac images, provided by fast computer tomography (Cine CT), magnetic resonance (MR), or ultrasound (echocardiography), is essential for the quantitative analysis of cardiac function. Manual tracing of the boundaries, which is presently used for subsequent analysis and diagnostics, is time consuming; this seriously limits the three-dimensional (3-D) spatial reconstruction of the LV shape and the clinical interpretation and utilization of the dynamical nature of the cardiac data. The automatic detection of the LV boundaries is difficult due to background noise, poor contrast, and often-unclear differentiation of the tissue characteristics of the ventricles, papillary muscles, and surrounding tissues. Our new approach to the automatic ventricular boundary detection employs set-theoretic techniques, and is based on incorporating a priori knowledge of the heart geometry, its brightness, spatial structure, and temporal dynamics into the boundaries detection algorithm. Available knowledge is interpreted as constraint sets in the functional space and the consistent boundaries are considered to belong to the intersection of all the introduced sets, thus satisfying the a priori information. A novel algorithm is also suggested for the simultaneous detection of the endocardial and epicardial boundaries of the LV. The procedure is demonstrated using Cine CT images of the human heart.