Direct Estimation of Cardiac Biventricular Volumes With an Adapted Bayesian Formulation

Abstract

Accurate estimation of the ventricular volumes is essential to the assessment of global cardiac functions. The existing estimation methods are mostly restricted to the left ventricle (LV), and often require segmentation which is challenging and computationally expensive. This paper proposes to estimate the volumes of both LV and right ventricle (RV) jointly with an efficient segmentation-free method. The proposed method employs an adapted Bayesian formulation. It introduces a novel likelihood function to exploit multiple appearance features, and a novel prior probability model to incorporate the area correlation between LV and RV cavities. The method is validated on a comprehensive dataset containing 56 clinical subjects (3360 images in total). The experimental results demonstrate that the estimated biventricular volumes are highly correlated to their independent ground truth. As a result, the proposed method enables a direct, efficient, and accurate assessment of global cardiac functions.