Inferring transducer viewpoints in cardiac echo videos

Abstract

During a 2D echo exam, the transducer position is varied to elicit important information about the heart function and its anatomy. Knowledge of the transducer viewpoint is important in automatic cardiac echo interpretation to understand the regions being depicted as well as in the quantification of their attributes. In this paper, we address the problem of inferring the transducer viewpoint from the spatio-temporal information in cardiac echo videos. Unlike previous approaches, we exploit motion of the heart within a cardiac cycle in addition to spatial information to discriminate between viewpoints. Specifically, we use an active shape model (ASM) to model cardiac appearance in an echo frame, and cardiac motion is modeled using eigen-motions of ASM feature tracks. We test our method on 2 data sets of patients with various cardiac diseases, and we report comparison with re-implementations of two state-of-the-art view recognition methods.