Heart Motion Abnormality Detection via an Information Measure and Bayesian Filtering

摘要: This study investigates heart wall motion abnormality detection with an information theoretic measure of based on the Shannon's differential entropy (SDE) and recursive Bayesian filtering. Heart is generally analyzed using functional images which are subject to noise segmentation inaccuracies, incorporation prior knowledge crucial in improving accuracy. The Kalman filter, a well known used this estimate left ventricular (LV) cavity points given incomplete noisy data, dynamic model. However, due similarities between statistical normal abnormal motions, detecting classifying challenging problem we proposed investigate global SDE. We further derive two other possible criteria, one Renyi Fisher information. method analyzes quantitatively by constructing distributions normalized radial distance estimates LV cavity. Using 269×20 segmented cavities short-axis magnetic resonance obtained from 30 subjects, experimental analysis demonstrates that SDE criterion can lead significant improvement over features prevalent literature related cavity, namely, mean displacement velocity.