Feature Drift Resilient Tracking of The Carotid Artery Wall Using Unscented Kalman Filtering With Data Fusion

An analysis of the motion of the common carotid artery (CCA) provides effective indicators for cardiovascular diseases. Here, we propose a method for tracking CCA wall motion from a B-mode ultrasound video sequence. An unscented Kalman filter based on a suitably devised state-space model fuses measurements produced by an optical flow algorithm and a CCA wall localization algorithm. This approach compensates for feature drift, which is a detrimental effect in optical flow algorithms. The proposed method is demonstrated to outperform a state-of-the-art tracking method based on optical flow.