LAUSR

Ultrasound (US) is commonly used in percutaneous needle procedures for real-time guidance. Accurate and robust automatic needle tracking is highly desirable to address the influence of noise and artifacts in US images. This letter presents a tracking approach which combines an improved compressive tracking (ICT) algorithm and a modified Sage-Husa adaptive Kalman filter (SHAKF) to achieve real-time needle tip tracking under 2D US. Estimated needle insertion velocity is used to improve the tracking performance while the high US pixel intensity of the needle tip is used to correct drift. A simplified SHAKF is then implemented to adaptively estimate the statistical characteristics of the noise in the compressive tracking results. An innovation threshold is proposed to improve the response speed of the filter while a normalized cross correlation based method is used to improve the tracking robustness. The proposed tracking approach has been evaluated in in-plane and out-of-plane motions under different insertion speeds and angles in both phantom and tissue experiments. Compared with the original compressive tracking, ICT+Kalman filter, and the template matching algorithm, our proposed approach demonstrates highly accurate tracking performance and high robustness in all cases.