A Dynamic System for Tracking Biopsy Needle in Two Dimensional Ultrasound Images

Abstract

Ultrasound imaging is widely used to track needle insertion during biopsy surgical procedures. However, the task of tracking the needle tip in ultrasound images is a challenging task that depends on the experience of the physician. To address this limitation, we present different tracking algorithms based on the Kalman filter and particle filter to achieve effective needle tip tracking during biopsy needle insertion procedures. The results showed that the Kalman filter can achieve effective needle tip tracking with an average ± standard deviation error of 1.46 ± 0.92 mm. In comparison, the particle filter can track the needle tip with an average ± standard deviation error of 1.17 ± 0.88 mm when the number of particles is set to 3000.