Task-Oriented Network Design for Visual Tracking and Motion Filtering of Needle Tip Under 2D Ultrasound

Abstract

Needle tip tracking under ultrasound (US) imaging is critical for accurate lesion targeting in US-guided percutaneous procedures. While most state-of-the-art trackers have relied on complex network architecture for enhanced performance, the compromised computational efficiency prevents their real-time implementation. Pure visual trackers are also limited in addressing the drift errors caused by temporary needle tip disappearance. In this paper, a compact, task-oriented visual tracker, consisting of an appearance adaptation module and a distractor suppression module, is first designed before it is integrated with a motion filter, namely TransKalman, that leverages the Transformer network for Kalman filter gain estimation. The ablation study shows that the mean tracking success rate (i.e. error <3mm in 95% video frames) of the visual tracker increases by 25% compared with its baseline model. The complete tracking system, integrating the visual tracker and TransKalman, outperforms other existing trackers by at least 5.1% in success rate and 47% in tracking speed during manual needle manipulation experiments in ex-vivo tissue. The proposed real-time tracking system will potentially be integrated in both manual and robotic procedures to reduce operator dependence and improve targeting accuracy during needle-based diagnostic and therapeutic procedures.