Tracking Any Point Methods for Markerless 3D Tissue Tracking in Endoscopic Stereo Images

TL;DR

This paper introduces a novel markerless 3D tissue tracking method using 2D Tracking Any Point networks, demonstrating accurate tracking in endoscopic stereo images for surgical guidance and robotic assistance.

Contribution

The work combines two CoTracker models for temporal and stereo tracking to achieve markerless 3D tissue motion estimation in endoscopic images, a novel application of TAP networks.

Findings

Achieved Euclidean distance errors as low as 1.1 mm on chicken tissue phantom.

Demonstrated reliable tracking at tissue velocities up to 10 mm/s.

Validated the method in a clinical laparoscopic setup with synthetic and biological phantoms.

Abstract

Minimally invasive surgery presents challenges such as dynamic tissue motion and a limited field of view. Accurate tissue tracking has the potential to support surgical guidance, improve safety by helping avoid damage to sensitive structures, and enable context-aware robotic assistance during complex procedures. In this work, we propose a novel method for markerless 3D tissue tracking by leveraging 2D Tracking Any Point (TAP) networks. Our method combines two CoTracker models, one for temporal tracking and one for stereo matching, to estimate 3D motion from stereo endoscopic images. We evaluate the system using a clinical laparoscopic setup and a robotic arm simulating tissue motion, with experiments conducted on a synthetic 3D-printed phantom and a chicken tissue phantom. Tracking on the chicken tissue phantom yielded more reliable results, with Euclidean distance errors as low as 1.1 mm at a velocity of 10 mm/s. These findings highlight the potential of TAP-based models for accurate, markerless 3D tracking in challenging surgical scenarios.