Self-Supervised Learning for Interactive Perception of Surgical Thread for Autonomous Suture Tail-Shortening

TL;DR

This paper introduces a robust 3D surgical thread tracking method using stereo vision and deep learning, enabling autonomous tail-shortening in suturing with high accuracy and success rate.

Contribution

A novel stereo vision-based 3D thread reconstruction and tracking approach that is robust to occlusions and complex configurations for autonomous surgical suturing tasks.

Findings

Achieves 1.33 pixel average reprojection error in 3D thread reconstruction.

Attains 90% success rate in autonomous tail-shortening task.

Demonstrates robustness to occlusions and complex thread configurations.

Abstract

Accurate 3D sensing of suturing thread is a challenging problem in automated surgical suturing because of the high state-space complexity, thinness and deformability of the thread, and possibility of occlusion by the grippers and tissue. In this work we present a method for tracking surgical thread in 3D which is robust to occlusions and complex thread configurations, and apply it to autonomously perform the surgical suture "tail-shortening" task: pulling thread through tissue until a desired "tail" length remains exposed. The method utilizes a learned 2D surgical thread detection network to segment suturing thread in RGB images. It then identifies the thread path in 2D and reconstructs the thread in 3D as a NURBS spline by triangulating the detections from two stereo cameras. Once a 3D thread model is initialized, the method tracks the thread across subsequent frames. Experiments suggest the method achieves a 1.33 pixel average reprojection error on challenging single-frame 3D thread reconstructions, and an 0.84 pixel average reprojection error on two tracking sequences. On the tail-shortening task, it accomplishes a 90% success rate across 20 trials. Supplemental materials are available at https://sites.google.com/berkeley.edu/autolab-surgical-thread/ .