Visual-Kinematics Graph Learning for Procedure-agnostic Instrument Tip Segmentation in Robotic Surgeries

TL;DR

This paper introduces a multi-modal graph learning framework combining visual and kinematic data to improve the robustness and accuracy of surgical instrument tip segmentation across various procedures in robotic surgery.

Contribution

It proposes a novel graph learning approach with cross-modal contrastive loss to leverage kinematic priors for enhanced segmentation performance.

Findings

Outperforms state-of-the-art image-based methods by 11.2% on Dice score.

Demonstrates robustness across multiple surgical procedures.

Effective use of multi-modal data for surgical instrument segmentation.

Abstract

Accurate segmentation of surgical instrument tip is an important task for enabling downstream applications in robotic surgery, such as surgical skill assessment, tool-tissue interaction and deformation modeling, as well as surgical autonomy. However, this task is very challenging due to the small sizes of surgical instrument tips, and significant variance of surgical scenes across different procedures. Although much effort has been made on visual-based methods, existing segmentation models still suffer from low robustness thus not usable in practice. Fortunately, kinematics data from the robotic system can provide reliable prior for instrument location, which is consistent regardless of different surgery types. To make use of such multi-modal information, we propose a novel visual-kinematics graph learning framework to accurately segment the instrument tip given various surgical procedures. Specifically, a graph learning framework is proposed to encode relational features of instrument parts from both image and kinematics. Next, a cross-modal contrastive loss is designed to incorporate robust geometric prior from kinematics to image for tip segmentation. We have conducted experiments on a private paired visual-kinematics dataset including multiple procedures, i.e., prostatectomy, total mesorectal excision, fundoplication and distal gastrectomy on cadaver, and distal gastrectomy on porcine. The leave-one-procedure-out cross validation demonstrated that our proposed multi-modal segmentation method significantly outperformed current image-based state-of-the-art approaches, exceeding averagely 11.2% on Dice.