Video-Instrument Synergistic Network for Referring Video Instrument Segmentation in Robotic Surgery

TL;DR

This paper introduces a novel network for referring surgical video instrument segmentation, leveraging video and language cues to improve accuracy and enable interactive, targeted segmentation in robotic surgery.

Contribution

It proposes the VIS-Net model that learns both video-level and instrument-level features, and introduces a graph-based module for multi-modal correlation, along with two new datasets for the task.

Findings

VIS-Net outperforms existing methods on new datasets

The model effectively integrates video and language information

Experimental results show significant accuracy improvements

Abstract

Robot-assisted surgery has made significant progress, with instrument segmentation being a critical factor in surgical intervention quality. It serves as the building block to facilitate surgical robot navigation and surgical education for the next generation of operating intelligence. Although existing methods have achieved accurate instrument segmentation results, they simultaneously generate segmentation masks for all instruments, without the capability to specify a target object and allow an interactive experience. This work explores a new task of Referring Surgical Video Instrument Segmentation (RSVIS), which aims to automatically identify and segment the corresponding surgical instruments based on the given language expression. To achieve this, we devise a novel Video-Instrument Synergistic Network (VIS-Net) to learn both video-level and instrument-level knowledge to boost performance, while previous work only used video-level information. Meanwhile, we design a Graph-based Relation-aware Module (GRM) to model the correlation between multi-modal information (i.e., textual description and video frame) to facilitate the extraction of instrument-level information. We are also the first to produce two RSVIS datasets to promote related research. Our method is verified on these datasets, and experimental results exhibit that the VIS-Net can significantly outperform existing state-of-the-art referring segmentation methods. Our code and our datasets will be released upon the publication of this work.