Video-Instrument Synergistic Network for Referring Video Instrument Segmentation in Robotic Surgery
This work addresses the need for interactive and targeted instrument segmentation in robotic surgery, enabling better surgical robot navigation and education, though it is incremental by building on existing segmentation methods with a novel multimodal approach.
The paper tackles the problem of segmenting specific surgical instruments in robot-assisted surgery videos based on language expressions, introducing a new task called Referring Surgical Video Instrument Segmentation (RSVIS) and a Video-Instrument Synergistic Network (VIS-Net) that outperforms existing state-of-the-art methods.
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.