Instrument-tissue Interaction Quintuple Detection in Surgery Videos

Abstract

Instrument-tissue interaction detection task, which helps understand surgical activities, is vital for constructing computer-assisted surgery systems but with many challenges. Firstly, most models represent instrument-tissue interaction in a coarse-grained way which only focuses on classification and lacks the ability to automatically detect instruments and tissues. Secondly, existing works do not fully consider relations between intraand inter-frame of instruments and tissues. In the paper, we propose to represent instrument-tissue interaction as ⟨instrument class, instrument bounding box, tissue class, tissue bounding box, action class⟩ quintuple and present an Instrument-Tissue Interaction Detection Network (ITID-Net) to detect the quintuple for surgery videos understanding. Specifically, we propose a Snippet Consecutive Feature (SCF) Layer to enhance features by modeling relationships of proposals in the current frame using global context information in the video snippet. We also propose a Spatial Corresponding Attention (SCA) Layer to incorporate features of proposals between adjacent frames through spatial encoding. To reason relationships between instruments and tissues, a Temporal Graph (TG) Layer is proposed with intra-frame connections to exploit relationships between instruments and tissues in the same frame and inter-frame connections to model the temporal information for the same instance. For evaluation, we build a cataract surgery video (PhacoQ) dataset and a cholecystectomy surgery video (CholecQ) dataset. Experimental results demonstrate the promising performance of our model, which outperforms other state-of-the-art models on both datasets.

CholecTriplet2022: Show me a tool and tell me the triplet - an endoscopic vision challenge for surgical action triplet detection

“…Xu et al (2021) employed a transformer model along with adversarial learning to generate captions, akin to triplets, depicting semantic relationships between components involved in a surgical scene. Lin et al (2022) assigned instrument and target bounding boxes to triplet information and utilized a spatio-temporal graph for instrument-target interaction detection in cataract surgery.…”

“…Actual action localization was offered by the SARAS-ESAD dataset (Bawa et al, 2021;Lin et al, 2022), with bounding boxes pointing to action verbs being performed.…”