cs.CVNov 6, 2026

GRAC: Graph-Based Retrieval-Augmented Captioning for Surgical Scene Description

Authors: Rochak Dhakal, Chen Zhao, Soup Cobb, Xin Qian, Xiaofeng Yang, Weihua Zhou

Organizations: Department of Data Science, Michigan Technological University, Houghton, MI, USA · Department of Computer Science, Kennesaw State University, Marietta, GA, 30060, USA · Department of Computer Science, Michigan Technological University, Houghton, MI, USA · Department of Physics and Anatomy, Stony Brook University Hospital, Stony Brook, NY, USA · 

Abstract

Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise. Automated surgical scene descriptions could reduce this burden by leveraging recurring surgical activities and prior knowledge. Methods: We propose GRAC (Graph-Based Retrieval-Augmented Captioning), a framework that represents surgical scenes as graphs capturing relationships among instruments, actions, and anatomical structures. Given an input scene graph, GRAC learns to retrieve relevant graph-caption pairs from training data. It compares instrument-tissue interactions between retrieved examples and the input scene, using comparison features to condition retrieved-caption representations during generation. Results: On the EndoVis-18 benchmark, GRAC achieved a CIDEr-D of 5.88, compared with 4.23 for SGT and 3.36 for the strongest conventional Transformer baseline. Exact instrument-action-target triplet-set accuracy reached 52.6%, compared with 32.7% for SGT and 26.2% for the strongest conventional baseline. These results demonstrate improvements in language quality and factual agreement. On TORS, GRAC achieved a CIDEr-D of 5.06, compared with 3.80 for the strongest baseline. Conclusion: GRAC demonstrates that combining structured surgical scene representations with retrieved examples improves surgical scene captioning and produces more contextually meaningful descriptions.

Figures & tables

Explore similar work

CardsList
  1. SAGE-OR: Semi-supervised Adaptive Scene Graph Generation for Operating Rooms

    Aug 15, 2026Brandon Leblanc, Charalambos PoullisScene Graph Generation3D Scene Understanding

  2. GroundedSurg: A Multi-Procedure Benchmark for Language-Conditioned Surgical Tool Segmentation

    Mar 1, 2026Tajamul Ashraf, Abrar Ul Riyaz, Wasif Tak +4Medical Image GroundingReferring Image Segmentation

  3. Towards Unified Surgical Scene Understanding:Bridging Reasoning and Grounding via MLLMs

    May 13, 2026Jincai Huang, Shihao Zou, Yuchen Guo +5Surgical Video UnderstandingVision-Language Grounding