GRAC：基于图的检索增强方法用于手术场景描述
GRAC: Graph-Based Retrieval-Augmented Captioning for Surgical Scene Description
医生写手术报告太费时间，这篇论文用图结构加检索生成场景描述，三元组准确率比 SGT 高了快 20 个点，做医疗 AI 的可以看看思路。
论文提出 GRAC 框架，把手术场景表示为图结构，捕捉器械、动作与解剖结构之间的关系。模型通过检索训练数据中的相似图-描述对，并比较器械-组织交互特征来生成描述。在 EndoVis-18 基准上，GRAC 的 CIDEr-D 达到 5.88，高于 SGT 的 4.23 和最强 Transformer 基线的 3.36；器械-动作-目标三元组准确率为 52.6%，比 SGT 的 32.7% 高出约 20 个百分点。在 TORS 数据集上 CIDEr-D 为 5.06，同样超过最强基线的 3.80。
GRAC: Graph-Based Retrieval-Augmented Captioning for Surgical Scene Description
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.