RoboSurg-VQA：面向手术分割感知的视觉问答多模态基准
RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering
AI总结：
提出RoboSurg-VQA基准，通过重新利用公共手术分割数据集，构建分割感知的视觉问答任务，以评估在机器人辅助和微创手术中恶劣视觉条件下的语言化临床问题理解能力。
摘要：
在机器人辅助和微创手术（RMIS/MIS）中，可靠的视觉理解不仅仅需要精确的掩膜：在临床实践中，临床医生会提出关于手术过程背景、可见性、伪影以及解剖结构和手术器械存在性的语言类问题，且通常是在由遮挡、烟雾、出血和镜面高光导致的退化视图下。我们提出了 extbf{RoboSurg-VQA}，这是一个基于共享模式重新利用公共手术分割数据集构建的分割感知视觉问答（VQA）基准。每帧图像与一组固定的临床驱动问题配对，涵盖手术过程背景、解剖结构（包括区域）、成像模态/视图、手术伪影、图像质量以及基本可见性和空间属性，并采用封闭答案集以实现一致的评估。为了扩展标注，我们通过约束提示生成候选答案，并自动进行有效性和一致性检查，随后进行人工审计以提高合理性和标签一致性。我们报告了基准统计信息、基线合理性以及在挑战性手术条件下的常见评估挑战。代码将在https://github.com/ziyangwang007/Robosurg-VQA上提供。
英文摘要：
Reliable visual understanding in robot-assisted and minimally invasive surgery (RMIS/MIS) demands more than accurate masks: in clinical practice, clinicians pose language-like questions about procedural context, visibility, artefacts, and the presence of anatomical structures and surgical instruments, often under degraded views caused by occlusion, smoke, bleeding, and specular highlights. We present \textbf{RoboSurg-VQA}, a segmentation-aware visual question answering (VQA) benchmark built by repurposing public surgical segmentation datasets under a shared schema. Each frame is paired with a fixed set of clinically motivated questions spanning procedure context, anatomy (including region), imaging modality/view, surgical artefacts, image quality, and basic visibility and spatial attributes, with closed answer sets to enable consistent evaluation. To scale annotation, we generate candidate answers via constrained prompting with automatic validity and consistency checks, followed by human auditing to improve plausibility and label consistency. We report benchmark statistics, sanity baselines, and common evaluation challenges under challenging surgical conditions. The code will be available on https://github.com/ziyangwang007/Robosurg-VQA.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
