发表机构
ShanghaiTech University; Wuhan United Imaging Surgical Co., Ltd.（上海科技大学; 武汉联影外科医疗有限公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对手术器械实例分割中前景掩码易生成错误实例集的问题，提出拓扑感知查询选择方法，经实验验证可提升实例集性能，稳定跨域迁移与组件效应仍待明确。
AI 中文摘要
精确的前景掩码仍可能形成错误的手术器械实例集：重复、碎片化、合并、遗漏或空帧预测虽能保持良好的像素重叠度，却违背了对象身份与计数要求。因此，最终查询选择是一个关系型、可变基数问题，而非一系列独立候选决策。本文评估了拓扑感知查询选择方法，该方法将固定Mask2Former的非空候选表示为完全图，学习关系型候选与对表示，预测集合基数，并求解精确结构化子集问题。正式对比了完全关系路径与节点特征匹配路径，评估了成对几何、消息传递及额外关系路径容量的综合效应，而非孤立组件。在含22个病例的密封源测试中，所有三个发现种子均支持实例集性能提升，同时保持分割保真度与预定义技术安全性：实例F1提升0.0504至0.0612，正帧集失败率降低0.0848至0.1060。直接ROBUST-MIPS迁移在三个种子中均复现完整结果，Endoscapes仅支持其中一个种子，未建立稳定直接迁移。综上，结果支持有限结论：所评估的完全路径在指定原生实例约束下，改进了从固定Mask2Former候选生成连贯实例集的过程，而稳定跨域迁移与组件特定效应仍未明确。
英文摘要
Accurate foreground masks can still form an incorrect surgical-instrument instance set: duplicate, fragmented, merged, missed, or empty-frame predictions may preserve favorable pixel overlap while violating object identity and count. Final query selection is therefore a relational, variable-cardinality problem rather than a collection of independent candidate decisions. We evaluate topology-aware query selection, which represents the nonempty candidates of a fixed Mask2Former as a complete graph, learns relational candidate and pair representations, predicts set cardinality, and solves an exact structured subset problem. The formal comparison is the complete relational path versus a node-feature-matched path; it evaluates the combined effect of pairwise geometry, message passing, and the additional relational-path capacity, not an isolated component. On the sealed 22-case source test, all three discovery seeds supported instance-set performance improvement with segmentation fidelity and predefined technical-safety preservation: instance F1 increased by 0.0504--0.0612 and positive-frame set-failure rate decreased by 0.0848--0.1060. Direct ROBUST-MIPS transfer reproduced the complete result in all three seeds. Endoscapes supported only one of three seeds and therefore did not establish stable direct transfer. Taken together, the results support a bounded conclusion: the evaluated complete path improved coherent instance-set construction from fixed Mask2Former candidates in specified native-instance contracts, while stable cross-domain transfer and component-specific effects remain unestablished.
CommentsPreprint. Main manuscript and supplementary material included. Code and reproducibility materials: https://github.com/yqjyzzz/structured-instance-set-selection
