TTDF：一种用于可靠手术阶段转换检测的两阶段框架
TTDF: A Two-Stage Framework for Reliable Surgical Phase Transition Detection
浏览论文内容
中文总结 AI 辅助
针对在线手术阶段识别器转换事件不可靠的问题，提出TTDF两阶段框架，通过候选提取与验证过滤虚假转换，在Cholec80上减少误报并保持召回率。
中文摘要 AI 辅助
可靠的工作流转换检测对于情境感知的手术辅助和下游决策支持至关重要。然而，在线手术阶段识别器主要关注逐帧准确性和时间一致性，而非工作流转换事件的可靠性。直接将阶段变化转换为事件是不可靠的：时间抖动和工作流不允许的切换会产生虚假或重复事件，而持续存在且符合工作流一致性的候选事件也可能是不正确的。为解决这一局限，我们将可靠的工作流转换检测定义为一个独立的事件级任务，作用于冻结的在线阶段识别器的输出。我们提出了两阶段转换检测框架（TTDF），这是一个逐步过滤转换候选的因果框架。转换候选提取（TCE）首先应用最小持续时间要求和工作流图约束，以移除由时间抖动和阶段转换（工作流图不允许的）导致的虚假候选。具体而言，仅当预测的目标阶段持续达到最小持续时间且有序阶段对属于工作流图允许的转换集时，候选才会被保留。因此，TCE无需额外训练即可产生高召回率的候选集。转换候选验证（TCV）利用阶段后验偏移和来自冻结DINOv2特征的视觉变化线索来抑制剩余的虚假候选。事件使用阶段对感知的一对一匹配协议进行评估。在Cholec80上的实验表明，TTDF减少了虚假转换发射，同时保持了召回率并控制了决策延迟。
英文摘要
Reliable workflow transition detection is important for context-aware surgical assistance and downstream decision support. However, online surgical phase recognizers primarily focus on frame-wise accuracy and temporal consistency, rather than the reliability of workflow transition events. Directly converting phase changes into events is unreliable: temporal jitter and workflow-illegal switches produce false or duplicate events, while persistent, workflow-consistent candidates may remain incorrect. To address this limitation, we formulate reliable workflow transition detection as a distinct event-level task operating on outputs of a frozen online phase recognizer. We propose the Two-Stage Transition Detection Framework (TTDF), a causal framework that progressively filters transition candidates. Transition Candidate Extraction (TCE) first applies a minimum-duration requirement and a workflow-graph constraint to remove false candidates caused by temporal jitter and phase transitions not allowed by the workflow graph. Specifically, a candidate is retained only if the predicted target phase persists for a minimum duration and the ordered phase pair belongs to the workflow graph's allowed transition set. TCE thereby produces a high-recall candidate set without additional training. Transition Candidate Verification (TCV) suppresses remaining false candidates using phase-posterior shifts and visual-change cues from frozen DINOv2 features. Events are assessed using a phase-pair-aware one-to-one matching protocol. Experiments on Cholec80 show that TTDF reduces false transition emissions while preserving recall and controlling decision delay.
发表机构
- University of Leeds（利兹大学）
- STORM Lab UK
机构由 AI 辅助整理，请以论文原文为准。
