发表机构
The Chinese University of Hong Kong; Shenzhen Loop Area Institute; Shenzhen University; Southern University of Science and Technology（香港中文大学; 深圳河套学院; 深圳大学; 南方科技大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出SurgLAT框架，结合DINOv3编码器等技术实现隐式手术注意力建模，通过机器人部署框架验证，可在复杂手术场景下实现自主腹腔镜稳健跟踪与稳定调整。
AI 中文摘要
自主腹腔镜摄像头控制需要在动态手术场景中持续理解外科医生的操作意图，其中目标操作区域并非稳定的物理对象，而是随时间演化的隐式注意力状态。本研究提出Surgical Latent Attention Tracking（SurgLAT），一种用于隐式手术注意力建模和自主腹腔镜视图控制的因果在线框架。SurgLAT使用冻结的DINOv3编码器和状态条件空间令牌混合器，在记忆引导的空间先验下提取操作证据，同时选择性因果隐式记忆模块通过动态检索当前、近期和历史隐式状态，共同建模短期运动连续性和长程手术意图演化。学习到的隐式手术注意力状态被解码为概率注意力热图和操作区域，用于下游内窥镜引导。除感知外，我们还引入基于虚拟轴公式的明确腹腔镜运动中心（Remote Center of Motion，RCM）约束控制的机器人部署框架，以及用于稳定平滑操纵器运动的感知冗余空空间初始化。我们在真实腹腔镜手术视频和物理机器人腹腔镜平台上验证了整个系统，实验结果表明，在遮挡、快速运动和目标转换下，系统能实现稳健的在线操作区域跟踪和稳定的自主内窥镜调整，凸显了隐式手术意图建模对于手术自主性的有效性。
英文摘要
Autonomous laparoscopic camera control requires continuous understanding of the surgeon's operative intent in dynamic surgical scenes, where the target operative region is not a stable physical object but a latent and temporally evolving attention state. In this work, we present Surgical Latent Attention Tracking (SurgLAT), a causal online framework for latent surgical attention modeling and autonomous laparoscopic view control. SurgLAT uses a frozen DINOv3 encoder and a state-conditioned spatial token mixer to extract operative evidence under a memory-guided spatial prior, while a selective causal latent memory module jointly models short-term motion continuity and long-horizon surgical intent evolution through dynamic retrieval of current, recent, and historical latent states. The learned latent surgical attention state is decoded into a probabilistic attention heatmap and operative region for downstream endoscope guidance. Beyond perception, we further introduce a robotic deployment framework with explicit laparoscopic Remote Center of Motion (RCM) constrained control based on virtual-axis formulation, together with redundancy-aware null-space initialization for stable and smooth manipulator motion. We validate the full system on real laparoscopic surgical videos and a physical robotic laparoscope platform. Experimental results demonstrate robust online operative-region tracking and stable autonomous endoscopy adjustment under occlusion, rapid motion, and target transitions, highlighting the effectiveness of latent surgical intent modeling for surgical autonomy.
