以数据为中心的基于学习的多任务手术注视感知模型设计
Data-centric Design of Learning-based Surgical Gaze Perception Models in Multi-Task Simulation
AI总结：
本研究探讨了在多任务模拟中，基于学习的手术注视感知模型的设计，通过主动-被动注视数据集分析，评估了不同注视来源对注意力模型学习的影响，并提出了可扩展的群众源注视监督方法。
摘要：
在机器人辅助微创手术（RMIS）中，减少的触觉反馈和深度线索增加了对专家视觉感知的依赖，推动了基于注视引导的训练和基于学习的手术感知模型。然而，操作专家的注视数据收集成本高，且不清楚注视监督来源（专家水平（中级 vs. 初学者）和感知模态（主动执行 vs. 被动观看））如何影响注意力模型的学习。我们引入了一个配对的主动-被动、多任务手术注视数据集，该数据集在达芬奇SimNow模拟器上进行了四次钻探任务。使用VR头盔和眼动追踪记录了任务执行期间的主动注视，相应的视频被重新利用作为刺激，以收集观察者的被动注视，从而实现受控的同视频比较。我们量化了技能和模态依赖的注视组织差异，并通过注视密度重叠分析和单帧显著性建模评估了被动注视在操作监督中的可替代性。在各种设置中，MSI-Net产生了稳定且可解释的预测，而SalGAN不稳定且经常与人类注视不一致。训练于被动注视的模型恢复了相当大的中级主动注意力，但存在可预测的退化，且主动和被动目标之间的迁移是不对称的。值得注意的是，初学者的被动标签在较高质量演示中对中级-被动目标的近似具有有限的损失，这表明了一条可行的路径，用于在手术指导和感知建模中实现可扩展的群众源注视监督。
英文摘要：
In robot-assisted minimally invasive surgery (RMIS), reduced haptic feedback and depth cues increase reliance on expert visual perception, motivating gaze-guided training and learning-based surgical perception models. However, operative expert gaze is costly to collect, and it remains unclear how the source of gaze supervision, both expertise level (intermediate vs. novice) and perceptual modality (active execution vs. passive viewing), shapes what attention models learn. We introduce a paired active-passive, multi-task surgical gaze dataset collected on the da Vinci SimNow simulator across four drills. Active gaze was recorded during task execution using a VR headset with eye tracking, and the corresponding videos were reused as stimuli to collect passive gaze from observers, enabling controlled same-video comparisons. We quantify skill- and modality-dependent differences in gaze organization and evaluate the substitutability of passive gaze for operative supervision using fixation density overlap analyses and single-frame saliency modeling. Across settings, MSI-Net produced stable, interpretable predictions, whereas SalGAN was unstable and often poorly aligned with human fixations. Models trained on passive gaze recovered a substantial portion of intermediate active attention, but with predictable degradation, and transfer was asymmetric between active and passive targets. Notably, novice passive labels approximated intermediate-passive targets with limited loss on higher-quality demonstrations, suggesting a practical path for scalable, crowd-sourced gaze supervision in surgical coaching and perception modeling.
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。
