S3-Tracker：基于对比随机游走的自监督手术组织追踪
S3-Tracker: Self-Supervised Surgical Tissue Tracking With Contrastive Random Walks
- Johns Hopkins University（约翰霍普金斯大学）
- The University of British Columbia（不列颠哥伦比亚大学）
- University of Arkansas（阿肯色大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
提出自监督手术组织追踪方法S3-Tracker，利用对比随机游走从未标注视频学习点轨迹，性能媲美半监督方法，减少对标注数据依赖。
AI中文摘要：
在内窥镜视频中进行鲁棒的点追踪对于计算机辅助干预和自主机器人手术至关重要，能够在软组织变形的情况下实现术中视频与术前影像之间的连续配准。然而，有监督追踪方法依赖于大规模标注数据集，而手术条件使得可靠的轨迹标注具有挑战性。我们提出了一种自监督的Track-Any-Point方法，通过建立全局像素对应关系并利用对比随机游走推断点轨迹，从未标注的手术视频中学习。该方法在无标注训练的情况下，达到了与现有半监督方法相当的性能，同时隐式处理了组织变形。这些发现证明了在手术环境中进行自监督点追踪的可行性，并展示了其减少对标注数据依赖的潜力。
英文摘要：
Robust point tracking in endoscopic videos is essential for computer-assisted intervention and autonomous robotic surgery, enabling continuous registration between intraoperative video and preoperative imaging despite soft tissue deformation. However, supervised tracking methods depend on large annotated datasets, while surgical conditions make reliable trajectory annotation challenging. We propose a self-supervised Track-Any-Point approach that learns from unlabeled surgical videos by establishing global pixel correspondences and inferring point trajectories through contrastive random walks. Trained without annotations, our method achieves performance comparable to existing semi-supervised approaches while implicitly handling tissue deformation. These findings demonstrate the feasibility of self-supervised point tracking in surgical environments and its potential to reduce reliance on annotated data.
