Scholarlink

<b>Purpose</b> <p>Continuous tracking of soft-tissue regions in minimally invasive surgery is essential for computer-assisted interventions, yet remains highly challenging due to non-rigid tissue deformation, unconstrained endoscopic camera motion, and frequent occlusions caused by surgical instruments. In particular, long-horizon occlusions, where regions of interest exit the field of view and later re-enter from different angles, remain largely unaddressed by existing online tracking methods.</p> <b>Methods</b> <p>We propose a real-time tracking pipeline that integrates dense optical flow for short-term region tracking, monocular visual odometry for camera localization and depth estimation, and a self-supervised template matching module based on contrastive learning for robust tissue re-identification. The template matching component employs a variational encoder trained using time cycle consistency, enabling the learning of deformation-aware visual representations without requiring manual annotations.</p> <b>Results</b> <p>To evaluate our approach, we rely on the public SurgT dataset and a synthetic dataset explicitly designed to feature long-horizon occlusions. The results show that the proposed pipeline maintains stable tracking performance under extended occlusions and viewpoint changes, enabling accurate re-identification of soft-tissue regions after reappearance. The contrastive variational encoder contributes to improved robustness against tissue deformation and appearance variability compared to reconstruction-based or purely geometric baselines.</p> <b>Conclusions</b> <p>Overall, the proposed framework provides a practical, self-supervised solution for long-horizon tissue tracking in minimally invasive surgery, demonstrating promising performance despite current quantitative evaluation being limited to synthetic data due to the lack of suitable real-world benchmarks. The code is available at <a href="https://github.com/Essex-AI-Innovation-Centre/cl-ve-tracking">https://github.com/Essex-AI-Innovation-Centre/cl-ve-tracking</a></p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Tissue tracking under long-horizon occlusions with contrastive learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月6日

查看全文
  • Myrto Inglezou,
  • Nikolaos Kegkeroglou,
  • Leonidas Delimpasis,
  • Panagiotis Chatzakos,
  • Antonios Porichis

摘要

Purpose

Continuous tracking of soft-tissue regions in minimally invasive surgery is essential for computer-assisted interventions, yet remains highly challenging due to non-rigid tissue deformation, unconstrained endoscopic camera motion, and frequent occlusions caused by surgical instruments. In particular, long-horizon occlusions, where regions of interest exit the field of view and later re-enter from different angles, remain largely unaddressed by existing online tracking methods.

Methods

We propose a real-time tracking pipeline that integrates dense optical flow for short-term region tracking, monocular visual odometry for camera localization and depth estimation, and a self-supervised template matching module based on contrastive learning for robust tissue re-identification. The template matching component employs a variational encoder trained using time cycle consistency, enabling the learning of deformation-aware visual representations without requiring manual annotations.

Results

To evaluate our approach, we rely on the public SurgT dataset and a synthetic dataset explicitly designed to feature long-horizon occlusions. The results show that the proposed pipeline maintains stable tracking performance under extended occlusions and viewpoint changes, enabling accurate re-identification of soft-tissue regions after reappearance. The contrastive variational encoder contributes to improved robustness against tissue deformation and appearance variability compared to reconstruction-based or purely geometric baselines.

Conclusions

Overall, the proposed framework provides a practical, self-supervised solution for long-horizon tissue tracking in minimally invasive surgery, demonstrating promising performance despite current quantitative evaluation being limited to synthetic data due to the lack of suitable real-world benchmarks. The code is available at https://github.com/Essex-AI-Innovation-Centre/cl-ve-tracking