Scholarlink

Purpose <p>Surgical navigation depends on precise image-to-patient registration, yet line-of-sight issues on the tracker, anatomy deformation, and occlusion from instruments and the surrounding environment degrade accuracy and lead to failing scenarios. We target a tracker-free, robust, and explainable vision-based framework for complex operative scenes.</p> Methods <p>We fuse accurate depth estimation with dense 2D point tracking to recover temporally consistent 3D surface motion from surgical video, continuously updating image–to-patient registration. We also present the registration error detection module where we evaluate tracking quality, motion consistency, and 3D motion agreement to rapidly detect and attribute errors (e.g., occlusion, or drift). If an error is detected, the module also disables the mesh overlay.</p> Results <p>Across three phantom scenarios (tool-occluded, layer-occluded, and deformed), our method improves target registration accuracy and robustness compared to the traditional method (ICP) and the learning-based baseline (PREDATOR), particularly under partial occlusion and moderate non-rigid manipulation. On the live-porcine sequence, our proposed method delivers higher accuracy and approximately 20<InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(\times \)</EquationSource> <EquationSource Format="MATHML"><math> <mo>×</mo> </math></EquationSource> </InlineEquation> faster runtime than baselines, indicating feasibility for a real-time application. Beyond accuracy, our approach enables early detection of failure modes, guiding appropriate user intervention.</p> Conclusions <p>Our proposed method, coupled with explainable error detection, maintains registration while reducing reliance on external trackers, contributing to the ongoing effort to build trustworthy, resilient image-guided surgery.</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

Cavir: confidence-aware vision-based registration for image-guided surgery

  • 期刊论文

  • 发表日期：

    2026年3月29日

查看全文
  • Hisashi Ishida,
  • Yuechao Lu,
  • Pourya Shirazian

摘要

Purpose

Surgical navigation depends on precise image-to-patient registration, yet line-of-sight issues on the tracker, anatomy deformation, and occlusion from instruments and the surrounding environment degrade accuracy and lead to failing scenarios. We target a tracker-free, robust, and explainable vision-based framework for complex operative scenes.

Methods

We fuse accurate depth estimation with dense 2D point tracking to recover temporally consistent 3D surface motion from surgical video, continuously updating image–to-patient registration. We also present the registration error detection module where we evaluate tracking quality, motion consistency, and 3D motion agreement to rapidly detect and attribute errors (e.g., occlusion, or drift). If an error is detected, the module also disables the mesh overlay.

Results

Across three phantom scenarios (tool-occluded, layer-occluded, and deformed), our method improves target registration accuracy and robustness compared to the traditional method (ICP) and the learning-based baseline (PREDATOR), particularly under partial occlusion and moderate non-rigid manipulation. On the live-porcine sequence, our proposed method delivers higher accuracy and approximately 20 \(\times \) × faster runtime than baselines, indicating feasibility for a real-time application. Beyond accuracy, our approach enables early detection of failure modes, guiding appropriate user intervention.

Conclusions

Our proposed method, coupled with explainable error detection, maintains registration while reducing reliance on external trackers, contributing to the ongoing effort to build trustworthy, resilient image-guided surgery.