Scholarlink

Purpose <p>Accurate 2D/3D registration between fluoroscopic X-ray images and preoperative CT models is essential to get dynamic joint kinematics in computer-assisted orthopedic analysis. Traditional correlation-based similarity metrics in model–image optimization often suffer from limited capture range and sensitivity to noise and occlusion.</p> Methods <p>We propose a pose-aware deep perceptual metric using contrastive learning for enlarged capture range and improved robustness. Inspired by LPIPS, our network was specialized and designed for 2D/3D fluoroscopic image registration, where the supervision reflects true 3D transformation discrepancies. The learned metric is integrated into a differentiable 2D/3D registration framework, enabling gradient-based optimization.</p> Results <p>The proposed metric enlarges the capture range of 2D/3D registration and smooths the loss landscape, while ensuring the required accuracy for automated registration. Our metric outperforms conventional similarity measures and standard LPIPS, presenting zero-shot ability for unseen low-contrast fluoroscopic conditions.</p> Conclusion <p>The proposed metric provides a robust and differentiable metric for fluoroscopic 2D/3D registration, improving accuracy in joint kinematics analysis for both single- and dual-plane fluoroscopy.</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

Pose-aware deep perceptual similarity for iterative 2D/3D registration of knee joints using contrastive learning

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年6月19日

查看全文
  • Jinhao Wang,
  • Xia Li,
  • Raphael Surbeck,
  • Saša Ćuković,
  • William R. Taylor

摘要

Purpose

Accurate 2D/3D registration between fluoroscopic X-ray images and preoperative CT models is essential to get dynamic joint kinematics in computer-assisted orthopedic analysis. Traditional correlation-based similarity metrics in model–image optimization often suffer from limited capture range and sensitivity to noise and occlusion.

Methods

We propose a pose-aware deep perceptual metric using contrastive learning for enlarged capture range and improved robustness. Inspired by LPIPS, our network was specialized and designed for 2D/3D fluoroscopic image registration, where the supervision reflects true 3D transformation discrepancies. The learned metric is integrated into a differentiable 2D/3D registration framework, enabling gradient-based optimization.

Results

The proposed metric enlarges the capture range of 2D/3D registration and smooths the loss landscape, while ensuring the required accuracy for automated registration. Our metric outperforms conventional similarity measures and standard LPIPS, presenting zero-shot ability for unseen low-contrast fluoroscopic conditions.

Conclusion

The proposed metric provides a robust and differentiable metric for fluoroscopic 2D/3D registration, improving accuracy in joint kinematics analysis for both single- and dual-plane fluoroscopy.