# Patch-Based Image Similarity for Intraoperative 2D/3D Pelvis Registration During Periacetabular Osteotomy

arXiv: https://arxiv.org/abs/1909.10443 · HTML: https://mlsanity.com/paper/1909.10443/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2019.

## Built on by (most cited first, 9 of 9)

- [Intraoperative 2D/3D Image Registration via Differentiable X-ray Rendering](https://mlsanity.com/paper/2312.06358/) (2023)
- [An Optimization-based Baseline for Rigid 2D/3D Registration Applied to Spine Surgical Navigation Using CMA-ES](https://mlsanity.com/paper/2402.05642/) (2024)
- [Fully Differentiable Correlation-driven 2D/3D Registration for X-ray to CT Image Fusion](https://mlsanity.com/paper/2402.02498/) (2024)
- [PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations](https://mlsanity.com/paper/2505.19256/) (2025)
- [Human-AI Collaboration and Explainability for 2D/3D Registration Quality Assurance](https://mlsanity.com/paper/2507.17597/) (2025)
- [Intraoperative 2D/3D Registration via Spherical Similarity Learning and Differentiable Levenberg-Marquardt Optimization](https://mlsanity.com/paper/2509.06890/) (2025)
- [Rapid patient-specific neural networks for intraoperative X-ray to volume registration](https://mlsanity.com/paper/2503.16309/) (2025)
- [Veriserum: A dual-plane fluoroscopic dataset with knee implant phantoms for deep learning in medical imaging](https://mlsanity.com/paper/2509.05483/) (2025)
- [Patient-Agnostic Synthetic Pretraining for Efficient Patient-Specific Intraoperative 2D/3D Registration](https://mlsanity.com/paper/2607.23343/) (2026)

## Abstract (arXiv)

Periacetabular osteotomy is a challenging surgical procedure for treating developmental hip dysplasia, providing greater coverage of the femoral head via relocation of a patient's acetabulum. Since fluoroscopic imaging is frequently used in the surgical workflow, computer-assisted X-Ray navigation of osteotomes and the relocated acetabular fragment should be feasible. We use intensity-based 2D/3D registration to estimate the pelvis pose with respect to fluoroscopic images, recover relative poses of multiple views, and triangulate landmarks which may be used for navigation. Existing similarity metrics are unable to consistently account for the inherent mismatch between the preoperative intact pelvis, and the intraoperative reality of a fractured pelvis. To mitigate the effect of this mismatch, we continuously estimate the relevance of each pixel to solving the registration and use these values as weightings in a patch-based similarity metric. Limiting computation to randomly selected subsets of patches results in faster runtimes than existing patch-based methods. A simulation study was conducted with random fragment shapes, relocations, and fluoroscopic views, and the proposed method achieved a 1.7 mm mean triangulation error over all landmarks, compared to mean errors of 3 mm and 2.8 mm for the non-patched and image-intensity-variance-weighted patch similarity metrics, respectively.