Skip to content

X-ray to Volume Registration

Training patient-specific 2D/3D registration models in 5 minutes

  • 🚀 A single CLI/API for training models and registering clinical data
  • ⚡️ 100x faster patient-specific model training than DiffPose
  • 📐 Submillimeter registration accuracy with new image similarity metrics
  • 🧭 Human-interpretable pose parameters for training your own models
  • 🐍 Pure Python/PyTorch implementation
  • 💾 Supports macOS, Linux, and Windows

Paper

Vivek Gopalakrishnan, David-Dimitris Chlorogiannis, Andrew Abumoussa, Anna M. Larson, Nazim Haouchine, Darren B. Orbach, Sarah Frisken, Neel Dey, and Polina Golland. Rapid patient-specific neural networks for X-ray to volume registration. Nature (2026): 1-9.

Installation

xvr is distributed on PyPI under the package name xvreg.

Full install

If you want the API and CLI, install xvr with your favorite package manager: 

pip install xvreg  # or `uv add xvreg`

Just the CLI

If you just want the CLI, you can run: 

uv tool install xvreg
after which, the CLI will be available globally: 
xvr --help

A quick test

If you just want to test the CLI without a permanent install, try: 

uvx --from xvreg xvr --help