🔥 FireANTs

The FireANTs library is a lightweight registration package for Riemannian diffeomorphic registration on GPUs.

Features

Currently, FireANTs supports the following forms of registration:

Moreover, it supports the following similarity metrics:

• Cross-correlation
• Mutual information
• Mean squared error
• Custom similarity metrics (see Tutorial)

FireANTs also provides functionality for saving transformations in the ANTs formats for seamless integration with existing workflows.

We also provide scripts for template building.

Core Idea

The initial motivations were to create a GPU reimplementation of the widely used ANTs library. However, we improved upon the initial implementation to implement first-order adaptive algorithms (like Adam) on Riemannian manifolds, specifically for multi-scale diffeomorphisms.

Installation

Follow the instructions on the GitHub page .

Documentation

Coming soon.

Support and Contributions

Feel free to add issues or pull requests to the repository. We welcome contributions to the package.