DeepReg is a freely available, community-supported open-source toolkit for research and education in medical image registration using deep learning.

The current version is implemented as a TensorFlow2-based framework, and contains implementations for unsupervised- and weakly-supervised algorithms with their combinations and variants. DeepReg has a practical focus on growing and diverse clinical applications, as seen in the provided examples - DeepReg Demos.

Get involved and help make DeepReg better!


DeepReg extends and simplifies workflows for medical imaging researchers working in TensorFlow 2, and can be easily installed and used for efficient training and rapid deployment of deep-learning registration algorithms.

DeepReg is designed to be used with minimal programming or scripting, owing to its built-in command line tools.

Our development and all related work involved in the project is public, and released under the Apache 2.0 license.


For development matters, please raise an issue.

For matters regarding the Code of Conduct, such as a complaint, please email the DeepReg Development Team:

Alternatively, please contact one or more members of the CoC Committee as appropriate: Nina Montana Brown (, Ester Bonmati (, Matt Clarkson (



DeepReg is maintained by a team of developers and researchers. People with significant contributions to DeepReg are acknowledged in the Contributor List.

This open-source initiative started within University College London, with support from the Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS), and partial support from the Wellcome/EPSRC Centre for Medical Engineering (CME).