DeepReg

DeepReg is an open-source Python toolkit for researchers and educators studying medical image registration with deep learning. It brings together algorithms for aligning medical images, with an emphasis on clinical applications and methods that use limited supervision.

The toolkit supports unsupervised and weakly supervised registration, including combinations and variants of those approaches. That gives researchers a common toolkit for exploring different registration methods rather than committing to a single algorithm. TensorFlow provides the foundation for model training and deployment.

Built-in command-line tools reduce the amount of programming and scripting needed to work with the toolkit. For teaching and research, its medical image registration demos use openly accessible data, so learners can study examples alongside the documentation and tutorials.

DeepReg is community-supported and released under the Apache 2.0 license, which permits use and modification for research and other applications.