Home

Awesome

CLAIRE

status status status

Documentation <a name="clairedoc"></a>

The links above point to individual markdown files. These files can be found in the doc subfolder. Basic examples for how to execute CLAIRE can be found in the doc/examples folder. The NIREP dataset used to test CLAIRE can be downloaded here.

About <a name="claireabout"></a>

CLAIRE stands for Constrained Large Deformation Diffeomorphic Image Registration. It is a C/C++ software package for velocity-based diffeomorphic image registration in three dimensions. Its performance is optimized for multi-core CPU systems (cpu branch) and multi-node, multi-GPU architectures (gpu branch; default). The CPU version uses MPI for data parallelism, and has been demonstrated to scale on several supercomputing platforms. CLAIRE can be executed on large-scale state-of-the-art computing systems as well as on local compute systems with limited resources.

Notice that the CPU version is accurate and running but new features are currently only being added to the GPU version. The GPU code is a major revision and therefore considered the default and recommended for use.

<p align="center"> <img src="doc/figs/claire4brains.jpg" alt="CLAIRE4Brains" width="800"/> </p>

If there are any issues, you have questions, you would like to give us feedback or you have feature requests, do not hesitate to send an email to andreas@math.uh.edu.

If you plan on using CLAIRE in your research please cite the following manuscript: A. Mang, A. Gholami, C. Davatzikos & G. Biros. CLAIRE: A distributed-memory solver for constrained large deformation diffeomorphic image registration. SIAM Journal on Scientific Computing 41(5):C548--C584, 2019 [arxiv, sisc]. Additional references are listed here.

Contributors

George Biros, Malte Brunn, Amir Gholami, James Herring, Naveen Himthani, Andreas Mang, and Miriam Mehl.

If you want to contribute to CLAIRE, read the guidlines (see doc/CONTRIBUTING.md).

Code of Conduct

See doc/CODE_OF_CONDUCT.md.

License

Read the LICENSE file for more details.