The XNAT ML (Beta) release is a stand-alone package that combines a pre-release version of XNAT 1.8 with several platform and plugin additions to enable a baseline of Machine Learning capability. These capabilities were first demonstrated in collaboration with the NVIDIA Clara suite of medical imaging AI tools, at RSNA 2019. Since then, we have been expanding functionality, deepening integrations, and hardening features to get to the point of this release.

Caveat Emptor

The XNAT ML (Beta) release has not gone through extensive testing, and there are many known limitations of the system, particularly for use cases that extend beyond the limits of this documentation. We do not recommend upgrading a production XNAT system to this beta. This distribution is strictly a proof of concept. We are open to all bug reports and feature suggestions. Feel free to join the discussion at the public XNAT Development Discussion Group.

Performing Training

Workflows

Setup Tasks

Data Import and Collection

Model Training

Other Operations

  • Deleting Models, Training, and Datasets

$label.name