NVIDIA Clara Imaging is a computational platform that makes it easy for developers to build, manage, and deploy intelligent medical imaging workflows and instruments.

NVIDIA Clara Train Application Framework

Clara Train Application Framework is a domain optimized developer application framework that is based upon the open source frameworks of MONAI.io and NVIDIA FLARE.

It includes capabilities for AI-Assisted Annotation, making any medical viewer AI capable. Clara Train also provides pre-trained models to kick-start AI development with techniques like Transfer Learning, Federated Learning, and AutoML.

Clara Train documentation:

Clara Train archive:

Clara Parabricks is a complete software solution for next generation sequencing, including short- and long-read applications, supporting workflows that start with basecalling and extend through tertiary analysis.

NVIDIA Clara Parabricks

NVIDIA’s Clara Parabricks brings next generation sequencing to GPUs, accelerating an array of gold-standard tooling such as BWA-MEM, GATK4, Google’s DeepVariant, and many more. Users can achieve a 30-60x acceleration and 99.99% accuracy for variant calling when comparing against CPU-only BWA-GATK4 pipelines, meaning a single server can process up to 60 whole genomes per day. These tools can be easily integrated into current pipelines with drop-in replacement commands to quickly bring speed and data-center scale to a range of applications including germline, somatic and RNA workflows.

Clara Parabricks documentation:

Clara Parabricks archive:


MONAI Toolkit is a one-stop development sandbox environment for researchers, data scientists, developers, and clinical teams.

MONAI provides the essential domain-specific tools from data labeling to model training to application deployment, making it easy to develop, reproduce and standardize medical AI lifecycles.

The toolkit includes additional training and enablement of MONAI and a curated set of Jupyter Notebooks and Tutorial Resources to help ease the onboarding process.

MONAI Toolkit documentation: