Nvidia unveils new Clara models

Nvidia has introduced new open models to its AI-powered Clara suite of applications, models, and tools, including models for imaging. 

The new models for Clara include Reason, a vision language model that advances explainable AI in imaging; Segment, for interactive 3D segmentation and annotation; and Generate, for producing high-quality synthetic CT and MR images.

Nvidia said that it collaborated with the National Institutes of Health (NIH) to capture the human expert reasoning process, with the aim of improving the transparency and interpretability of medical AI. 

The NIH is integrating Clara Reason models into its radiology workflows to assist with drafting reports and explaining findings, as well as to support clinician training, Nvidia said. 

In addition to imaging models, Nvidia is also introducing models aimed at enabling the early drug-discovery pipeline. These include CodonFM, a model that learns the rules of RNA to reveal how changes in its code can improve the design of therapeutics, and La-Proteina, which creates 3D protein structures atom by atom. La-Proteina works at double the length and faster than similar models, Nvidia added, to enable the design of better medicines, enzymes, and materials.

Additionally, Kitware has integrated Clara open models into its VolView platform, allowing users to experiment with AI capabilities for segmentation, reasoning, and generative workflows within their existing imaging and data ecosystems.