HOPPR, a Health2047 company, is using the RSNA venue to launch Grace, a multimodal foundation model developed for image-to-image and text-to-image learning across all imaging modalities.
This beta model is targeted to radiology PACS vendors, AI companies, and other medical imaging-related developers for fine-tuning and application development.
Dubbed Grace, the B2B foundation model enables image-to-image and text-to-image learning across all medical imaging modalities. It enables application developers to more quickly build meaningful AI solutions designed for radiologists, technologists, and radiology support staff to engage interactively with medical images.
The foundation model enables users to unlock diagnostic, clinical, and operational value from medical imaging data, according to the company. The model can be fine-tuned for use in applications that allow users to converse with medical imaging studies about findings, alternative imaging views, suggested surgical interventions, and treatment protocols. It also supports workflow, billing and coding review, and quality assurance.
Grace is powered by Amazon Web services (AWS). Early partners RadNet and Rad AI are conducting live demonstrations throughout the Technical Exhibition at Booth 4547 and 4733, respectively.
