Grace is a B2B foundation model that enables image-to-image and text-to-image learning across all medical imaging modalities, including X-rays, CTs, MRIs, and ECGs, to help application developers rapidly build meaningful AI solutions
The new foundation model is powered by Amazon Web Services (AWS). (Credit: Dmitriy Gutarev from Pixabay)
HOPPR, a portfolio company of Health2047, has rolled out its new multi-modal foundation model, Grace, for medical imaging, powered by Amazon Web Services (AWS).
The company is offering the new foundation model through private beta, to developers, radiology PACS, and AI companies for fine-tuning and application development.
Grace is a B2B foundation model that enables image-to-image and text-to-image learning across all medical imaging modalities, including X-rays, CTs, MRIs, and ECGs.
It is available through an API service and enables application developers to rapidly build meaningful AI solutions that can engage interactively with medical images.
The new foundation model was developed exclusively on AWS using Amazon SageMaker, with plans to leverage AWS Health Imaging, Amazon Bedrock, and other services in future.
HOPPR CEO Khan Siddiqui said: “We are thrilled to launch the beta HOPPR foundation model to trusted PACS vendors and developers to fine-tune models and provide feedback to prepare us for commercial expansion in Q1 of 2024.
“Grace represents a game-changing advance for HOPPR and the broader medical imaging space, which stands to benefit enormously from the transformative potential of AI to improve the efficiency and quality of clinical care.”
AWS healthcare and life sciences general manager Dan Sheeran said: “Accelerating AI’s clinical and operational value in medical imaging eases burdens for radiologists, providers, and support staff, which could ultimately result in better patient outcomes.
“We are excited to work with HOPPR to make fine-tuning and deploying foundation models for medical imaging easier and faster, decreasing the time to value from years to months.”
Grace has been precisely developed using more than a petabyte of permission-based, anonymised medical imaging study data, enriched with corresponding reports.
It contains around five trillion parameters, five times more than current commercial generative models trained on one trillion parameters.
The model also supports non-clinical use cases, including workflow, billing and coding review, and QA, providing a one-API shop for all the data needed to support the imaging sector.
Grace has been developed with a privacy-centric approach using healthcare industry-standard quality management systems based on ISO 13485, said HOPPR.
Separately, HOPPR has received $3m in a funding round led by Health2047, with participation from Evidium, Medcurio, Phenomix Sciences, ScholarRx, SiteBridge and Zing Health.
Health2047 CEO Lawrence Cohen said: “Health2047 is proud to support HOPPR’s work to build a powerful data repository for researchers and clinicians.
“As a physician, imagine if you could chat with imaging studies, asking them for treatment protocols, alternate views, and more.
“HOPPR’s work to unleash the full potential of AI for medical imaging promises to spur innovation and improve efficiency and outcomes.”