HOPPR and AWS Launch Generative AI Model ‘Grace’ to Bolster Medical Imaging
In Brief
HOPPR and AWS launched generative AI based medical imaging model ‘Grace’, to help clinicians with diagnostic studies.
US-based AI startup HOPPR announced the launch of Grace – a multi-modal foundation model for medical imaging to help clinicians and support staff interact with diagnostic studies. Powered by Amazon Web Services’ (AWS) SageMaker, Grace is now available through a private beta for developers, radiology vendors and AI companies.
According to the announcement, this access will enables fine-tuning and application development, marking an important moment in the company’s mission to tap into the potential of generative AI in medical imaging.
“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,” said HOPPR’s CEO, Dr. Khan M. Siddiqui. “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.”
HOPPR says that Grace is a B2B foundation model and is not confined to specific imaging modalities. It facilitates image-to-image and text-to-image learning of medical imaging types, including X-rays, CT scans, MRIs and echocardiograms.
Delivered through an API service, Grace will help application developers to build AI solutions that promote interactive engagement with medical images.
Users of Grace can use its capabilities to extract diagnostic, clinical and operational value from medical imaging data. The model’s capabilities extend to various applications, ranging from deciphering findings and suggesting alternative imaging views to supporting surgical interventions and treatment protocols.
Beyond clinical applications, Grace accommodates non-clinical use cases, including workflow optimization, billing and coding review and quality assurance.
Trained on Anonymized Data to Ensure Privacy
According to the company, the foundation model has been developed using over a petabyte of permission-based, anonymized medical imaging study data. Further, it is enriched with corresponding reports and has undergone rigorous training for commercial deployment across extensive datasets, covering both 2D and 3D modalities.
The development adheres to a privacy-centric approach, aligning with healthcare industry-standard quality management systems, it added.
The company added that its collaborations, including partnerships with Gradient Health, ensure that Grace encompasses longitudinal imaging studies, setting it apart from conventional generative models. At scale, Grace is anticipated to boast approximately five trillion parameters, outstripping current commercial models.
To refine its offerings and align them precisely with the evolving needs of the healthcare sector, HOPPR is engaging with industry leaders such as RadNet and Rad AI.
The company will showcase live demonstrations of Grace at the Radiological Society of North America (RSNA) annual conference from November 26 to 29, with an aim to highlight the potential applications of the model across the radiology and healthcare landscape.
Future plans involve leveraging additional AWS services, including Health Imaging and Bedrock, for data storage, inferencing, and model development. The collaboration aims to address key obstacles to optimal AI use in medical imaging, including dynamic integration, faster application development and increased image depth.
As the healthcare sector braces for innovation, Grace’s impact may reverberate across clinical care, workflow optimization, and the broader landscape of medical imaging technology.
Disclaimer
In line with the Trust Project guidelines, please note that the information provided on this page is not intended to be and should not be interpreted as legal, tax, investment, financial, or any other form of advice. It is important to only invest what you can afford to lose and to seek independent financial advice if you have any doubts. For further information, we suggest referring to the terms and conditions as well as the help and support pages provided by the issuer or advertiser. MetaversePost is committed to accurate, unbiased reporting, but market conditions are subject to change without notice.
About The Author
Kumar is an experienced Tech Journalist with a specialization in the dynamic intersections of AI/ML, marketing technology, and emerging fields such as crypto, blockchain, and NFTs. With over 3 years of experience in the industry, Kumar has established a proven track record in crafting compelling narratives, conducting insightful interviews, and delivering comprehensive insights. Kumar's expertise lies in producing high-impact content, including articles, reports, and research publications for prominent industry platforms. With a unique skill set that combines technical knowledge and storytelling, Kumar excels at communicating complex technological concepts to diverse audiences in a clear and engaging manner.
More articles
Kumar is an experienced Tech Journalist with a specialization in the dynamic intersections of AI/ML, marketing technology, and emerging fields such as crypto, blockchain, and NFTs. With over 3 years of experience in the industry, Kumar has established a proven track record in crafting compelling narratives, conducting insightful interviews, and delivering comprehensive insights. Kumar's expertise lies in producing high-impact content, including articles, reports, and research publications for prominent industry platforms. With a unique skill set that combines technical knowledge and storytelling, Kumar excels at communicating complex technological concepts to diverse audiences in a clear and engaging manner.
