NVIDIA Introduces MONAI Application Package (MAP): A Comprehensive Framework for Deploying Medical Imaging AI Applications

To deliver AI-accelerated medical services at scale, healthcare institutions need to orchestrate thousands of neural networks working in concert to address a wide range of tasks spanning human physiology, all disease categories, and even hospital operations—a significant challenge in today’s smart hospital environment.

Currently, leading enterprises and institutions in the field of medical imaging, such as the University of California, San Francisco (UCSF), Cincinnati Children's Hospital, and the startup Qure.ai, are leveraging MONAI Deploy to translate research breakthroughs into clinical applications.

MONAI is an open-source AI framework for medical imaging, accelerated by NVIDIA technology, with over 650,000 downloads to date. Leveraging the MONAI Application Package (MAP), MONAI enables easier integration of models into clinical workflows.

MAP viaMONAI DeployProvided as a packaged AI model, it facilitates easier deployment within existing healthcare ecosystems.

Dr. Ryan Moore of Cincinnati Children’s Hospital stated, “Deploying several AI models in the imaging department to assist experts in identifying more than a dozen different conditions or to enable semi-automated generation of medical imaging reports would require substantial time and resources to secure appropriate hardware and software infrastructure for each model. While this was ‘possible’ in the past, it was not ‘feasible.’”

MAP can streamline this process. If developers use the MONAI Deploy Application SDK to package an application, hospitals can easily run it either locally or in the cloud. The MAP specification also integrates healthcare IT standards, such as DICOM for medical imaging interoperability.

Jorge Cardoso, Chief Technology Officer of the Value-Based Healthcare program at the London Medical Imaging & AI Centre, stated: “Currently, most AI models remain in the research and development phase and are rarely deployed in actual patient care. MONAI Deploy will help translate R&D outcomes into practice, enabling more impactful clinical AI.”

Healthcare institutions, academic medical centers, and AI software developers around the world are adopting MONAI Deploy, including:

●Cincinnati Children’s Hospital: This academic medical center is developing a Model Approval Package (MAP) for an AI model capable of automatically segmenting total heart volume from CT images, thereby supporting pediatric heart transplant patients through a project funded by the National Institutes of Health.

●UK National Health Service (NHS): NHS trusts have deployed a MONAI-based AI deployment engine platform—AIDE (AI Deployment Engine)—across four hospitals, aiming to provide healthcare professionals with AI-powered disease detection tools. These healthcare professionals serve 5 million patients annually.

●Qure.ai: NVIDIA Inception Program member Qure.ai has developed AI models for medical imaging in use cases such as lung cancer, traumatic brain injury, and tuberculosis. The company is using MAP to package solutions requiring deployment, accelerating their clinical impact.

●SimBioSys: This Chicago-based member of the NVIDIA Inception Program has developed 3D virtual representations of patient tumors and leverages MAP for precision medicine AI applications that help predict how patients will respond to specific treatments.

●University of California, San Francisco: The University of California, San Francisco is developing Model Assessment Protocols (MAPs) for several AI models, including applications such as hip fracture detection, liver and brain tumor segmentation, and classification of knee joint conditions and breast cancer.

The MAP specifications are developed by the MONAI Deploy Working Group. This working group comprises experts from more than a dozen medical imaging institutions, with the goal of supporting AI application developers as well as clinical and infrastructure platforms that run AI applications.

For developers, MAP enables researchers to easily package and test models in clinical settings, thereby accelerating the evolution of AI models. This allows them to collect real-world feedback for further refinement and improvement of AI systems.

For cloud service providers, support for MAP (designed using cloud-native technologies) can empower researchers and enterprises adopting MONAI Deploy to run AI applications on their own platforms through container or native application integration. Cloud platforms that integrate MONAI Deploy and MAP include:

●Amazon HealthLake Imaging: The MAP interface has been integrated into the HealthLake Imaging service, enabling clinicians to view, process, and segment medical images in real time.

●Google Cloud: Google Cloud’s Medical Imaging Suite makes medical imaging data more accessible, interoperable, and practical. The suite has integrated MONAI into its platform, enabling clinicians to deploy AI-assisted annotation tools that help automate manual and repetitive medical imaging labeling tasks.

●Microsoft Azure-Powered Nuance Precision Imaging Network: Nuance and NVIDIA recently announced a collaboration to integrate MONAI with the Nuance Precision Imaging Network. The Nuance Precision Imaging Network is a cloud platform that provides AI tools and insights to more than 12,000 healthcare institutions.

●Oracle Cloud Infrastructure: Oracle and NVIDIA recently announced a partnership to bring accelerated computing solutions for the healthcare industry, including MONAI Deploy, to Oracle Cloud Infrastructure. Effective immediately, developers can use NVIDIA containers available on the Oracle Cloud Marketplace to build MAPs via MONAI Deploy.

Since the launch of MONAI, NVIDIA has worked closely with the industry to continuously understand market needs and refine the platform based on feedback. The provision of MAP facilitates easier deployment within existing healthcare ecosystems, further strengthening MONAI’s position in the industry ecosystem.

Get StartedMONAI. Focus on this week'sRSNA Annual Meeting, learn how NVIDIA helps build the AI medical imaging ecosystem.