MAP “all in one package”: MONAI launches a framework for deploying medical imaging AI applications

Leading companies and institutions in the field of medical imaging, including the University of California, San Francisco (UCSF), Cincinnati Children's Hospital, and startup Qure.ai, rely on MONAI Deploy to bring research breakthroughs to the clinic.

In order to provide AI-accelerated medical services at scale, medical institutions need to have thousands of neural networks working together to deal with all aspects of human physiology, all diseases, and even hospital operations. This is in today's smart hospital environment. is a major challenge.

MONAI is an open source medical imaging AI framework accelerated by NVIDIA technology, and has been downloaded more than 650,000 times. With the MONAI Application Package (MAP), MONAI can more easily integrate models into clinical workflows.

MAP is provided through MONAI Deploy, which is a packaging method of AI models that can be deployed more easily in the existing medical ecosystem.

"If you want to deploy several AI models in the imaging department to help experts identify a dozen different conditions or to semi-automate the creation of medical imaging reports, it will take a lot of time and resources to create a complete model for each patient," said Dr. Ryan Moore of Cincinnati Children's Hospital. This model seeks the right hardware and software infrastructure. This was 'possible' but not 'feasible' in the past."

MAP simplifies this process. If developers use the MONAI Deploy application software development kit to package an application, hospitals can easily run the application locally or in the cloud. The MAP specification also integrates medical IT standards, such as the medical imaging interoperability standard DICOM.

Jorge Cardoso, chief technology officer of the Value-Based Healthcare project at the London Center for Medical Imaging and AI, said: "Currently, most AI models have been in the research and development stage, and few can actually be used in patient care. MONAI Deploy will help promote the implementation of research and development results, Enabling more impactful clinical AI.”

MONAI Deploy adopted by hospitals and healthcare startups

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

● Cincinnati Children's Hospital: The academic medical center is creating a MAP for an AI model that can automatically segment whole heart volumes in CT images to assist pediatric heart transplant patients through a project funded by the National Institutes of Health.

● British National Health Service (NHS): NHS trusts have deployed MONAI-based AI deployment engine platform - AIDE (AI Deployment Engine) in four hospitals, committed to providing AI disease detection tools for professional medical staff. These medical staff serve 5 million patients annually.

● Qure.ai: NVIDIA Startup Accelerator Program member Qure.ai develops medical imaging AI models for use cases such as lung cancer, brain trauma, and tuberculosis. The company is using MAP to package solutions for deployment and drive these solutions to clinical impact more quickly.

● SimBioSys: This Chicago-based NVIDIA Startup Acceleration Program member builds 3D virtual representations of patients’ tumors and uses MAP for precision medicine AI applications that help predict how patients will respond to specific treatments.

● University of California, San Francisco: UCSF is developing MAP for several AI models, including applications such as hip fracture detection, liver and brain tumor segmentation, and knee and breast cancer classification.

Deploy medical imaging AI to MAP

MAP specifications are developed by the MONAI Deploy working group. The working group consists of experts from more than a dozen medical imaging institutions and aims to support AI application developers as well as clinical and infrastructure platforms that run AI applications.

For developers, MAP can help researchers easily package and test models in clinical settings, thereby accelerating the evolution of AI models. This allows them to collect real-world feedback to refine and improve the AI.

For cloud service providers, support for MAP (designed using cloud native technology) can help researchers and enterprises using MONAI Deploy run AI applications on their own platforms through container or native application integration. Cloud platforms integrating MONAI Deploy and MAP include:

● Amazon HealthLake Imaging: The MAP interface has been integrated into the HealthLake imaging service, allowing 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, more interoperable and more useful. The suite has integrated MONAI into its platform, enabling clinicians to deploy AI-assisted annotation tools to help automate manual and repetitive medical image labeling tasks.

● Nuance Precision Imaging Network powered by Microsoft Azure: Nuance and NVIDIA recently announced a collaboration to combine 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 medical institutions.

● Oracle Cloud Infrastructure: Oracle and NVIDIA recently announced a collaboration to bring accelerated computing solutions for the healthcare industry, including MONAI Deploy, to Oracle Cloud Infrastructure. Starting today, developers can use NVIDIA containers on Oracle Cloud Marketplace to build MAP through MONAI Deploy.

Get started with MONAI. Pay attention to this week's RSNA conference to learn how NVIDIA helps build an AI medical imaging ecosystem.