The Medical Imaging and Data Resource Center (MIDRC), a federally funded initiative hosted at the University of Chicago to provide researchers with data and resources for developing machine learning and artificial intelligence (AI) of medical images, has been selected to participate in a new pilot program from the National Science Foundation (NSF) to democratize AI research.
The National Artificial Intelligence Research Resource (NAIRR) pilot will gather 10 federal agencies and 25 private sector, nonprofit, and philanthropic organizations to build a shared research infrastructure that will strengthen access to critical resources necessary to power responsible AI discovery and innovation. The project will provide access to advanced computing, datasets, models, software, training, and user support to U.S.-based researchers and educators and, as it continues to grow, will inform the design of a national AI ecosystem.
Confronting the pandemic
MIDRC was launched in August of 2020 to confront the COVID-19 pandemic by creating and curating a massive database of medical images to help better understand and treat disease, with funding from the National Institute of Biomedical Imaging and Bioengineering (NIBIB) at the National Institutes of Health (NIH). By collecting and integrating images and their data via a secure networked system, MIDRC provides a large-scale, open data commons framework to enable technological advancements, guide researchers’ validation and use of AI, and translate clinical systems for the best patient management decisions.
In its first three years of operation, MIDRC collected more than 300,000 imaging studies (including x-rays and CT scans) and has released more than 165,000 imaging studies from almost 70,000 patients across the U.S. to date. The Center also helped create 27 in-house algorithms for the detection, diagnosis, monitoring, and prognosis of COVID-19.
In 2023, MIDRC was selected as a performer for the Advanced Research Projects Agency for Health (ARPA-H) Biomedical Data Fabric (BDF) Toolbox, an initiative to de-risk technologies for an easily deployable, multi-modal, multi-scale, connected data ecosystem for biomedical data. MIDRC provides domain expertise and data commons technology development in medical imaging for the project.
Securing AI for research
The NAIRR pilot will initially support AI research to advance safe, secure, and trustworthy AI, as well as the application of AI to challenges in healthcare and environmental and infrastructure sustainability. The pilot will also provide support to educators to enable training on AI technologies and their responsible approaches.
MIDRC has been selected to participate in one of the four NAIRR pilot projects called NAIRR Secure, co-led by NIH and the U.S. Department of Energy. This pilot will enable AI research requiring privacy and security-preserving resources and will assemble exemplary privacy preserving resources.
“The overall goal of MIDRC is to support the medical imaging AI ecosystem. We’ve built the infrastructure to house, curate, and organize medical images, we’ve collected a huge amount of real-world imaging data, and we’ve put forth a concerted effort to educate users about the development of algorithms and potential sources of bias,” said Maryellen L. Giger, PhD, the A.N. Pritzker Distinguished Service Professor of Radiology at UChicago and MIDRC principal investigator. “The collaborations and infrastructure that have been established provide a solid foundation for the creation of more medical imaging datasets and the development of AI algorithms for all sorts of use cases through this new NAIRR pilot program.”
Maryellen L. Giger, PhD
A.N. Pritzker Distinguished Service Professor of Radiology
of Committee on Medical Physics
MIDRC is co-led by investigators from the American Association of Physicists in Medicine (AAPM), the Radiological Society of North America (RSNA), and the American College of Radiology (ACR). It is hosted at the University of Chicago (MIDRC Central) on the Gen3 data ecosystem maintained by the University of Chicago Center for Translational Data Science.
