MIDRC collects, curates, harmonizes and makes available a large, inclusive, and representative dataset of clinical medical imaging, currently centered around the chest (Xray, Computed Tomography, MRI) targeting the COVID-19 pandemic and beyond.
MIDRC is a multi-institutional collaborative initiative driven by the medical imaging community aimed at accelerating the transfer of knowledge and innovation in medical imaging, foster the development and accelerate the translation of medical imaging Artificial Intelligence and Machine Learning (AI/ML) algorithms towards clinical translation and real world deployment, through large scale data sharing and dissemination of imaging and associated clinical data. MIDRC provides AI-ready data through harmonized data management. From intake, curation, de-identification, labeling, all the way to data sharing, including tools for cohort building and data query, MIDRC is a significant source of data for medical imaging and associated clinical data for AI/ML development, supported by a Gen3 data commons portal and its associated Graphic User Interface (GUI) and API services.
MIDRC is funded by the National Institute of Biomedical Imaging and Bioengineering (NIBIB); it is based at the University of Chicago, and is co-led by the American College of Radiology®, the Radiological Society of North America, and the American Association of Physicists in Medicine.
MIDRC has established interoperability with NHLBI's BioData Catalyst and NCATS's National COVID Cohort Collaborative (N3C), allowing for the integration of medical images deposited in MIDRC with clinical and electronic health record (EHR) data deposited in BioData Catalyst and N3C, respectively.
For an update list of publications, please visit:
MIDRC publication list.
Currently, best description and start up resources can be found at: