MIDRC - sporedata/researchdesigneR GitHub Wiki
General description
The Medical Imaging and Data Resource Center (MIDRC) is a collaboration of leading medical imaging organizations launched in response to the COVID-19 pandemic designed to develop a high-quality repository for medical images related to acute and long-term COVID-19 and associated clinical data.
MIDRC is disease agnostic, open to all medical imaging datasets, and continues to build and expand its artificial intelligence-ready data commons to fuel machine intelligence research. Furthermore, MIDRC is a high-quality date commons that adheres to the FAIR principles (Findable, Accessible, Interoperable and Re-usable) in a bid to leverage existing infrastructure.
An important focus of the MIDRC data commons is to develop interoperability strategies with other (non-imaging) data commons so that users can link imaging data (including the metadata available in MIDRC) with more extensive electronic health record data available in other repositories.
Related publications
- AI in medical imaging grand challenges: translation from competition to research benefit and patient care
- MedShift: Automated Identification of Shift Data for Medical Image Dataset Curation
- Training certified detectives to track down the intrinsic shortcuts in COVID-19 chest x-ray data sets
- Machine learning with multimodal data for COVID-19
- Longitudinal assessment of demographic representativeness in the Medical Imaging and Data Resource Center open data commons
- "Shortcuts" Causing Bias in Radiology Artificial Intelligence: Causes, Evaluation, and Mitigation
- External COVID-19 Deep Learning Model Validation on ACR AI-LAB: It's a Brave New World
- Automated deidentification of radiology reports combining transformer and "hide in plain sight" rule-based methods
- Evaluation of federated learning variations for COVID-19 diagnosis using chest radiographs from 42 US and European hospitals
- Toward fairness in artificial intelligence for medical image analysis: identification and mitigation of potential biases in the roadmap from data collection to model deployment
Data access
More information about MIDRC can be found at https://www.midrc.org/
To access MIDRC data, visit https://www.midrc.org/midrc-data