“NIH’s National Institute of Biomedical Imaging and Bioengineering had brought together leaders from different medical imaging associations to discuss the need for a high-quality source of imaging data to expedite machine learning and artificial intelligence for medical imaging.
They were looking for a use case to pilot the idea. ‘Then COVID hit,’ recalls Maryellen Giger, the A.N. Pritzker distinguished service professor of radiology, the Committee on Medical Physics and the College at the University of Chicago…”
“The [Medical Imaging and Data Resource Center’s] first goal is to build the infrastructure around data commons. A major challenge is getting institutions to provide medical images. The diversity of data depends on which institutions donate them. MIDRC, through RSNA and ACR, is helping organizations cover the costs of an IT employee to upload images.
MIDRC’s second goal is to use machine learning to research COVID-19. For instance, an algorithm could be used to explore whether it’s possible to assess the severity of a patient’s disease based on image analysis. Ideally, the infrastructure and model for MIDRC will also be used for other illnesses…”
“’We don’t know of any open commons like MIDRC, one that aims to yield diverse and trustworthy data that will allow investigators to ask various clinical questions,’ says Giger. ‘You’re not pigeonholed into one clinical question. Ultimately, we want to be almost disease-agnostic in our collection.’…” Read the full article here.
Source: Temporary COVID-19 IT Solutions Provide Permanent Options for Federal Agencies – By Melissa Delaney, November 12, 2021. FedTech Magazine.
