RSNA’s first dataset of annotated COVID-19 images officially published
The Radiological Society of North American on Friday announced that its first set of annotated COVID-19 images has been published by the Cancer Imaging Archive.
This initial dataset includes 120 COVID-19 positive chest CT scans from four international care sites. The public repository comes by way of the RSNA International COVID-19 Open Radiology Database (RICORD) with additional help from the Society of Thoracic Radiology.
The hope is that researchers use this new data for insight into the coronavirus and new tools, such as artificial intelligence, to help detect the disease.
“RSNA was able to draw on relationships established from prior machine learning challenges to quickly put together a COVID-19 AI Task Force,” Carol Wu, MD, a radiologist at MD Anderson Cancer Center and member of the society’s task force, said in a statement. “Contributing sites, already proficient at sharing data with RSNA, were able to quickly process necessary legal agreements, identify suitable cases, perform image de-identification and transfer the images in record speed.”
This publication also marks RICORD’s first contribution to the Medical Imaging and Data Resource Center, a collaboration between RSNA, the American College of Radiology, and the American Association of Physicists in Medicine. MIDRC, as it’s known, is funded by the National Institute of Biomedical Imaging and Bioengineering and hosted by the University of Chicago.
Going forward, RSNA’s COVID-19 AI Task Force plans to continue updating its RICORD data, including a soon-to-be-published collection of negative chest CT control cases and a labeled set of 1,000 COVID-19 positive chest x-rays.
“RSNA is extremely proud to be part of the MIDRC effort,” Curtis Langlotz, MD, PhD, RSNA board liaison for information technology and its annual meeting, said on Friday. “It will build a valuable repository of data for research to address the current pandemic and will serve as a model for how to collect and aggregate data to support imaging research.”
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.