Database intended to be the largest open database of COVID-19-related imaging worldwide.
The Radiological Society of North America (RSNA) launched what could likely become the largest open international database of COVID-19 images.
Known as RICORD (RSNA International COVID-19 Open Radiology Database), and created in concert with the RSNA COVID-19 Task Force, it already has received expressed interest to participate from more than 200 institutions globally. With accompanying clinical information and expert annotations, RSNA leaders say the intent is for radiologists to use the significant de-identified data compilation for research and educational efforts that will save lives.
“More than ever, this pandemic is showing us that we can rally together toward a common purpose,” said RSNA COVID-19 AI Task Force chair Matthew P. Lungren, M.D., MPH, assistant professor of radiology at Stanford University and associate director of the Stanford Center for Artificial Intelligence in Medicine and Imaging. “Rather than siloing data and pursuing fractured efforts, we can instead choose to collaborate through efforts like RICORD to accelerate an end to this pandemic as a united global imaging community.”
The idea for RICORD was borne out of the science community’s efforts in the early stages of the pandemic to isolate the virus and quickly sequence its genome. Once complete, that sequence was immediately release for widespread research and educational use.
To help radiologists use the database, RSNA has developed data-sharing agreements and tools, as well as created collection pathways that make contributing and accessing data in RICORD safe and convenient, RSNA leaders said. It also connects to sustainable storage infrastructure via the National Institutes of Health.
The first version of RICORD is the first annotated core dataset that contains chest radiography and CT exams in DICOM format, including expert radiologist annotation labels. Future iterations will include greater volume and variety of data.
Related Content: ACR Launches COVID-19 Imaging Research Registry
This RSNA launch coincides with the announcement from the American College of Radiology earlier this week that the College was also initiating a COVID-19 imaging registry designed with the same goal.
Computed Tomography Study Assesses Model for Predicting Recurrence of Non-Small Cell Lung Cancer
January 31st 2025A predictive model for non-small cell lung cancer (NSCLC) recurrence, based on clinical parameters and CT findings, demonstrated an 85.2 percent AUC and 83.3 percent sensitivity rate, according to external validation testing in a new study.
What Emerging CT Research Reveals About Obesity and Post-Op Survival for Non-Small Cell Lung Cancer
January 29th 2025For those without low skeletal muscle mass on CT and myosteatosis, obese patients have a 23 percent lower risk of death than non-obese patients after undergoing curative resection for non-small cell lung cancer, according to newly published research.