RICORD FAQs

RICORD is an open database of COVID-19-related medical imaging assembled by RSNA with the help of partners and contributing sites around the world. RICORD can be used by the global radiology research and education communities to gain insights, apply new tools such as artificial intelligence and deep learning, and accelerate clinical recognition of this terrible new disease. Watch RSNA’s RICORD webinar to learn more about this important initiative. 

Any institution that has the capacity to submit data meeting the minimum data requirements and de-identification protocol can participate. Institutions that can submit imaging studies of COVID-19 negative patients, as well as clinical outcomes and other data correlated to imaging studies are strongly encouraged to do so.

Include:
All patients at least 18 years of age with chest imaging (CT and/or Xray) for suspected COVID-19 infection (for example ICD-10-CM code U07.1 among discharge diagnosis).

Positive infection should be confirmed with one or more of the following:

• RT-PCR test
• Positive IgM antibody test
• Clinical diagnosis using hospital specific criteria

Positive infection encompasses:

• Patients who are diagnosed prior to hospitalization, but still symptomatic during the hospitalization
• Patients with a positive test or diagnosis during hospital admission
• Patients who are symptomatic during the hospitalization and have a confirmed test available only after hospital discharge

Exclude:

• Patients younger than 18 years of age
• Patients who did not receive chest imaging (CT and/or Xray)

You should always follow your individual institution’s guidance regarding the necessity of your institutional review board’s (IRB) approval for this initiative. Your hospital IRB will determine whether participation is subject to or exempt from IRB oversight. The U.S. Department of Health & Human Services offers a resource that may help answer your specific IRB questions.

Sites participating in RICORD are required to sign a Data Submission Agreement with identical terms and provisions to the one used by the National Cancer Institute’s Cancer Imaging Archive, which will be the host for the initial public version of RICORD. Sites are also required to deidentify their data in accordance with the specified protocol. Data contributed by many sites will be combined into an organized data resource and made freely available for non-commercial research and educational uses.

Data submissions began in early June 2020. These submissions are being used in a pilot project to define annotation methods for COVID imaging. Plans are underway to make the first RICORD datasets publicly available in July. Future releases of RICORD will expand the volume and types of data available.

The data in RICORD will be freely available for non-commercial research and educational uses.

We anticipate receiving COVID-19 imaging data through the end of 2020. We will consider extending data submission based on identified needs for additional types or volumes of data to support research.

Interested sites can complete the expression of interest form. The steps for submitting agreements and selecting, de-identifying and submitting data are outlined on our resources page.

RICORD will allow for optional inclusion of key patient clinical characteristics, labs, vitals and outcomes in patients hospitalized with COVID-19. Below is a high-level summary of the types of data captured.

A minimal required set of data elements and laboratory tests is specified in the RICORD data inclusion criteria.

Researchers and educators interested in using the data for non-commercial research and education can get free access by agreeing to the terms of the TCIA Data Use Agreement.