Data experts with the University of Arkansas for Medical Sciences (UAMS) have uploaded clinical images of COVID-19 patients to a publically available national database that scientists can use in researching the disease and its impact in a global pandemic.
Initial findings were published in the journal Nature, Scientific Data that describe de-identified chest X-rays and other images of UAMS COVID-19 patients uploaded on The Cancer Imaging Archive (TCIA), a publicly available database supported by the National Cancer Institute (NCI).
Ahmad Baghal, M.D., Ph.D.
UAMS was the first to contribute data to TCIA as part of an effort led by Fred Prior, Ph.D., principal investigator for TCIA and professor and chair of the UAMS College of Medicine Department of Biomedical Informatics, and Ahmad Baghal, M.D., Ph.D., director of the Arkansas Clinical Data Repository at UAMS.
“Researchers want this data,” Prior said, noting that 42% of Arkansas’ population is considered rural compared to 15% nationally. “Our state’s inclusion is essential as scientists are trying to figure out how this disease is evolving, how it is impacting different groups of people, and why there are such a wide variety of symptoms and outcomes.”
Over the summer, the NCI authorized use of TCIA as a COVID-19 image repository, Prior said. The Arkansas data gives researchers across the U.S. vital information about COVID-19’s impact on a rural population.
The UAMS biomedical informatics team reports in the journal that it provided a total 256 chest images in the initial phase of the ongoing project, including 233 radiographs (X-rays) and 23 Computed Tomography (CT) images of 105 patients. The patients ranged from ages 19 to 91, with an average age of 54.
Lung damage was common in the hospitalized patients.
“The most frequent pattern of imaging findings is ‘organizing pneumonia’ which is essentially a pattern of lung changes as a response to inflammation,” the article states.
Many of the CT scans included the chest, abdomen and pelvis, which is important, Prior said, because COVID-19 is also affecting organs such as the kidneys and liver.
UAMS’ contributions to TCIA also include genomic sequencing images of SARS-CoV-2 taken from positive test samples in COVID-19 patients.
The data is available on the TCIA website: https://www.cancerimagingarchive.net/collections/
The collection and publication of the data was funded by the UAMS Translational Research Institute, which is supported by the National Institutes of Health National Center for Advancing Translational Sciences, grant UL1TR003107.