Radiology imaging is playing an increasingly vital role in the diagnosis of COVID-19 patients and determining therapeutic options, patient care management and new research directions. Publicly available imaging data is essential to drive new research by permitting the creation of large multi-site cohorts for machine learning based analyses. All too frequently rural populations are underrepresented in such public collections. In fact, the literature demonstrates there is very limited data on COVID-19 outcomes in rural populations, while it is well established that such populations have differentially high expression of key comorbidities. Similarly, while the number of genomes of the SARS-COV-2 virus are rapidly growing in public repositories, few samples represent the variants expressed in rural populations. This gap in available data is of particular importance given that the southern United States, as of July 2020, is the most rapidly expanding COVID-19 hot spot on earth. We have published a collection of radiographic and CT imaging studies for patients who tested positive for COVID-19. Each patient is described by a limited set of clinical data correlates that includes demographics, comorbidities, selected lab data and key radiology findings. These data are cross-linked to SARS-COV-2 cDNA sequence data extracted from clinical isolates from the same population, uploaded to the Genbank repository. We believe this collection will help to define appropriate correlative data and contribute samples from this normally underrepresented population to the global research community.
We would like to acknowledge the individuals and institutions that have provided data for this collection:
The University of Arkansas for Medical Sciences (UAMS) Translational Research Institute, Department of Radiology, Department of Biomedical Informatics and Department of Surgery, Little Rock, Arkansas, USA.
Additional datasets and information about TCIA efforts to support COVID-19 research can be found here.