AUTHOR=Tse Zion Tsz Ho , Hovet Sierra , Ren Hongliang , Barrett Tristan , Xu Sheng , Turkbey Baris , Wood Bradford J. 

TITLE=AI-Assisted CT as a Clinical and Research Tool for COVID-19

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 4 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2021.590189

DOI=10.3389/frai.2021.590189

ISSN=2624-8212

ABSTRACT=There is compelling support for widening the role of computed tomography (CT) in diagnosing and researching COVID-19. RT-PCR testing, the gold standard for COVID-19 diagnosis, has two main pain points: (1) results take several hours to several days to obtain, meaning asymptomatic patients admitted to hospitals may unwittingly spread the disease, and (2) RT-PCR testing kits can run out when demand spikes. Using CT in conjunction with RT-PCR as the standard diagnosis protocol in hospitals would be an effective way to address these problems because CT can be performed on patients entering a hospital as a screening tool to identify possible cases of COVID-19, allowing suspected patients to be quarantined while they await RT-PCR testing. Additionally, CT can be performed even if there are no RT-PCR testing kits available. Furthermore, artificial intelligence (AI) should play a key role in improving the ability of CT to accurately diagnose COVID-19, characterize COVID-19 for clinical research, and increase patient safety by optimizing radiation exposure.