AUTHOR=Deng Hanqiu , Li Xingyu 

TITLE=AI-Empowered Computational Examination of Chest Imaging for COVID-19 Treatment: A Review

JOURNAL=Frontiers in Artificial Intelligence

VOLUME=Volume 4 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2021.612914

DOI=10.3389/frai.2021.612914

ISSN=2624-8212

ABSTRACT=Since the first case of Coronavirus disease 2019 (COVID-19) discovered in Dec. 2019, COVID-19 swiftly spreads over the world. As the end of March 2021, more than 136 million patients have been infected. Since the 2nd and 3rd waves of COVID-19 outbreak are in full swing, it is important to investigate effective and timely solutions for patients’ check-up and treatment. Though the SARS-CoV-2 virus-specific reverse transcriptase polymerase chain reaction test is recommended for the diagnosis of COVID-19, the test is prone to be falsely negative in the early course of COVID-19 infection. To enhance the screening efficiency and accessibility, chest images captured via X-ray or computed tomography (CT) provides valuable information in evaluating patients with suspected COVID-19 infection. Particularly, with the advanced artificial intelligence (AI) techniques, AI-driven models training with lung scans emerge as a quick diagnostic and screening tool to look for COVID-19 infection in patients. In this paper, we provide a comprehensive review of state-of-the-art AI-empowered methods for computational examination of COVID-19 patients with lung scans. In this regard, we searched papers and preprints on bioRxiv, medRxiv and arXiv published for the period from 1 January 2020 to March 31, 2021, with keywords of COVID, lung scans, and AI. After quality screening, 96 studies are included in this review. Based on their target application scenarios, the reviewed studies are grouped into three categories:automatic detection of coronavirus disease, infection segmentation, severity assessment and prognosis prediction. Latest AI solutions to process and analyze chest images for COVID-19 treatment, as well as their advance and limitations, are presented. In addition to the review of rapidly developing techniques, we also summarize publicly-accessible lung scan image sets. The paper ends with discussions of the challenges in current research and potential directions in designing effective computational solutions to fight against the COVID-19 pandemic in future.