Computer Vision For COVID-19 Control: A Survey

TL;DR

The paper surveys computer vision efforts against COVID-19, focusing on diagnostic imaging, prevention/control, and clinical management. It systematically catalogs representative CT- and X-ray–based methods, plus prevention and management applications, and documents available datasets and code resources. The authors highlight performance ranges across models and emphasize rapid, open dissemination of preprint work in a time-critical setting. The work provides a structured, resource-rich baseline to accelerate future CV research and deployment for COVID-19 control.

Abstract

The COVID-19 pandemic has triggered an urgent need to contribute to the fight against an immense threat to the human population. Computer Vision, as a subfield of Artificial Intelligence, has enjoyed recent success in solving various complex problems in health care and has the potential to contribute to the fight of controlling COVID-19. In response to this call, computer vision researchers are putting their knowledge base at work to devise effective ways to counter COVID-19 challenge and serve the global community. New contributions are being shared with every passing day. It motivated us to review the recent work, collect information about available research resources and an indication of future research directions. We want to make it available to computer vision researchers to save precious time. This survey paper is intended to provide a preliminary review of the available literature on the computer vision efforts against COVID-19 pandemic.

Figures (9)

• Figure 1: A portrayal of current increase in research articles about coronavirus related research. Adapted fromref6.
• Figure 2: A classification Computer Vision Approaches for COVUD-19 Control
• Figure 3: CT images adapted fromref10ref20 portray CT features related to COVID-19. Ground glass opacities (top) and ground glass halo (bottom).
• Figure 4: Architectural diagram of COVID-Netref54. High architectural diversity and selective long-range connectivity can be observed.
• Figure 5: Chest radiographs of an elderly male patient from Wuhan, China, who travelled to Hong Kong, China. These are 3 chest radiographs selected out of the daily chest radiographs acquired in this patient. The consolidation in the right lower zone on day 0 persist into day 4 with new consolidative changes in the right midzone periphery and perihilar region. This midzone change improves on the day 7 film. Image adapted fromref52.