Published April 2021 | Version v1
Journal article

Texture feature-based machine learning classifier could assist in the diagnosis of COVID-19

  • 1. Beijing Municipal Key Laboratory of Clinical Epidemiology, Capital Medical University, Beijing (China)
  • 2. Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University, Beijing (China)
  • 3. Beijing Youan Hospital, Capital Medical University, Beijing (China)

Description

Highlights: • COVID-19 patients show similar clinical manifestations as other pneumonias. • Specific pattern of CT texture features attributes to COVID-19. • Texture feature overrides clinical sign given the recognition of COVID-19. • Radiomics-based machine learning assists in the diagnosis of COVID-19. Differentiating COVID-19 from other acute infectious pneumonias rapidly is challenging at present. This study aims to improve the diagnosis of COVID-19 using computed tomography (CT).

Availability note (English)

Available from http://dx.doi.org/10.1016/j.ejrad.2021.109602

Additional details

Identifiers

DOI
10.1016/j.ejrad.2021.109602;
PII
S0720048X21000826;

Publishing Information

Journal Title
European Journal of Radiology
Journal Volume
137
Journal Page Range
vp.
ISSN
0720-048X
CODEN
EJRADR

Optional Information

Copyright
Copyright (c) 2021 Elsevier B.V. All rights reserved.