Your browser doesn't support javascript.
Fast automated detection of COVID-19 from medical images using convolutional neural networks.
Liang, Shuang; Liu, Huixiang; Gu, Yu; Guo, Xiuhua; Li, Hongjun; Li, Li; Wu, Zhiyuan; Liu, Mengyang; Tao, Lixin.
  • Liang S; School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China.
  • Liu H; School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, 100083, China.
  • Gu Y; School of Automation, Guangdong University of Petrochemical Technology, Maoming, 525000, Guangdong, China. guyu@mail.buct.edu.cn.
  • Guo X; Beijing Advanced Innovation Center for Soft Matter Science and Engineering, Beijing University of Chemical Technology, Beijing, 100029, China. guyu@mail.buct.edu.cn.
  • Li H; Department of Chemistry, Institute of Inorganic and Analytical Chemistry, Goethe University, 60438, Frankfurt, Germany. guyu@mail.buct.edu.cn.
  • Li L; Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University, Beijing, China.
  • Wu Z; Beijing Municipal Key Laboratory of Clinical Epidemiology, Capital Medical University, Beijing, China.
  • Liu M; Beijing Youan Hospital, Capital Medical University, Beijing, China.
  • Tao L; Beijing Youan Hospital, Capital Medical University, Beijing, China.
Commun Biol ; 4(1): 35, 2021 01 04.
Article in English | MEDLINE | ID: covidwho-1065967
ABSTRACT
Coronavirus disease 2019 (COVID-19) is a global pandemic posing significant health risks. The diagnostic test sensitivity of COVID-19 is limited due to irregularities in specimen handling. We propose a deep learning framework that identifies COVID-19 from medical images as an auxiliary testing method to improve diagnostic sensitivity. We use pseudo-coloring methods and a platform for annotating X-ray and computed tomography images to train the convolutional neural network, which achieves a performance similar to that of experts and provides high scores for multiple statistical indices (F1 scores > 96.72% (0.9307, 0.9890) and specificity >99.33% (0.9792, 1.0000)). Heatmaps are used to visualize the salient features extracted by the neural network. The neural network-based regression provides strong correlations between the lesion areas in the images and five clinical indicators, resulting in high accuracy of the classification framework. The proposed method represents a potential computer-aided diagnosis method for COVID-19 in clinical practice.
Subject(s)

Full text: Available Collection: International databases Database: MEDLINE Main subject: Radiographic Image Interpretation, Computer-Assisted / Tomography, X-Ray Computed / Neural Networks, Computer / Deep Learning / SARS-CoV-2 / COVID-19 Type of study: Diagnostic study / Observational study / Prognostic study Limits: Humans Language: English Journal: Commun Biol Year: 2021 Document Type: Article Affiliation country: S42003-020-01535-7

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Main subject: Radiographic Image Interpretation, Computer-Assisted / Tomography, X-Ray Computed / Neural Networks, Computer / Deep Learning / SARS-CoV-2 / COVID-19 Type of study: Diagnostic study / Observational study / Prognostic study Limits: Humans Language: English Journal: Commun Biol Year: 2021 Document Type: Article Affiliation country: S42003-020-01535-7