EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19

Hersh Sagreiya iD, Michael A Jacobs, Alireza Akhbardeh

Diagnostics · 16.08.2023 · 13 (16) · 2692

DOI: 10.3390/diagnostics13162692 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 16.08.2023. Verfasst von Hersh Sagreiya und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Radiological Society of North America, American Lung Association COVID-19 and Emerging Respiratory Viruses Research Award, National Institutes of Health.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

COVID-19 is an ongoing global health pandemic. Although COVID-19 can be diagnosed with various tests such as PCR, these tests do not establish pulmonary disease burden. Whereas point-of-care lung ultrasound (POCUS) can directly assess the severity of characteristic pulmonary findings of COVID-19, the advantage of using US is that it is inexpensive, portable, and widely available for use in many clinical settings. For automated assessment of pulmonary findings, we have developed an unsupervised learning technique termed the calculated lung ultrasound (CLU) index. The CLU can quantify various types of lung findings, such as A or B lines, consolidations, and pleural effusions, and it uses these findings to calculate a CLU index score, which is a quantitative measure of pulmonary disease burden. This is accomplished using an unsupervised, patient-specific approach that does not require training on a large dataset. The CLU was tested on 52 lung ultrasound examinations from several institutions. CLU demonstrated excellent concordance with radiologist findings in different pulmonary disease states. Given the global nature of COVID-19, the CLU would be useful for sonographers and physicians in resource-strapped areas with limited ultrasound training and diagnostic capacities for more accurate assessment of pulmonary status.

Schlagwörter

Stichwörter der Autor:innen

COVID-19POCUScomputer visionmachine learningtreatment effectivenessultrasoundunsupervised learning

Autor:innen und Institutionen

  • Department of Radiology, Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA 19104, USA.
  • The Russell H. Morgan Department of Radiology and Radiological Science, The Johns Hopkins University School of Medicine, Baltimore, MD 21205, USA.
  • Department of Diagnostic and Interventional Imaging, The University of Texas Health Science Center, Houston, TX 77030, USA.
  • Ambient Digital LLC, Daly City, CA 94014, USA.

ORCID-Profile: Hersh Sagreiya

Förderung

  • Radiological Society of North America
  • American Lung Association COVID-19 and Emerging Respiratory Viruses Research Award
  • National Institutes of Health

Zitieren

APA

Sagreiya, H., Jacobs, M. A., & Akhbardeh, A. (2023). Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19. Diagnostics, 13(16), 2692. https://doi.org/10.3390/diagnostics13162692

Vancouver

Sagreiya H, Jacobs MA, Akhbardeh A. Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19. Diagnostics. 2023;13(16):2692. doi:10.3390/diagnostics13162692

BibTeX
@article{Sagreiya2023,
  author = {Sagreiya, Hersh and Jacobs, Michael A and Akhbardeh, Alireza},
  title = {Automated Lung Ultrasound Pulmonary Disease Quantification Using an Unsupervised Machine Learning Technique for COVID-19},
  journal = {Diagnostics},
  year = {2023},
  volume = {13},
  number = {16},
  pages = {2692},
  doi = {10.3390/diagnostics13162692}
}
Kostenlos starten →