Deep Learning-Based Venous Gas Emboli Grade Classification in Doppler Ultrasound Audio Recordings.

Journal: IEEE transactions on bio-medical engineering
PMID: 36301781

Abstract

OBJECTIVE: Doppler ultrasound (DU) is used to detect venous gas emboli (VGE) post dive as a marker of decompression stress for diving physiology research as well as new decompression procedure validation to minimize decompression sickness risk. In this article, we propose the first deep learning model for VGE grading in DU audio recordings.

Authors

  • Arian Azarang
    Department of Electrical and Computer Engineering, The University of Texas at Dallas, Richardson, TX 75080, USA.
  • David Q Le
  • Andrew H Hoang
  • S Lesley Blogg
  • Paul A Dayton
  • Rachel M Lance
  • Michael Natoli
  • Alan Gatrell
  • Frauke Tillmans
  • Richard E Moon
  • Peter Lindholm
    Department of Physiology and Pharmacology, Karolinska Institutet, Stockholm, Sweden.
  • Virginie Papadopoulou

Keywords

External Resources

Popular Topics
Recent Journals