DeepACSA: Automatic Segmentation of Cross-Sectional Area in Ultrasound Images of Lower Limb Muscles Using Deep Learning.

Journal: Medicine and science in sports and exercise
Published Date: Aug 6, 2022

Abstract

PURPOSE: Muscle anatomical cross-sectional area (ACSA) can be assessed using ultrasound and images are usually evaluated manually. Here, we present DeepACSA, a deep learning approach to automatically segment ACSA in panoramic ultrasound images of the human rectus femoris (RF), vastus lateralis (VL), gastrocnemius medialis (GM) and lateralis (GL) muscles.

Authors

  • Paul Ritsche
    Department of Sport, Exercise and Health, University of Basel, Basel, SWITZERLAND.
  • Philipp Wirth
    Lightly AG, Zurich, SWITZERLAND.
  • Neil J Cronin
    Neuromuscular Research Centre, Faculty of Sport and Health Sciences, University of Jyväskylä, Jyväskylä, Finland.
  • Fabio Sarto
    Department of Biomedical Sciences, University of Padova, Padova, ITALY.
  • Marco V Narici
  • Oliver Faude
    Department of Sport, Exercise and Health, University of Basel, Basel, SWITZERLAND.
  • Martino V Franchi

Keywords

External Resources

Popular Topics
Recent Journals