Can deep learning classify cerebral ultrasound images for the detection of brain injury in very preterm infants?

Journal: European radiology
PMID: 39212671

Abstract

OBJECTIVES: Cerebral ultrasound (CUS) is the main imaging screening tool in preterm infants. The aim of this work is to develop deep learning (DL) models that classify normal vs abnormal CUS to serve as a computer-aided detection tool providing timely interpretation of the scans.

Authors

  • Tahani Ahmad
    Department of Pediatric Radiology, IWK Health, Halifax, NS, Canada. tahani.ahmad@iwk.nshealth.ca.
  • Alessandro Guida
    Biomedical Translational Imaging Centre, Nova Scotia Health Authority and IWK Health Centre, Halifax, NS, Canada.
  • Samuel Stewart
    Department of Community Health and Epidemiology, Dalhousie University, Halifax, NS, Canada.
  • Noah Barrett
    Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada.
  • Xiang Jiang
    Faculty of Computer Science, Dalhousie University, Halifax, NS, Canada.
  • Michael Vincer
    Department of Pediatrics, Dalhousie University, Halifax, NS, Canada.
  • Jehier Afifi
    Department of Pediatrics, Dalhousie University, Halifax, NS, Canada.

Keywords

External Resources

Popular Topics
Recent Journals