Development of a deep learning method to identify acute ischaemic stroke lesions on brain CT.

Journal: Stroke and vascular neurology
Published Date: Aug 26, 2025

Abstract

BACKGROUND: CT is commonly used to image patients with ischaemic stroke but radiologist interpretation may be delayed. Machine learning techniques can provide rapid automated CT assessment but are usually developed from annotated images which necessarily limits the size and representation of development data sets. We aimed to develop a deep learning (DL) method using CT brain scans that were labelled but not annotated for the presence of ischaemic lesions.

Authors

  • Alessandro Fontanella
    The University of Edinburgh School of Informatics, Edinburgh, UK A.Fontanella@sms.ed.ac.uk.
  • Wenwen Li
    School of Geographical Sciences and Urban Planning, Arizona State University, Tempe, AZ 85287, USA.
  • Grant Mair
    Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, UK.
  • Antreas Antoniou
  • Eleanor Platt
    The University of Edinburgh School of Informatics, Edinburgh, UK.
  • Paul Armitage
    Academic Unit of Radiology, Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, United Kingdom.
  • Emanuele Trucco
  • Joanna M Wardlaw
    Department of Neuroimaging Sciences, Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, United Kingdom.
  • Amos Storkey

Keywords

External Resources

Popular Topics
Recent Journals