Semi-supervised learning framework with shape encoding for neonatal ventricular segmentation from 3D ultrasound.

Journal: Medical physics
Published Date:

Abstract

BACKGROUND: Three-dimensional (3D) ultrasound (US) imaging has shown promise in non-invasive monitoring of changes in the lateral brain ventricles of neonates suffering from intraventricular hemorrhaging. Due to the poorly defined anatomical boundaries and low signal-to-noise ratio, fully supervised methods for segmentation of the lateral ventricles in 3D US images require a large dataset of annotated images by trained physicians, which is tedious, time-consuming, and expensive. Training fully supervised segmentation methods on a small dataset may lead to overfitting and hence reduce its generalizability. Semi-supervised learning (SSL) methods for 3D US segmentation may be able to address these challenges but most existing SSL methods have been developed for magnetic resonance or computed tomography (CT) images.

Authors

  • Zachary Szentimrey
    School of Engineering, University of Guelph, Guelph, Ontario, Canada.
  • Abdullah Al-Hayali
    School of Engineering, University of Guelph, Guelph, Ontario, Canada.
  • Sandrine de Ribaupierre
    Department of Clinical Neurological Sciences, London Health Sciences Centre, London, Ontario, Canada.
  • Aaron Fenster
    Imaging Research Laboratories, Robarts Research Institute, 100 Perth Drive, London, Ontario N6A 5K8, Canada.
  • Eranga Ukwatta
    School of Engineering, University of Guelph, Guelph, ON, Canada.