Deep learning for segmentation of colorectal carcinomas on endoscopic ultrasound.

Journal: Techniques in coloproctology
PMID:

Abstract

BACKGROUND: Bowel-preserving local resection of early rectal cancer is less successful if the tumor infiltrates the muscularis propria as opposed to submucosal infiltration only. Magnetic resonance imaging currently lacks the spatial resolution to provide a reliable estimation of the infiltration depth. Endoscopic ultrasound (EUS) has better resolution, but its interpretation is investigator dependent. We hypothesize that automated image segmentation of EUS could be a way to standardize EUS interpretation.

Authors

  • F van den Noort
    Department of Applied Mathematics, Technical Medical Center, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, the Netherlands. f.vandennoort@utwente.nl.
  • F Ter Borg
    Department of Gastroenterology & Hepatology, Deventer Hospital, Deventer, the Netherlands.
  • A Guitink
    Department of Gastroenterology & Hepatology, Deventer Hospital, Deventer, the Netherlands.
  • J Faber
    Department of Epidemiology, Deventer Hospital, Deventer, the Netherlands.
  • J M Wolterink
    Department of Applied Mathematics, Technical Medical Center, University of Twente, Drienerlolaan 5, 7522 NB, Enschede, the Netherlands.