Gastrointestinal bleeding detection on digital subtraction angiography using convolutional neural networks with and without temporal information.

Journal: Diagnostic and interventional radiology (Ankara, Turkey)
Published Date: Aug 7, 2025

Abstract

PURPOSE: Digital subtraction angiography (DSA) offers a real-time approach to locating lower gastrointestinal (GI) bleeding. However, many sources of bleeding are not easily visible on angiograms. This investigation aims to develop a machine learning tool that can locate GI bleeding on DSA prior to transarterial embolization.

Authors

  • Derek Smetanick
    The University of Arizona College of Medicine, Department of Interventional Radiology, Tucson, USA.
  • Sailendra Naidu
    Mayo Clinic College of Medicine and Science, Department of Radiology, Phoenix, USA.
  • Alex Wallace
    Mayo Clinic College of Medicine and Science, Department of Radiology, Phoenix, USA.
  • M-Grace Knuttinen
    Mayo Clinic College of Medicine and Science, Department of Radiology, Phoenix, USA.
  • Indravadan Patel
    Mayo Clinic College of Medicine and Science, Department of Radiology, Phoenix, USA.
  • Sadeer Alzubaidi
    Mayo Clinic College of Medicine and Science, Department of Radiology, Phoenix, USA.

Keywords

External Resources

Popular Topics
Recent Journals