A deep learning pipeline for systematic and accurate vertebral fracture reporting in computed tomography.

Journal: Clinical radiology
PMID: 39970769

Abstract

AIM: Spine fractures are a frequent and relevant diagnosis, but systematic documentation is time-consuming and sometimes overlooked. A deep learning pipeline for opportunistic fracture detection in computed tomography (CT) spine images of varying field-of-views is introduced.

Authors

  • C Glessgen
    Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland; Department of Radiology, Geneva University Hospitals, Geneva, Switzerland. Electronic address: carl.glessgen@hug.ch.
  • J Cyriac
    Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland. Electronic address: Joshy.cyriac@usb.ch.
  • S Yang
    Neural Engineering Data Consortium, Temple University, Philadelphia, Pennsylvania, USA, {scott.yang, silvia.lopez, meysam, obeid, picone}@temple.edu.
  • S Manneck
    Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland. Electronic address: Sebastian.manneck@gzf.ch.
  • H Wichtmann
    Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland. Electronic address: Hildegard.wichtmann@gmail.com.
  • A M Fischer
    University Department of Geriatric Medicine, Felix Platter, Basel, Switzerland. Electronic address: Andreasm.fischer@felixplatter.ch.
  • H-C Breit
    Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland. Electronic address: Hanns-christian.breit@usb.ch.
  • D Harder
    Department of Radiology, University Hospital Basel, University of Basel, Basel, Switzerland. Electronic address: Dorothee.harder@usb.ch.

Keywords

External Resources

Popular Topics
Recent Journals