Leg-Length Discrepancy Variability on Standard Anteroposterior Pelvis Radiographs: An Analysis Using Deep Learning Measurements.

Journal: The Journal of arthroplasty
PMID:

Abstract

BACKGROUND: Leg-length discrepancy (LLD) is a critical factor in component selection and placement for total hip arthroplasty. However, LLD radiographic measurements are subject to variation based on the femoral/pelvic landmarks chosen. This study leveraged deep learning (DL) to automate LLD measurements on pelvis radiographs and compared LLD based on several anatomically distinct landmarks.

Authors

  • Seong Jun Jang
    Weill Cornell College of Medicine, New York, New York; Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York.
  • Kyle N Kunze
    Department of Orthopedic Surgery, Hospital for Special Surgery, New York, NY, USA.
  • Troy D Bornes
    Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York; Division of Orthopaedic Surgery, Royal Alexandra Hospital, University of Alberta, Edmonton, Alberta, Canada.
  • Christopher G Anderson
    Stavros Niarchos Foundation Complex Joint Reconstruction Center, Hospital for Special Surgery, New York, New York.
  • David J Mayman
    Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York; Adult Reconstruction and Joint Replacement Service, Hospital for Special Surgery, New York, New York.
  • Seth A Jerabek
    Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York; Adult Reconstruction and Joint Replacement Service, Hospital for Special Surgery, New York, New York.
  • Jonathan M Vigdorchik
    Department of Orthopedic Surgery, Hospital for Special Surgery, New York, New York; Adult Reconstruction and Joint Replacement Service, Hospital for Special Surgery, New York, New York.
  • Peter K Sculco
    The Stavros Niarchos Foundation Complex Joint Reconstruction Center, Department of Orthopaedic Surgery, Hospital for Special Surgery, Washington, District of Columbia, USA.