Landet: an efficient physics-informed deep learning approach for automatic detection of anatomical landmarks and measurement of spinopelvic alignment.

Journal: Journal of orthopaedic surgery and research
PMID:

Abstract

PURPOSE: An efficient physics-informed deep learning approach for extracting spinopelvic measures from X-ray images is introduced and its performance is evaluated against manual annotations.

Authors

  • AliAsghar MohammadiNasrabadi
    Department of Systems Design Engineering, University of Waterloo, 200 University Ave W, Waterloo, ON, N2L 3G1, Canada. aliasgharmn@uwaterloo.ca.
  • Gemah Moammer
    Department of Spine Surgery, Grand River Hospital (GRH), 835 King St W, Kitchener, ON, N2G 1G3, Canada.
  • Ahmed Quateen
    Department of Spine Surgery, Grand River Hospital (GRH), 835 King St W, Kitchener, ON, N2G 1G3, Canada.
  • Kunal Bhanot
    Department of Surgery, McMaster University, 1280 Main Street West, Hamilton, ON, L8S 4K1, Canada.
  • John McPhee
    Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.