Uncertainty-Aware Deep Learning Characterization of Knee Radiographs for Large-Scale Registry Creation.

Journal: The Journal of arthroplasty
PMID: 39477040

Abstract

BACKGROUND: We present an automated image ingestion pipeline for a knee radiography registry, integrating a multilabel image-semantic classifier with conformal prediction-based uncertainty quantification and an object detection model for knee hardware.

Authors

  • Kellen L Mulford
    Department of Orthopedic Surgery, Orthopedic Surgery Artificial Intelligence Laboratory, Mayo Clinic, Rochester, Minnesota.
  • Austin F Grove
    Mayo Clinic, Rochester, Minnesota.
  • Elizabeth S Kaji
    Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota.
  • Pouria Rouzrokh
    Department of Radiology, Mayo Clinic, Radiology Informatics Laboratory, Rochester, MN.
  • Ryan D Roman
    Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota.
  • Mete Kremers
    Orthopedic Surgery Artificial Intelligence Laboratory (OSAIL), Department of Orthopedic Surgery, Mayo Clinic, Rochester, Minnesota.
  • Hilal Maradit Kremers
    Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN; Department of Health Sciences Research, Mayo Clinic, Rochester, MN.
  • Michael J Taunton
    Department of Health Sciences Research, Mayo Clinic, Rochester, MN; Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN.
  • Cody C Wyles
    Department of Orthopedic Surgery, Mayo Clinic, Rochester, MN.

Keywords

External Resources

Popular Topics
Recent Journals