Generative AI in orthopedics: an explainable deep few-shot image augmentation pipeline for plain knee radiographs and Kellgren-Lawrence grading.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date:

Abstract

OBJECTIVES: Recently, deep learning medical image analysis in orthopedics has become highly active. However, progress has been restricted by the absence of large-scale and standardized ground-truth images. To the best of our knowledge, this study is the first to propose an innovative solution, namely a deep few-shot image augmentation pipeline, that addresses this challenge by synthetically generating knee radiographs for training downstream tasks, with a specific focus on knee osteoarthritis Kellgren-Lawrence (KL) grading.

Authors

  • Nickolas Littlefield
    Intelligent Systems Program, University of Pittsburgh, Pittsburgh, PA, 15213, USA.
  • Soheyla Amirian
    School of Computing, University of Georgia, Athens, GA, 30602 USA.
  • Jacob Biehl
    School of Computing and Information, University of Pittsburgh, Pittsburgh, PA 15260, United States.
  • Edward G Andrews
    University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA; Department of Neurological Surgery, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania, USA.
  • Michael Kann
    School of Medicine, University of Pittsburgh, Pittsburgh, PA 15213, United States.
  • Nicole Myers
    School of Health and Rehabilitation Sciences, University of Pittsburgh, PA, USA.
  • Leah Reid
    Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA 15260, United States.
  • Adolph J Yates
    Department of Orthopaedic Surgery, University of Pittsburgh, Pittsburgh, PA 15213, United States.
  • Brian J McGrory
    Department of Orthopaedic Surgery, Tufts University, Medford, MA 02111, United States.
  • Bambang Parmanto
    Department of Health Information Management, University of Pittsburgh, Pittsburgh, PA 15260, United States.
  • Thorsten M Seyler
    Department of Orthopaedic Surgery, Duke University, Durham, NC27560, United States.
  • Johannes F Plate
    Department of Orthopaedic Surgery, University of Pittsburgh, Pittsburgh, 15213, USA. platefj2@upmc.edu.
  • Hooman H Rashidi
    Department of Pathology, University of Pittsburgh Medical Center, Pittsburgh, Pennsylvania; Computational Pathology and AI Center of Excellence (CPACE), University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania. Electronic address: rashidihh@upmc.edu.
  • Ahmad P Tafti
    School of Health and Rehabilitation Sciences, University of Pittsburgh, Pittsburgh, PA 15260, USA.