Towards trustworthy artificial intelligence in musculoskeletal medicine: A narrative review on uncertainty quantification.

Journal: Knee surgery, sports traumatology, arthroscopy : official journal of the ESSKA
Published Date:

Abstract

INTRODUCTION: Deep learning (DL) models have achieved remarkable performance in musculoskeletal (MSK) medical imaging research, yet their clinical integration remains hindered by their black-box nature and the absence of reliable confidence measures. Uncertainty quantification (UQ) seeks to bridge this gap by providing each DL prediction with a calibrated estimate of uncertainty, thereby fostering clinician trust and safer deployment.

Authors

  • Amir M Vahdani
    Image Guided Surgery Lab, Research Center for Biomedical Technologies and Robotics, Advanced Medical Technologies and Equipment Institute, Imam Khomeini Hospital Complex, Tehran University of Medical Sciences, Tehran, Iran.
  • Moein Shariatnia
    Tehran University of Medical Sciences, School of Medicine, Tehran, Iran.
  • Pranav Rajpurkar
    Harvard Medical School, Department of Biomedical Informatics, Cambridge, MA, 02115, US.
  • Ayoosh Pareek
    Department of Orthopaedic Surgery and Sports Medicine, Mayo Clinic, Rochester, Minnesota, USA.

Keywords

No keywords available for this article.