Exploring the performance and explainability of fine-tuned BERT models for neuroradiology protocol assignment.

Journal: BMC medical informatics and decision making
PMID: 38326769

Abstract

BACKGROUND: Deep learning has demonstrated significant advancements across various domains. However, its implementation in specialized areas, such as medical settings, remains approached with caution. In these high-stake environments, understanding the model's decision-making process is critical. This study assesses the performance of different pretrained Bidirectional Encoder Representations from Transformers (BERT) models and delves into understanding its decision-making within the context of medical image protocol assignment.

Authors

  • Salmonn Talebi
    Molecular Cell Biomechanics Laboratory, Departments of Bioengineering and Mechanical Engineering, University of California, 208A Stanley Hall #1762, Berkeley, CA, 94720-1762, USA.
  • Elizabeth Tong
    Department of Radiology, Stanford University, Stanford, California, USA.
  • Anna Li
    Stanford University, Stanford, CA, USA.
  • Ghiam Yamin
    Department of Radiology, University of California San Diego School of Medicine, La Jolla, CA.
  • Greg Zaharchuk
    Stanford University, Stanford CA 94305, USA.
  • Mohammad R K Mofrad
    Molecular Cell Biomechanics Laboratory, Departments of Bioengineering and Mechanical Engineering, University of California, Berkeley, California 94720, United States of America.

Keywords

External Resources

Popular Topics
Recent Journals