Deep learning for classification of thyroid nodules on ultrasound: validation on an independent dataset.

Journal: Clinical imaging
Published Date: Apr 24, 2023

Abstract

OBJECTIVES: The purpose is to apply a previously validated deep learning algorithm to a new thyroid nodule ultrasound image dataset and compare its performances with radiologists.

Authors

  • Jingxi Weng
    Department of Radiation Oncology, University of Florida, Gainesville, FL, USA.
  • Benjamin Wildman-Tobriner
    From the Department of Radiology, Duke University Hospital, 2301 Erwin Rd, Durham, NC 27701 (B.W.T., M.B., J.K.H., R.G.S., M.A.M.); Mallinckrodt Institute of Radiology, Washington University School of Medicine, St Louis, Mo (W.D.M., D.T.); and Department of Radiology, University of Alabama at Birmingham, Birmingham, Ala (F.N.T.).
  • Mateusz Buda
    Department of Radiology, Duke University School of Medicine, Durham, NC, USA; School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology, Stockholm, Sweden. Electronic address: buda@kth.se.
  • Jichen Yang
  • Lisa M Ho
    Department of Radiology, Duke University Medical Center, USA.
  • Brian C Allen
    Department of Radiology, Duke University Medical Center, USA.
  • Wendy L Ehieli
    Department of Radiology, Duke University Medical Center, USA.
  • Chad M Miller
    Department of Radiology, Duke University Medical Center, USA.
  • Jikai Zhang
    Department of Biostatistics and Bioinformatics (J.Z., R.H.), Duke University School of Medicine, Durham, NC.
  • Maciej A Mazurowski
    Department of Radiology, Duke University School of Medicine, 2424 Erwin Road, Suite 302, Durham, NC, 27705, USA.

Keywords

External Resources

Popular Topics
Recent Journals