Pre-trained convolutional neural network with transfer learning by artificial illustrated images classify power Doppler ultrasound images of rheumatoid arthritis joints.

Journal: The Journal of international medical research
PMID: 39904596

Abstract

OBJECTIVE: To study the classification performance of a pre-trained convolutional neural network (CNN) with transfer learning by artificial joint ultrasonography images in rheumatoid arthritis (RA).

Authors

  • Jun Fukae
    Department of Rheumatology, Kuriyama Red Cross Hospital, Hokkaido, Japan.
  • Yoshiharu Amasaki
    Department of Rheumatology, Kuriyama Red Cross Hospital, Hokkaido, Japan.
  • Yuichiro Fujieda
    Department of Rheumatology, Endocrinology and Nephrology, Faculty of Medicine and Graduate School of Medicine, Hokkaido University, Sapporo, Japan.
  • Yuki Sone
    Department of Rheumatology, Kuriyama Red Cross Hospital, Hokkaido, Japan.
  • Ken Katagishi
    Department of Rheumatology, Kuriyama Red Cross Hospital, Hokkaido, Japan.
  • Tatsunori Horie
    Department of Radiological Technology, Hokkaido University Hospital, Sapporo, Japan.
  • Tamotsu Kamishima
    Faculty of Health Sciences, Hokkaido University, Kita-ku, Sapporo, Japan.
  • Tatsuya Atsumi
    Division of Rheumatology, Endocrinology and Nephrology, Hokkaido University Graduate School of Medicine , Sapporo , Japan.

Keywords

External Resources

Popular Topics
Recent Journals