Deep learning-based algorithm improved radiologists' performance in bone metastases detection on CT.

Journal: European radiology
Published Date:

Abstract

OBJECTIVES: To develop and evaluate a deep learning-based algorithm (DLA) for automatic detection of bone metastases on CT.

Authors

  • Shunjiro Noguchi
    Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan. Electronic address: noguchi.shunjiro.c95@kyoto-u.jp.
  • Mizuho Nishio
    Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan.
  • Ryo Sakamoto
    Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, 54 Kawahara-cho, Shogoin, Sakyo-ku, Kyoto 606-8507, Japan.
  • Masahiro Yakami
    Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan.
  • Koji Fujimoto
    Human Brain Research Center, Kyoto University Graduate School of Medicine, Kyoto, Japan.
  • Yutaka Emoto
    Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, 54 Shogoin-kawahara-cho, Sakyo-ku, Kyoto, 606-8507, Japan.
  • Takeshi Kubo
    Department of Diagnostic Imaging and Nuclear Medicine, Kyoto University Graduate School of Medicine, Kyoto, Japan.
  • Yoshio Iizuka
    Medical Products Technology Development Center, R&D Headquarters, Canon Inc., 3-30-2, Shimomaruko, Ohta-ku, Tokyo, 146-8501, Japan.
  • Keita Nakagomi
    Medical Products Technology Development Center, R&D Headquarters, Canon Inc, Tokyo, Japan.
  • Kazuhiro Miyasa
    Medical Products Technology Development Center, R&D Headquarters, Canon Inc., 3-30-2, Shimomaruko, Ohta-ku, Tokyo, 146-8501, Japan.
  • Kiyohide Satoh
    Medical Products Technology Development Center, R&D Headquarters, Canon Inc., 3-30-2, Shimomaruko, Ohta-ku, Tokyo, 146-8501, Japan.
  • Yuji Nakamoto
    Department of Diagnostic Imaging and Nuclear Medicine, Graduate School of Medicine, Kyoto University.