Feasibility of Bone Mineral Density and Bone Microarchitecture Assessment Using Deep Learning With a Convolutional Neural Network.

Journal: Journal of computer assisted tomography
PMID: 37185012

Abstract

OBJECTIVES: We evaluated the feasibility of using deep learning with a convolutional neural network for predicting bone mineral density (BMD) and bone microarchitecture from conventional computed tomography (CT) images acquired by multivendor scanners.

Authors

  • Kazuki Yoshida
    Brigham and Women's Hospital and Harvard Medical School, Boston, Massachusetts.
  • Yuki Tanabe
    Department of Radiology, Ehime University Graduate School of Medicine, Shitsukawa, Toon, Ehime, 791-0295, Japan. yuki.tanabe.0225@gmail.com.
  • Hikaru Nishiyama
    From the Departments of Radiology.
  • Takuya Matsuda
    Medical Informatics.
  • Hidetaka Toritani
    Ehime University School of Medicine, Shitsukawa, Toon City, Japan.
  • Takuya Kitamura
    From the Departments of Radiology.
  • Shinichiro Sakai
    Orthopedic Surgery, Ehime University Graduate School of Medicine.
  • Kunihiko Watamori
    Orthopedic Surgery, Ehime University Graduate School of Medicine.
  • Masaki Takao
  • Eizen Kimura
    Medical Informatics.
  • Teruhito Kido
    Department of Radiology, Ehime University Graduate School of Medicine, Shitsukawa, Toon, Ehime, 791-0295, Japan.

Keywords

External Resources

Popular Topics
Recent Journals