Translating Simulated Images to Real Radiograph using Generative Adversarial Networks: Estimation of Pelvic Tilt from Real Images

DOI
  • HIASA Yuta
    Division of Information Science, Nara Institute of Science and Technology
  • OTAKE Yoshito
    Division of Information Science, Nara Institute of Science and Technology
  • MATSUOKA Takumi
    Division of Information Science, Nara Institute of Science and Technology
  • TAKAO Masaki
    Graduate School of Medicine, Osaka University
  • SUGANO Nobuhiko
    Graduate School of Medicine, Osaka University
  • SATO Yoshinobu
    Division of Information Science, Nara Institute of Science and Technology

Bibliographic Information

Other Title
  • GANを用いた実X線画像からの疑似X線画像変換 ―骨盤傾斜角推定手法の実画像への適用―

Description

<p>In total hip arthroplasty, pelvic tilt in standing position is important in preoperative planning of the optimum placement angle of the cup. However, such tilt angle cannot be accessed from CT images scanned in the supine position. Previous study has been focused on radiographs scanned in the standing position. 2D-3D registration between a radiograph and a patient-specific CT image achieved that, but its application was limited due to the radiation exposure at CT acquisition. To solve this problem, we have proposed a method to estimate pelvic tilt angle from only single radiograph using convolution neural networks and tested with simulated images. However, its application to real radiographs is difficult due to the influence of noises and the X-ray spectrum. In this paper, we introduce estimation of pelvic tilt from real radiographs using a generative adversarial networks translating a real radiograph to a simulated image.</p>

Journal

  • Medical Imaging Technology

    Medical Imaging Technology 37 (3), 125-129, 2019-05-25

    The Japanese Society of Medical Imaging Technology

Related Projects

See more

Keywords

Details 詳細情報について

  • CRID
    1390845713076448256
  • NII Article ID
    130007662439
  • DOI
    10.11409/mit.37.125
  • ISSN
    21853193
    0288450X
  • Text Lang
    ja
  • Data Source
    • JaLC
    • CiNii Articles
    • KAKEN
  • Abstract License Flag
    Disallowed

Report a problem

Back to top