Deep Learning Reconstruction at CT: Phantom Study of the Image Characteristics.

Journal: Academic radiology
PMID: 31818389

Abstract

OBJECTIVES: Noise, commonly encountered on computed tomography (CT) images, can impact diagnostic accuracy. To reduce the image noise, we developed a deep-learning reconstruction (DLR) method that integrates deep convolutional neural networks into image reconstruction. In this phantom study, we compared the image noise characteristics, spatial resolution, and task-based detectability on DLR images and images reconstructed with other state-of-the art techniques.

Authors

  • Toru Higaki
    Department of Diagnostic Radiology, Graduate School of Biomedical Sciences, Hiroshima University, Hiroshima, Japan.
  • Yuko Nakamura
    Department of Diagnostic Radiology, Graduate School of Biomedical and Health Science, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan.
  • Jian Zhou
    CTIQ, Canon Medical Research USA, Inc., Vernon Hills, 60061, USA.
  • Zhou Yu
  • Takuya Nemoto
    Canon Medical Systems, Otawara, Tochigi, Japan.
  • Fuminari Tatsugami
    Department of Diagnostic Radiology, Graduate School of Biomedical and Health Science, Hiroshima University, 1-2-3 Kasumi, Minami-ku, Hiroshima, 734-8551, Japan.
  • Kazuo Awai
    Department of Diagnostic Radiology, Graduate School of Biomedical Sciences, Hiroshima University, Hiroshima, Japan.

Keywords

External Resources

Popular Topics
Recent Journals