Increasing angular sampling through deep learning for stationary cardiac SPECT image reconstruction.

Journal: Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology
Published Date: May 4, 2022

Abstract

BACKGROUND: The GE Discovery NM (DNM) 530c/570c are dedicated cardiac SPECT scanners with 19 detector modules designed for stationary imaging. This study aims to incorporate additional projection angular sampling to improve reconstruction quality. A deep learning method is also proposed to generate synthetic dense-view image volumes from few-view counterparts.

Authors

  • Huidong Xie
    School of Chemistry and Chemical Engineering, Division of Laboratory and Equipment Management, Xi'an University of Architecture and Technology Xi'an 710055 Shaanxi China xiehuidong@tsinghua.org.cn.
  • Stephanie Thorn
    Department of Internal Medicine (Cardiology), Yale University, New Haven, CT, USA.
  • Xiongchao Chen
    Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
  • Bo Zhou
    Department of Neurology, The Third People's Hospital of Yibin, Yibin, China.
  • Hui Liu
    Institute of Urology and Nephrology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China.
  • Zhao Liu
    Centre for Nanohealth, Swansea University Medical School, Swansea, UK.
  • Supum Lee
    Department of Internal Medicine (Cardiology), Yale University, New Haven, CT, USA.
  • Ge Wang
    Biomedical Imaging Center, Rensselaer Polytechnic Institute, Troy, New York, USA.
  • Yi-Hwa Liu
    Department of Internal Medicine (Cardiology), Yale University, New Haven, CT, USA.
  • Albert J Sinusas
    Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, New Haven, Connecticut.
  • Chi Liu

Keywords

External Resources

Popular Topics
Recent Journals