Deep learning-based denoising in projection-domain and reconstruction-domain for low-dose myocardial perfusion SPECT.

Journal: Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology
PMID: 35982208

Abstract

BACKGROUND: Low-dose (LD) myocardial perfusion (MP) SPECT suffers from high noise level, leading to compromised diagnostic accuracy. Here we investigated the denoising performance for MP-SPECT using a conditional generative adversarial network (cGAN) in projection-domain (cGAN-prj) and reconstruction-domain (cGAN-recon).

Authors

  • Jingzhang Sun
    Biomedical Imaging Laboratory (BIG), Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Macau SAR, China.
  • Han Jiang
    Second Affiliated Hospital, Nanchang University, Nanchang, China. jhan3939@sina.com.
  • Yu Du
    State Key Lab of CAD&CG, College of Computer Science and Technology, Zhejiang University, Hangzhou, China.
  • Chien-Ying Li
    Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan, ROC.
  • Tung-Hsin Wu
    Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan, ROC.
  • Yi-Hwa Liu
    Department of Internal Medicine (Cardiology), Yale University, New Haven, CT, USA.
  • Bang-Hung Yang
    Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei, Taiwan, ROC. bhyang@vghtpe.gov.tw.
  • Greta S P Mok
    Biomedical Imaging Laboratory (BIG), Department of Electrical and Computer Engineering, Faculty of Science and Technology, University of Macau, Taipa, Macao SAR, China.

Keywords

External Resources

Popular Topics
Recent Journals