Deep learning with noise-to-noise training for denoising in SPECT myocardial perfusion imaging.

Journal: Medical physics
Published Date: Nov 23, 2020

Abstract

PURPOSE: Post-reconstruction filtering is often applied for noise suppression due to limited data counts in myocardial perfusion imaging (MPI) with single-photon emission computed tomography (SPECT). We study a deep learning (DL) approach for denoising in conventional SPECT-MPI acquisitions, and investigate whether it can be more effective for improving the detectability of perfusion defects compared to traditional postfiltering.

Authors

  • Junchi Liu
    Medical Imaging Research Center & Department of Electrical and Computer Engineering, Illinois Institute of Technology, Chicago, IL, 60616, USA.
  • Yongyi Yang
    Medical Imaging Research Center, Illinois Institute of Technology, 3440 S. Dearborn St., Suite 100, Chicago, IL, 60616, USA.
  • Miles N Wernick
    ADM Diagnostics, Northbrook, IL, USA.
  • P Hendrik Pretorius
  • Michael A King

Keywords

External Resources

Popular Topics
Recent Journals