loading page

An Investigation of Stochastic Variance Reduction Algorithms for 3D Penalised PET Image Reconstruction
  • +8
  • Robert Twyman ,
  • Simon Arridge ,
  • Zeljko Kereta ,
  • Bangti Jin ,
  • Ludovica Brusaferri ,
  • Sangtae Ahn ,
  • Charles Stearns ,
  • Brian Hutton ,
  • Irene A. Burger ,
  • Fotis Kotasidis ,
  • Kris Thielemans
Robert Twyman
Author Profile
Simon Arridge
Author Profile
Zeljko Kereta
Author Profile
Bangti Jin
Author Profile
Ludovica Brusaferri
Author Profile
Sangtae Ahn
Author Profile
Charles Stearns
Author Profile
Brian Hutton
Author Profile
Irene A. Burger
Author Profile
Fotis Kotasidis
Author Profile
Kris Thielemans
Author Profile

Abstract

Application of stochastic variance reduction algorithms to iterative PET reconstruction. We investigated the SAGA and SVRG algorithms for non-TOF PET image reconstruction. Both similated data and a patient data sets were used in the analysis. We found that the stochastic algorithms can improve convergence rate and eliminate behaviour, commonly know as limit cycle behaviour, from PET reconstruction within 5 epochs.