Improving a Stochastic Algorithm for Regularized PET Image Reconstruction

Claire Delplancke, Mark Gurnell, Jonas Latz, Pawel J. Markiewicz, Carola Bibiane Schönlieb, Matthias J. Ehrhardt

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

1 Citation (SciVal)

Abstract

Positron Emission Tomography (PET) image reconstruction presents challenges related to the large scale of data to be processed, which affects reconstruction speed, and the need to include regularizers to improve image quality. Among the methods proposed to overcome these challenges, the recently introduced Stochastic Primal Dual Hybrid Gradient (SPDHG) algorithm combines the ability to deal with regularizers like Total Variation and to process large datasets by random subsampling. We present two contributions regarding the step-sizes of SPDHG: i) larger step-sizes facilitated by a new formula, and ii) a numerical method to calibrate, in the context of PET reconstruction, the tradeoff between primal and dual progression, which is common to all primal-dual algorithms. We validate improvements in speed reconstruction on real PET data from the Siemens Biograph mMR.

Original languageEnglish
Title of host publication2020 IEEE Nuclear Science Symposium and Medical Imaging Conference
PublisherIEEE
ISBN (Electronic)9781728176932
DOIs
Publication statusPublished - 12 Aug 2021
Event2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020 - Boston, USA United States
Duration: 31 Oct 20207 Nov 2020

Publication series

Name2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020
ISSN (Print)1082-3654
ISSN (Electronic)2577-0829

Conference

Conference2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020
Country/TerritoryUSA United States
CityBoston
Period31/10/207/11/20

Bibliographical note

Funding Information:
Manuscript received December 19, 2020. This work was funded by the UK EPSRC grant PET++: Improving Localisation, Diagnosis and Quantification in Clinical and Medical PET Imaging with Randomised Optimisation EP/S026045/1.

Publisher Copyright:
© 2020 IEEE

Funding

Manuscript received December 19, 2020. This work was funded by the UK EPSRC grant PET++: Improving Localisation, Diagnosis and Quantification in Clinical and Medical PET Imaging with Randomised Optimisation EP/S026045/1.

ASJC Scopus subject areas

  • Signal Processing
  • Radiology Nuclear Medicine and imaging
  • Nuclear and High Energy Physics

Fingerprint

Dive into the research topics of 'Improving a Stochastic Algorithm for Regularized PET Image Reconstruction'. Together they form a unique fingerprint.

Cite this