Improving a Stochastic Algorithm for Regularized PET Image Reconstruction

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

doi:10.1109/NSS/MIC42677.2020.9508013

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 proceeding › Chapter 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 language	English
Title of host publication	2020 IEEE Nuclear Science Symposium and Medical Imaging Conference
Publisher	IEEE
ISBN (Electronic)	9781728176932
DOIs	https://doi.org/10.1109/NSS/MIC42677.2020.9508013
Publication status	Published - 12 Aug 2021
Event	2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020 - Boston, USA United States Duration: 31 Oct 2020 → 7 Nov 2020

Publication series

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

Conference

Conference	2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020
Country/Territory	USA United States
City	Boston
Period	31/10/20 → 7/11/20

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

Access to Document

10.1109/NSS/MIC42677.2020.9508013

Cite this

Delplancke, C., Gurnell, M., Latz, J., Markiewicz, P. J., Schönlieb, C. B., & Ehrhardt, M. J. (2021). Improving a Stochastic Algorithm for Regularized PET Image Reconstruction. In 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference Article 9508013 (2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020). IEEE. https://doi.org/10.1109/NSS/MIC42677.2020.9508013

Improving a Stochastic Algorithm for Regularized PET Image Reconstruction. / Delplancke, Claire; Gurnell, Mark; Latz, Jonas et al.
2020 IEEE Nuclear Science Symposium and Medical Imaging Conference. IEEE, 2021. 9508013 (2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020).

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

Delplancke, C, Gurnell, M, Latz, J, Markiewicz, PJ, Schönlieb, CB & Ehrhardt, MJ 2021, Improving a Stochastic Algorithm for Regularized PET Image Reconstruction. in 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference., 9508013, 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020, IEEE, 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020, Boston, USA United States, 31/10/20. https://doi.org/10.1109/NSS/MIC42677.2020.9508013

@inproceedings{1492c4b0afbb4cfeb19af88c1ac22b45,

title = "Improving a Stochastic Algorithm for Regularized PET Image Reconstruction",

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.",

author = "Claire Delplancke and Mark Gurnell and Jonas Latz and Markiewicz, {Pawel J.} and Sch{\"o}nlieb, {Carola Bibiane} and Ehrhardt, {Matthias J.}",

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: {\textcopyright} 2020 IEEE; 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020 ; Conference date: 31-10-2020 Through 07-11-2020",

year = "2021",

month = aug,

day = "12",

doi = "10.1109/NSS/MIC42677.2020.9508013",

language = "English",

series = "2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020",

publisher = "IEEE",

booktitle = "2020 IEEE Nuclear Science Symposium and Medical Imaging Conference",

address = "USA United States",

}

TY - GEN

T1 - Improving a Stochastic Algorithm for Regularized PET Image Reconstruction

AU - Delplancke, Claire

AU - Gurnell, Mark

AU - Latz, Jonas

AU - Markiewicz, Pawel J.

AU - Schönlieb, Carola Bibiane

AU - Ehrhardt, Matthias J.

N1 - 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

PY - 2021/8/12

Y1 - 2021/8/12

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=85124704975&partnerID=8YFLogxK

U2 - 10.1109/NSS/MIC42677.2020.9508013

DO - 10.1109/NSS/MIC42677.2020.9508013

M3 - Chapter in a published conference proceeding

AN - SCOPUS:85124704975

T3 - 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020

BT - 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference

PB - IEEE

T2 - 2020 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2020

Y2 - 31 October 2020 through 7 November 2020

ER -

Improving a Stochastic Algorithm for Regularized PET Image Reconstruction

Abstract

Publication series

Conference

Bibliographical note

Funding

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this