Preprint

An Investigation of Stochastic Variance Reduction Algorithms for 3D Penalised PET Image Reconstruction

Robert TwymanDepartment of Computer Science, UCL, UKSimon ArridgeNuclear Medicine Department, University Hospital Zurich, University of ZurichŽeljko KeretaGE Healthcare, Waukesha, WI 53188 USA. IBangti JinInstitute of Nuclear Medicine, UCL,Ludovica BrusaferriInstitute of Nuclear Medicine, UCL, UKSangtae AhnNuclear Medicine Department, University Hospital Zurich, University of ZurichC.W. StearnsMartinos Center for Biomedical Imaging, Harvard Medical School. S. Ahn is with GE Research, Niskayuna, NY 12309 USA. C. W. Stearns and F. Kotasidis are withBrian HuttonNuclear Medicine Department, University Hospital Zurich, University of ZurichIrene A. BurgerMartinos Center for Biomedical Imaging, Harvard Medical School. S. Ahn is with GE Research, Niskayuna, NY 12309 USA. C. W. Stearns and F. Kotasidis are withFotis A. KotasidisGE Healthcare, Waukesha, WI 53188 USA. IKris ThielemansInstitute of Nuclear Medicine, UCL, UK

2022en

Ochiq kirishYashil

Litsenziya: cc-by

Manbada oʻqishdoi.org(yangi oynada ochiladi)

ABI

Annotatsiya

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.

Hali tarjima qilinmagan

Mavzular

Medical Imaging Techniques and Applications Radiomics and Machine Learning in Medical Imaging Medical Image Segmentation Techniques

Identifikatorlar

DOI: 10.36227/techrxiv.19497680.v1

Iqtiboslar va manbalar

0 ta iqtibos54 ta foydalanilgan manba