Distributed MLEM: An Iterative Tomographic Image Reconstruction Algorithm for Distributed Memory Architectures

The processing speed for positron emission tomography (PET) image reconstruction has been greatly improved in recent years by simply dividing the workload to multiple processors of a graphics processing unit (GPU). However, if this strategy is generalized to a multi-GPU cluster, the processing speed...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on medical imaging 2013-05, Vol.32 (5), p.957-967
Main Authors:	Jingyu Cui, Pratx, G., Bowen Meng, Levin, C. S.
Format:	Article
Language:	eng
Subjects:	Algorithms Clustering algorithms Compute unified device architecture (CUDA) Computer Graphics Computer Simulation Equations graphics processing unit (GPU) Graphics processing units high performance computing Image Processing, Computer-Assisted - methods Image reconstruction Linear programming list-mode Mathematical model maximum likelihood expectation maximization (MLEM) parallel computing Phantoms, Imaging Positron emission tomography positron emission tomography (PET) image reconstruction Positron-Emission Tomography - methods
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	The processing speed for positron emission tomography (PET) image reconstruction has been greatly improved in recent years by simply dividing the workload to multiple processors of a graphics processing unit (GPU). However, if this strategy is generalized to a multi-GPU cluster, the processing speed does not improve linearly with the number of GPUs. This is because large data transfer is required between the GPUs after each iteration, effectively reducing the parallelism. This paper proposes a novel approach to reformulate the maximum likelihood expectation maximization (MLEM) algorithm so that it can scale up to many GPU nodes with less frequent inter-node communication. While being mathematically different, the new algorithm maximizes the same convex likelihood function as MLEM, thus converges to the same solution. Experiments on a multi-GPU cluster demonstrate the effectiveness of the proposed approach.
ISSN:	0278-0062 1558-254X