GPU Acceleration of a Fully 3D Iterative Reconstruction Software for PET using CUDA

被引：6
|
作者：
Herraiz, J. L. [1 ]
Espana, S. [2 ]
Garcia, S. [3 ]
Cabido, R. [3 ]
Montemayor, A. S. [3 ]
Desco, M. [4 ]
Vaquero, J. J. [4 ]
Udias, J. M. [1 ]
机构：
[1] Univ Complutense Madrid, Grp Fis Nucl, Dept Fis Atom Mol & Nucl, E-28040 Madrid, Spain
[2] Univ Complutense Madrid, Grp Fis Nucl, Madrid, Spain
[3] Univ Rey Juan Carlos, Dept Ciencias Computac, Madrid, Spain
[4] Hosp Gen Univ Gregorio Maranon, Unidad Med & Cirugia Expt, Madrid, Spain
来源：
2009 IEEE NUCLEAR SCIENCE SYMPOSIUM CONFERENCE RECORD, VOLS 1-5 | 2009年
关键词：
D O I：
10.1109/NSSMIC.2009.5402402
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
A CUDA implementation of the existing software FIRST (Fast Iterative Reconstruction Software for (PET) Tomography) is presented. This implementation uses consumer graphics processing units (GPUs) to accelerate the compute-intensive parts of the reconstruction: forward and backward projection. FIRST was originally developed in FORTRAN, and it has been migrated to C language to be used with NVIDIA C for CUDA, as well as for a straightforward implementation and performance comparison between the C versions of the code running on the CPU and on the GPU. We measured the execution time of the CUDA version compared to the fastest available CPU. The CUDA implementation includes a loop re-ordering and an optimized memory allocation, which improves even more the performance of the reconstruction on the GPUs.
引用
收藏
页码：4064 / +
页数：2
相关论文
共 50 条
  • [1] Fully 3D GPU PET reconstruction
    Herraiz, J. L.
    Espana, S.
    Cal-Gonzalez, J.
    Vaquero, J. J.
    Desco, M.
    Udias, J. M.
    [J]. NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT, 2011, 648 : S169 - S171
  • [2] Fast and efficient fully 3D PET image reconstruction using sparse system matrix factorization with GPU acceleration
    Zhou, Jian
    Qi, Jinyi
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2011, 56 (20): : 6739 - 6757
  • [3] Fully 3D iterative scatter-corrected OSEM for HRRT PET using a GPU
    Kim, Kyung Sang
    Ye, Jong Chul
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2011, 56 (15): : 4991 - 5009
  • [4] High Performance Multi-GPU Acceleration for Fully 3D List-Mode PET Reconstruction
    Bahi, Zakaria
    Bert, Julien
    Autret, Awen
    Visvikis, Dimitris
    [J]. 2012 IEEE NUCLEAR SCIENCE SYMPOSIUM AND MEDICAL IMAGING CONFERENCE RECORD (NSS/MIC), 2012, : 3390 - 3393
  • [5] GPU-Based Fast Iterative Reconstruction of Fully 3-D PET Sinograms
    Herraiz, J. L.
    Espana, S.
    Cabido, R.
    Montemayor, A. S.
    Desco, M.
    Vaquero, J. J.
    Udias, J. M.
    [J]. IEEE TRANSACTIONS ON NUCLEAR SCIENCE, 2011, 58 (05) : 2257 - 2263
  • [6] Iterative Reconstruction for Transmission Tomography on GPU Using Nvidia CUDA
    Damien Vintache
    Bernard Humbert
    David Brasse
    [J]. Tsinghua Science and Technology, 2010, 15 (01) : 11 - 16
  • [7] Fully 3D list-mode time-of-flight PET image reconstruction on GPUs using CUDA
    Cui, Jing-yu
    Pratx, Guillem
    Prevrhal, Sven
    Levin, Craig S.
    [J]. MEDICAL PHYSICS, 2011, 38 (12) : 6775 - 6786
  • [8] PET 3D Iterative Reconstruction on Cell BE
    Chevalier, David E.
    Drapkin, Evgeny
    [J]. 2009 IEEE NUCLEAR SCIENCE SYMPOSIUM CONFERENCE RECORD, VOLS 1-5, 2009, : 4054 - 4058
  • [9] Fully 3D iterative CT reconstruction using polar coordinates
    Thibaudeau, Christian
    Leroux, Jean-Daniel
    Fontaine, Rejean
    Lecomte, Roger
    [J]. MEDICAL PHYSICS, 2013, 40 (11)
  • [10] Analytical volume calculation of voxel fragments for iterative, fully 3D PET reconstruction
    Scheins, JJ
    Herzog, H
    Boschen, F
    [J]. 2004 IEEE NUCLEAR SCIENCE SYMPOSIUM CONFERENCE RECORD, VOLS 1-7, 2004, : 2502 - 2506
12345