The Architecture of Specialized GPU Clusters Used for Solving the Inverse Problems of 3D Low-Frequency Ultrasonic Tomography

被引:8
作者
Goncharsky, Alexander [1 ]
Seryozhnikov, Sergey [1 ]
机构
[1] Lomonosov Moscow State Univ, Moscow, Russia
来源
SUPERCOMPUTING, RUSCDAYS 2017 | 2017年 / 793卷
基金
俄罗斯科学基金会;
关键词
Ultrasonic tomography; Coefficient inverse problems; Finite-difference time-domain (FDTD) method; GPU clusters; Medical imaging; EQUATION;
D O I
10.1007/978-3-319-71255-0_29
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
This paper is dedicated to the development of the architecture of specialized GPU clusters that can be used as computing systems in medical ultrasound tomographic facilities that are currently being developed. The inverse problem of ultrasonic tomography is formulated as a coefficient inverse problem for a hyperbolic equation. An approximate solution is constructed using an iterative process of minimizing the residual functional between the measured and simulated wave fields. The algorithms used to solve the inverse problem are optimized for a GPU. The requirements for the architecture of a GPU cluster are formulated. The proposed architecture accelerates the reconstruction of ultrasonic tomographic images by 1000 times compared to what is achieved by a personal computer.
引用
收藏
页码:363 / 375
页数:13
相关论文
共 14 条
  • [1] [Anonymous], 2012, OPEN SYST J
  • [2] Beilina L., 2010, J MATH SCI, V167, P279, DOI DOI 10.1007/S10958-010-9921-1
  • [3] GPU-based iterative transmission reconstruction in 3D ultrasound computer tomography
    Birk, Matthias
    Dapp, Robin
    Ruiter, N. V.
    Becker, J.
    [J]. JOURNAL OF PARALLEL AND DISTRIBUTED COMPUTING, 2014, 74 (01) : 1730 - 1743
  • [4] Breast ultrasound tomography: Bridging the gap to clinical practice
    Duric, Neb
    Littrup, Peter
    Li, Cuiping
    Roy, Olivier
    Schmidt, Steven
    Janer, Roman
    Cheng, Xiaoyang
    Goll, Jefferey
    Rama, Olsi
    Bey-Knight, Lisa
    Greenway, William
    [J]. MEDICAL IMAGING 2012: ULTRASONIC IMAGING, TOMOGRAPHY, AND THERAPY, 2012, 8320
  • [5] ENGQUIST B, 1977, MATH COMPUT, V31, P629, DOI 10.1090/S0025-5718-1977-0436612-4
  • [6] Two Approaches to the Solution of Coefficient Inverse Problems for Wave Equations
    Goncharskii, A. V.
    Romanov, S. Yu
    [J]. COMPUTATIONAL MATHEMATICS AND MATHEMATICAL PHYSICS, 2012, 52 (02) : 245 - 251
  • [7] A computer simulation study of soft tissue characterization using low-frequency ultrasonic tomography
    Goncharsky, A. V.
    Romanov, S. Y.
    Seryozhnikov, S. Y.
    [J]. ULTRASONICS, 2016, 67 : 136 - 150
  • [8] Inverse problems of 3D ultrasonic tomography with complete and incomplete range data
    Goncharsky, A. V.
    Romanov, S. Y.
    Seryozhnikov, S. Y.
    [J]. WAVE MOTION, 2014, 51 (03) : 389 - 404
  • [9] Iterative methods for solving coefficient inverse problems of wave tomography in models with attenuation
    Goncharsky, Alexander V.
    Romanov, Sergey Y.
    [J]. INVERSE PROBLEMS, 2017, 33 (02)
  • [10] Inverse problems of ultrasound tomography in models with attenuation
    Goncharsky, Alexander V.
    Romanov, Sergey Y.
    [J]. PHYSICS IN MEDICINE AND BIOLOGY, 2014, 59 (08) : 1979 - 2004