UCL  IRIS
Institutional Research Information Service
UCL Logo
Please report any queries concerning the funding data grouped in the sections named "Externally Awarded" or "Internally Disbursed" (shown on the profile page) to your Research Finance Administrator. Your can find your Research Finance Administrator at http://www.ucl.ac.uk/finance/research/post_award/post_award_contacts.php by entering your department
Please report any queries concerning the student data shown on the profile page to:

Email: portico-services@ucl.ac.uk

Help Desk: http://www.ucl.ac.uk/ras/portico/helpdesk
Publication Detail
Implementation of a heterogeneous image reconstruction system for clinical Magnetic Resonance
  • Publication Type:
    Conference
  • Authors:
    Kowalik G, Steeden J, Atkinson D, Taylor A, Muthurangu V
  • Publication date:
    08/09/2013
  • Pagination:
    469, 479
  • Published proceedings:
    Lecture Notes in Computer Science
  • Volume:
    8384
  • Editors:
    Wyrzykowski R,Dongarra J,Karczewski K,Waśniewski J
  • ISBN-13:
    978-3-642-55224-3
  • Status:
    Published
  • Name of conference:
    10th International Conference on Parallel Processing and Applied Mathematics PPAM 2013
  • Conference place:
    Warsaw, Poland
  • Conference start date:
    08/09/2013
  • Conference finish date:
    11/09/2013
  • Keywords:
    GPGPU, CUDA, Medical Imaging
Abstract
This paper describes development of a novel online, heterogeneous image reconstruction system. The system integrates an external computer equipped with a GPU card into an MR scanner’s image reconstruction pipeline. The system promotes fast online reconstruction for computationally intensive algorithms making them feasible in a busy clinical service. An on-going work on analyse and improvement of execution time of the SENSE algorithm as well as networking framework are presented. The imaging algorithm was broken down into distinctive steps for execution time profiling. Also, steps to achieve overlapping of execution and transmission are described. The GPU version reduced the algorithm’s bottleneck from 81% to 40% of iteration’s time. This allowed a full overlap between an acquisition and a reconstruction making a delay time between finishing of the acquisition and that of the reconstruction to be constant. The system was successfully used in research and clinical studies requiring high data throughput.
Publication data is maintained in RPS. Visit https://rps.ucl.ac.uk
 More search options
UCL Researchers Show More
Author
Experimental & Translational Medicine
Author
Childrens Cardiovascular Disease
Author
Childrens Cardiovascular Disease
Author
Childrens Cardiovascular Disease
Author
Childrens Cardiovascular Disease
University College London - Gower Street - London - WC1E 6BT Tel:+44 (0)20 7679 2000

© UCL 1999–2011

Search by