A grid Environment for Medical Imaging Summary Medical Imaging


Download 445 b.
Sana30.03.2018
Hajmi445 b.


A Grid Environment for Medical Imaging


Summary

  • Medical Imaging

  • Grid environment for medical imaging

  • Perspectives

  • Acknowledgments



Medical Imaging

  • CAVIAR

    • Myocardium segmentation
    • Motion estimation
  • ThIS/GATE

    • Monte-Carlo simulation
    • Cancer treatment planning
  • SIMRI



Grid environment for medical imaging

  • Reliable and responsive grid execution

    • Successful execution of one application on a grid node
    • Distant grid node environment and application customization
  • Application parallelization

    • MPI (Message Passing Interface) -> Simri
    • Split the simulation into independent jobs (Monte Carlo) -> Gate
  • Execution framework: advanced tools for

    • Job submission, monitoring and retrieval
    • Integration into service platforms
  • High level interface



Reliable and responsive grid execution

  • DIANE

    • Registers/removes agents
    • Schedules tasks on agents
    • Stdout/err transfers
  • EGEE – gLite

    • Schedules agents on grid sites
    • Transfer input/result files to/from worker nodes


Execution framework

  • Moteur workflow engine

    • Workflow execution
      • Each application is described as a workflow (using Taverna)
    • Job submission, input selection and data piping between jobs
  • Moteur – DIANE interface



Graphical interface to the grid

  • VBrowser

    • Provides user interface to the grid
    • Browses input/result files
    • Launches Moteur
    • Follows experiment progress (job monitoring)
  • Application: the Gate-Lab

    • GATE-Lab client (VBrowser plugin)
      • Parses simulation (mac) file, zip inputs
      • Stores inputs on the grid, submits workflow
      • Keeps track of simulation history
    • GATE-Lab server
      • Launches workflow engine
      • Starts DIANE pilot-job master
      • Submits agents when necessary


Perspectives (I)

  • VIP – Virtual Imaging Platform

  • Goal

    • Enable heavy simulations: multimodal, dynamic
    • Store and retrieve data (organ models and simulated images)
  • Multi-platform execution

    • Large-scale grids (EGEE, NorduGrid)
    • Local clusters (Creatis, IN2P3)
    • GPU


Perspectives (II)

  • Distributed database for medical imaging

    • Storage, sharing, indexing and search on metadata
    • Technologies
      • iRODS
        • Access and uniform management of heterogeneous data distributed among different sites
      • MDM (Medical Data Manager)‏


Acknowledgements

  • University of Lyon, CREATIS-LRMN

  • Hugues Benoit-Cattin, David Sarrut, Patrick Clarysse

  • I3S, CNRS

  • Johan Montagnat

  • University of Amsterdam, Academic Medical Centre

  • Silvia D. Olabarriaga

  • CERN

  • Jakub T. Mosciki



Thank you for your attention!

  • Questions?



Download 445 b.

Do'stlaringiz bilan baham:




Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©fayllar.org 2020
ma'muriyatiga murojaat qiling