Hector%20DUQUE,%20Creatis/LIRIS - PowerPoint PPT Presentation

About This Presentation
Title:

Hector%20DUQUE,%20Creatis/LIRIS

Description:

(Centre de Recherche et d'Application en Traitement de l'Image et du Signal, Lyon, ... H. DUQUE, J.M. PIERSON, V. BRETON, L. BRUNIE, I.E. MAGNIN, DM2: Medical ... – PowerPoint PPT presentation

Number of Views:45
Avg rating:3.0/5.0
Slides: 17
Provided by: hectordu
Category:

less

Transcript and Presenter's Notes

Title: Hector%20DUQUE,%20Creatis/LIRIS


1
DM2 A Distributed Medical Data Manager for Grids.
Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT,
Creatis Jean-Marc PIERSON, LIRIS Lionel BRUNIE,
LIRIS Isabelle E. MAGNIN, Creatis
CREATIS, CNRS UMR 5515 (Centre de Recherche et
d'Application en Traitement de l'Image et du
Signal, Lyon, France) LIRIS (LISI), CNRS/INSA
FRE 2672 (Laboratoire d'InfoRmatique en Image et
Syst?mes d'information, Lyon, France)
2
  • Goals
  • To supply a Distributed System for the medical
    community able to deal with medical images and
    sensitive medical metadata
  • To provide hybrid content based queries and
    metadata queries over large databases of medical
    images (image processing)
  • To transparently use GRIDS in order to get
    advantage of its computing power and its massive
    storage capacity
  • To propose an arquitecture for developing this
    kind of systems (DSE Distributed System Engines)

3
  • challenges
  • content-based queries over images
  • Image processing
  • Interfacing Grids and Image Archiving Systems
  • distributed queries
  • massive storage
  • high performance computing

4
medical data constraints
  • Very large databases of images with a very long
    term storage
  • Data distributed over acquisition sites
  • Sensitive medical data (strong security
    constraints)
  • Read-only access to raw scanner data (replicas
    needed)
  • Keep track of data processing
  • Different kinds of users (patients, physicians
    and researchers)

5
applications
  • Hybrid queries to images's databases of
    Mammography and IRM cardiological sequences -
    metadata - parametric analysis (indexing) -
    content processing
  • Similarity queries

Source image (e.g. thorax, MRI)
Target images (thorax, MRI)
Similarity measures
Most similar
Less similar
6
a distributed system set of engines
IRM
IRM
hospital
IRM
USER
hospital
IRM
hospital
USER
messages
IRM
hospital
hospital
GRID
IRM
IRM
DSE Distributed Systems Engines
7
1- definition of a multilayer architecture 2-
implementation of the middleware level 3-
implementation of the application level
Distributed Systems Engines (multilayer
architecture)
DSE4
0 user
3- applications
0 Application 0 DM2
DSE3
0 distribution
DSE2
2-middleware
semantic level
DSE1
0 transaction
DSE0
0 message passing
8
(1) -Architecture (DSE1)
client machine
Transaction Drivers (TRD)
Task Drivers (TKD)
Tool Drivers (TOD)
message passing kernel (MPK)
Request Drivers (RQD)
server machine
a transaction is a set of tasks a task is a set
of requests a request is a set of messages
DSE1 a set of drivers
9
(2) - middelware
10
random source (normal/poisson distribution)
query 1 image sequence 10 dicom files
N images
tn
t0
DM2_qud lt 7005
security_tod
N img 10 slices
4
dicom_tkd
cache_tod
grid_tkd
14
database_tkd
13
11
images_tod
virtual_rqd gt7005
DICOM_rqd
8
SE_rqdgt7007
1
MYSQL_rqd gt8080
N10 files
1
10
11
17.5 hours (3000 x 3 sec / 3600 sec 18000 x 3
sec / 3600 sec))
12
hDSEM0 vs PVM (not remote) 500, 1000, 1500 ...
5000 messages 25 ... 110 Kbytes
13
(3) Application (usecase) A physician queries
DM2 to find all images similar to an image of
interest
CLIENT (DM2 API)
request similar images to an imageID
DM2 TRD
Security TOD
1
Cache TOD
Grid TKD
METADATA TKD
Images TOD
DM2 RQD
Grid RQD
METADATA RQD
mammo
METADATA
DM2 image DICOM file
heart
14
in summary
  • The DM2 architecture is designed for high
    performance andextensibility.
  • The proposed architecture (DSE) is appropriate
    for developing
  • distributed medical systems.
  • The concept of multilayered architecture has
    allow us to deal with the design and development
    of a complex system as a distributed medical
    application is.
  • Computing GRIDS are very useful for medical
    image storageand analysis (distributed data,
    high processing power).
  • The DM2 system allows the physicians to get
    secure access totheir data and to issue hybrid
    requests over huge databases.

15
papers
- Jun 2003 - submitted H. DUQUE, J. MONTAGNAT,
J.M. PIERSON, L. SEITZ, L. BRUNIE, I.E. MAGNIN,
An Architecture for Large Scale and High
Performance Medical Imaging Applications ,
Parallel Processing Letters, special issue on
grid computing for bioinformatics applications,
2004 - January 2003 J. MONTAGNAT, H. DUQUE,
J.M. PIERSON, V. BRETON, L. BRUNIE, I.E. MAGNIN,
DM2 Medical Image Content-Based Queries using
the Grid, Healthgrid 2003, January 15th-16th,
Lyon, France - January 2003 H. DUQUE, J.
MONTAGNAT, J.M. PIERSON, L. BRUNIE, I.E. MAGNIN,
DM2 A Distributed Medical Data Manager for
Grids, Biogrid 2003, may 12th-15th, Tokyo, Japan
16
This work is partly supported by
  • the IST European DataGrid project
  • www.edg.org
  • the French ministry for
  • research ACI-GRID project
  • www-sop.inria.fr/aci/grid/public
  • ECOS-Nord Committee (action C03S02)
Write a Comment
User Comments (0)
About PowerShow.com