[email protected] 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis...

17
[email protected] 1 http://www.creatis.insa-lyon.fr/~duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS Lionel BRUNIE, LIRIS Isabelle E. MAGNIN, Creatis DM 2 : A Distributed Medical Data Manager for Grids. 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) BIOGRID'03, May 14th, 2003, Tokyo, Japan
  • date post

    19-Dec-2015
  • Category

    Documents

  • view

    223
  • download

    0

Transcript of [email protected] 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis...

Page 1: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 1http://www.creatis.insa-lyon.fr/~duque

Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis

Jean-Marc PIERSON, LIRIS Lionel BRUNIE, LIRIS

Isabelle E. MAGNIN, Creatis

DM2: A Distributed Medical Data Manager for Grids.

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)

BIOGRID'03, May 14th, 2003, Tokyo, Japan

Page 2: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 2http://www.creatis.insa-lyon.fr/~duque

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)

Page 3: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 3http://www.creatis.insa-lyon.fr/~duque

challenges

content-based queries over images

Image processing

Interfacing Grids and Image Archiving Systems

distributed queries

massive storage

high performance computing

Page 4: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 4http://www.creatis.insa-lyon.fr/~duque

Raid 5

DICOM client

DICOM server

DICOM

hospital architecture

DICOM

DICOM

DICOM

data acquisition device(IRM)

DICOM file = metadata + image

DICOM

Page 5: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 5http://www.creatis.insa-lyon.fr/~duque

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)

medical data constraints

Page 6: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 6http://www.creatis.insa-lyon.fr/~duque

applications Hybrid queries to images's databases of Mammography and IRM cardiological sequences

- metadata- parametric analysis (indexing)- content processing

Similarity queriesSource image

(e.g. thorax, MRI)Target images (thorax, MRI)

Most similar Less similar

Similaritymeasures

Page 7: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 7http://www.creatis.insa-lyon.fr/~duque

DSE

DSE

DSE

DSE

hospital

hospital

hospital

hospital

hospital

hospital

a distributed system = set of engines

GRID

messages

DSE: Distributed Systems Engines

Page 8: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 8http://www.creatis.insa-lyon.fr/~duque

DSE0

DSE4

DSE3

DSE2

DSE1

message passing

distribution

Application DM2

transaction

user

middleware

applications

sem

antic

leve

l

DSE DSE is the definition ofthe multilevel architecture plust its implementation

Distributed Systems Engines (multilayer architecture)

Page 9: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 9http://www.creatis.insa-lyon.fr/~duque

DSE0network_in / ipc_out processes (NIIO)

ipc_in / network_out processes (IINO)

ipc_in processes only (IIO)

DSE0 = set of processes and a MPK

IINO

NIIO

IIIO

IIIO

IIO

tcp/ip

tcp/ip

ipc

ipc

ipc_in / ipc_out processes (IIIO)

Message Passing Kernel (MPK)

Page 10: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 10http://www.creatis.insa-lyon.fr/~duque

DSE1

Tool Drivers (TOD)

Request Drivers (RQD)

server machine

client machine

Task Drivers (TKD)

DSE1 = a set of drivers

Transaction Drivers (TRD)

a transaction is a set of tasksa task is a set of requestsa request is a set of messages

message passing kernel (MPK)

Page 11: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 11http://www.creatis.insa-lyon.fr/~duque

network

network

IPCIPC

client machines

server machines

messages

messages

TRD

RQD

TKDTOD

Page 12: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 12http://www.creatis.insa-lyon.fr/~duque

METADATA TKD

DM2 TRD

DM2 image = {DICOM file} METADATA

DM2

DM2 RQD

CLIENT (DM2 API) Grid

heart

mammo

Security TOD

request comparable images to an imageID

Usecase:a- A physician queries DM2 to find all images comparable to an image of interest

1

METADATA RQD

Page 13: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 13http://www.creatis.insa-lyon.fr/~duque

METADATA TKD

Grid TKD

DM2 TRD

DM2 image = {DICOM file} METADATA

Grid DM2

CLIENT (DM2 API) Grid

heart

mammo

Security TOD

request comparable images to an imageID

Usecase:a- A physician queries DM2 to find all images comparable to an image of interest

1

b- he queries the DM2 to get a list of images similar to a DM2image

request similar images to an imageID

2

METADATA RQD

DM2 RQD Grid RQD

Page 14: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 14http://www.creatis.insa-lyon.fr/~duque

Cache TOD

DICOM TKD

Grid TKD

DM2 TRD

DM2 image = {Dicom file}

DICOM

METADATA RQD

Grid

DICOM RQD Grid RQD

DICOM

Grid

heart

mammo

Images TOD

Security TOD

GET (imageID)

Usecasec- the Grid requests an image

1

2

3

3

45

66

METADATA

METADATA TKD

Page 15: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 15http://www.creatis.insa-lyon.fr/~duque

Results (Intel Pentium 4 CPU 1.70GHz, memory 512 MB)

number of transactions * / minute:

without cache

cache (file)

cache (image)

(totally concurrent)

31

98

590

(sequence)

3

37

590

* transfer 10 files x .5 MB = 5 MBbuilt 1 image of 5 Mbuntil 10*3 + 8 messages = 38 messagesrestricted to 10 channels with a DICOM server

Page 16: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 16http://www.creatis.insa-lyon.fr/~duque

in summary

The DM2 architecture is designed for high performance andextensibility. The proposed architecture (DSE) is appropriate for developingdistributed 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.

Page 17: Hector.duque@creatis.insa-lyon.fr 1 duque Hector DUQUE, Creatis/LIRIS Johan MONTAGNAT, Creatis Jean-Marc PIERSON, LIRIS.

[email protected] 17http://www.creatis.insa-lyon.fr/~duque

This work is partly supported by:

the IST European DataGrid project www.edg.org

the French ministry forresearch ACI-GRID projectwww-sop.inria.fr/aci/grid/public

ECOS-Nord Committee (action C03S02)