I V I F2 F July 2005 Talk

12
Tony Pan, Ashish Sharma, Benjamin Rutt, Metin Gurcan, Stephen Langella, Joel Saltz, Tahsin Kurc Department of Biomedical Informatics The Ohio State University Medical Center, Columbus OH gridFTP for Third Party Data Transfer in gridImage — A Demonstration of the Middleware Project For more information, please contact Tony Pan ([email protected]) Dept. of Biomedical Informatics, The Ohio State University http://bmi.osu.edu

description

Just testing this website out

Transcript of I V I F2 F July 2005 Talk

Page 1: I V I  F2 F  July 2005  Talk

Tony Pan, Ashish Sharma, Benjamin Rutt, Metin Gurcan,Stephen Langella, Joel Saltz, Tahsin Kurc

Department of Biomedical InformaticsThe Ohio State University Medical Center, Columbus OH

gridFTP for Third Party Data Transfer in gridImage — A

Demonstration of the Middleware Project

For more information, please contact Tony Pan ([email protected]) Dept. of Biomedical Informatics, The Ohio State University http://bmi.osu.edu

Page 2: I V I  F2 F  July 2005  Talk

gridFTP for Bulk Data Transfer

A Demo from the In Vivo Imaging Middleware Project

• Use of gridFTP for Bulk Data Transfer

• Provide a client to support remote human markup of nodules

• Enable better algorithm development and validation through the use of many

distributed, shared image datasets

• Support remote algorithm execution – reduce data transfer and avoid the

need to transmit PHI

• Reduce overall processing time and algorithm development cycle through

remote compute resource recruitment and CAD compute farms

• Scalable and open source — caGrid 1.0 based

Page 3: I V I  F2 F  July 2005  Talk

Benefits

Remote execution of multiple CAD algorithms using

multiple image databases

• Facilitate research and clinical decision support with large number of

subjects and multiple CAD algorithms.

– Parameter studies, clinical and preclinical trials, etc

• Provide a client to support remote human markup of nodules

• Enable better algorithm development and validation through the use of

many distributed, shared image datasets

• Support remote algorithm execution – reduce data transfer and avoid the

need to transmit PHI

• Reduce overall processing time and algorithm development cycle

through remote compute resource recruitment and CAD compute farms

• Scalable and open source — caGrid 1.0 based

Page 4: I V I  F2 F  July 2005  Talk

gridCAD ArchitectureExpose algorithms, human markup and

image data as caGrid Services

Page 5: I V I  F2 F  July 2005  Talk

Image Data Service

• Expose data in PACS servers as caGrid Data Service• An open source DICOM server — Pixelmed

• XML based data transfer (our own schema)

caBIG

Columbus

3 Participating Data Services

Los Angeles

Page 6: I V I  F2 F  July 2005  Talk

CAD Application Service• caGRID middleware to wrap CAD applications with grid services• Interact with Data Services to retrieve images• Invoke algorithm with required inputs• Transform and report results to results data service

caGrid Introduce Hides complexity of plugging an algorithm into the grid

CAD algorithms provided by iCAD Inc. Prototypes for investigational use only; not commercially available

caGrid Dorian Used to provide authentication service

caBIG

Columbus

2 Participating Analytic Services

Page 7: I V I  F2 F  July 2005  Talk

Human Markup Services• Query a work-order queue to detect any new markup requests • Interact with Data Services to retrieve images• Capture markups and save to results data service

BaltimoreColumbus

2 Human Markup Services

Page 8: I V I  F2 F  July 2005  Talk

User Interface

Available data services

Queried results

DICOM image viewer

Click to browse images, submit CAD analysis, and view results

Page 9: I V I  F2 F  July 2005  Talk

caBIG Technologies

• caGrid 1.0– Globus Toolkit 4.0.1 compliant– Introduce toolkit for service creation and deployment– Dorian security management for user and service

authentication and authorization

• caDSR– CIP compliant vocabulary for DICOM data elements

• CQL based query and retrieve for “data services”

Page 10: I V I  F2 F  July 2005  Talk

Future Direction

• Location independenceMove algorithms to dataMove data to algorithmsMove both data and algorithms to compute serversCurrently supported – ongoing collaborations to deploy these capabilities

• Security and PrivacyEncryption and Just-In-Time anonymization for the image data services

• Scaling and DeploymentHigh performance image transfer mechanismsGreater number and variety of CAD vendorsAdditional application areas, including CAD for other diseases and in vitro image analysis

Page 11: I V I  F2 F  July 2005  Talk

Acknowledgements

For more information, please contact Tony Pan ([email protected]) Dept. of Biomedical Informatics, The Ohio State University http://bmi.osu.edu

The RIDER dataset used during this demonstration is provided courtesy of NCI Cancer Imaging Program

iCAD Inc.: Euvondia Friedmann, Maha Sallam, Tim Carter

This project was funded by NIH BISTI Center for Grid Enabled Medical Imaging, NCI, NSF, and the State of Ohio

Board of Regents BRTT program

Page 12: I V I  F2 F  July 2005  Talk

Thank You