Resolving Clinicians’ Queries Across a Grid’s Infrastructure

Summary

Objectives: The past decade has witnessed order of magnitude increases in computing power, data storage capacity and network speed, giving birth to applications which may handle large data volumes of increased complexity, distributed over the internet.

Methods: Medical image analysis is one of the areas for which this unique opportunity likely brings revolutionary advances both for the scientist’s research study and the clinician’s everyday work. Grids [1] computing promises to resolve many of the difficulties in facilitating medical image analysis to allow radiologists to collaborate without having to co-locate.

Results: The EU-funded MammoGrid project [2] aims to investigate the feasibility of developing a Grid-enabled European database of mammograms and provide an information infrastructure which federates multiple mammogram databases. This will enable clinicians to develop new common, collaborative and co-operative approaches to the analysis of mammographic data.

Conclusion: This paper focuses on one of the key requirements for large-scale distributed mammogram analysis: resolving queries across a grid-connected federation of images.

Keywords

Distributed database - queries - meta-data - mammography - medical image analysis - epidemiological studies

• References

• 1 Foster I, Kesselman C. The Grid: Blueprint for a New Computing Infrastructure. Morgan Kaufmann publishers, 1998. ISBN 1558604758.
• 2 The Information Societies Technology project: Mammo Grid – A European federated mammogram database implemented on a GRID infrastructure. EU Contract IST-2001 37614.
• 3 Viborny CJ, Giger ML, Nishikawa RM. Computer aided detection and diagnosis of breast cancer. Radiol Clin N Am 2000; 38 (04) 725-40.
• 4 Thursjell EL, Lernevall KA, Taube AAS. Benefit of independent double reading in a population based mammography screening program. Radiology 1994; 191: 241.
• 5 Ciatto S, Rosselli Del Turco M, Burke P, Visioli C, Paci E, Zappa M. Comparison of standard and double reading and computer-aided detection (CAD) of interval cancers at prior negative screening mammograms: a blind review. British Journal of Cancer 2003; 89: 1645-9.
• 6 McClatchey R. et al. MammoGrid User Requirements Document V1.0. Requirements for Large- Scale Distributed Medical Image Analysis. Available on request from authors and see. http://mammogrid.vitamib.com/.
• 7 The Rational Unified Process Model. See. http://www.rational.comForparticulardetailsconsult:http://www.rational.com/products/rup/whitepapers.jsp.
• 8 CRISTAL – Common Repositories and Information Systems to Track Assembly Lifecycles. In. Estrella F. editor. Objects, Patterns and Descriptions in Data Management. Bristol, England: PhD Thesis, University of the West of England; December 2000
• 9 The Mirada Workstation. Details available in [10] and from. www.mirada-solutions.com.
• 10 McClatchey R. et al. The Mammo Grid Information Infrastructure Specification. Document V1.1. Available from the authors (EU Contract IST-200137614).
• 11 Foster I, Kesselman C, Nick J, Tueke S. The Physiology of the Grid – An Open Services Grid Architecture for Distributed Systems Integration. Draft document at. http://www.globus.org/research/papers/ogsa.pdf.
• 12 OGSI. The Open Grids Services Infrastructure. See. http://www-106.ibm.com/developerworks/grid/library/gr-gt3/.