An architecture for DICOM medical images storage and retrieval adopting distributed file systems

  • Authors:
  • Douglas D. J. De Macedo;Aldo Von Wangenheim;M. A. R. Dantas;Hilton G. W. Perantunes

  • Affiliations:
  • PPGEGC, Federal University of Santa Catarina, Florianopolis, SC, 88040-/900, Brazil.;PPGEGC, Federal University of Santa Catarina, Florianopolis, SC, 88040-/900, Brazil/ INE, Federal University of Santa Catarina, Florianopolis, SC, 88040-/900, Brazil.;PPGEGC, Federal University of Santa Catarina, Florianopolis, SC, 88040-/900, Brazil/ INE, Federal University of Santa Catarina, Florianopolis, SC, 88040-/900, Brazil.;INE, Federal University of Santa Catarina, Florianopolis, SC, 88040-/900, Brazil

  • Venue:
  • International Journal of High Performance Systems Architecture
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Conventional storage and retrieval of information from telemedicine environments is usually based on ordinary database systems. Aspects such as scalability, information distribution, high performance system techniques and operational costs are well known challenges to be circumvented in the research for novel proposals in the field of large-scale telemedicine systems. In this paper we present an architecture that targets high performance levels in storing and retrieving DICOM medical images, adopting a distributed approach in a cluster configuration. Our proposal has two main components: the first element is a data model that is based on image hierarchy, considering the hierarchical data format 5 (HDF5). The second component is a distributed file system, characterised by the parallel virtual file system (PVFS) that was employed in this proposal as a distributed storage data system. As a result, this paper presents a differentiated approach for storage and retrieval of information for a telemedicine environment. Experimental results, utilising the architecture, indicate an enhanced level of performance around 16% in terms of storage process. This number represents an improved performance in comparison to a conventional database system.