3D medical volume reconstruction using web services

Rob Kooper, Andrew Shirk, Sang Chul Lee, Amy Lin, Robert Folberg, Peter Bajcsy

Research output: Contribution to journalArticlepeer-review

Abstract

We address the problem of 3D medical volume reconstruction using web services. The use of proposed web services is motivated by the fact that the problem of 3D medical volume reconstruction requires significant computer resources and human expertise in medical and computer science areas. Web services are implemented as an additional layer to a dataflow framework called data to knowledge. In the collaboration between UIC and NCSA, pre-processed input images at NCSA are made accessible to medical collaborators for registration. Every time UIC medical collaborators inspected images and selected corresponding features for registration, the web service at NCSA is contacted and the registration processing query is executed using the image to knowledge library of registration methods. Co-registered frames are returned for verification by medical collaborators in a new window. In this paper, we present 3D volume reconstruction problem requirements and the architecture of the developed prototype system at http://isda.ncsa.uiuc.edu/MedVolume. We also explain the tradeoffs of our system design and provide experimental data to support our system implementation. The prototype system has been used for multiple 3D volume reconstructions of blood vessels and vasculogenic mimicry patterns in histological sections of uveal melanoma studied by fluorescent confocal laser scanning microscope.

Original languageEnglish (US)
Pages (from-to)490-500
Number of pages11
JournalComputers in Biology and Medicine
Volume38
Issue number4
DOIs
StatePublished - Apr 2008

Keywords

  • Medical image analysis
  • Test case
  • Web services architecture
  • Workflow

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Fingerprint Dive into the research topics of '3D medical volume reconstruction using web services'. Together they form a unique fingerprint.

Cite this