Efficient 3-D medical image registration using a distributed blackboard architecture

Conf Proc IEEE Eng Med Biol Soc. 2006:2006:3045-8. doi: 10.1109/IEMBS.2006.260146.

Abstract

A major drawback of 3-D medical image registration techniques is the performance bottleneck associated with re-sampling and similarity computation. Such bottlenecks limit registration applications in clinical situations where fast execution times are required and become particularly apparent in the case of registering 3-D data sets. In this paper a novel framework for high performance intensity-based volume registration is presented. Geometric alignment of both reference and sensed volume sets is achieved through a combination of scaling, translation, and rotation. Crucially, resampling and similarity computation is performed intelligently by a set of knowledge sources. The knowledge sources work in parallel and communicate with each other by means of a distributed blackboard architecture. Partitioning of the blackboard is used to balance communication and processing workloads. Large-scale registrations with substantial speedups, when compared with a conventional implementation, have been demonstrated.

MeSH terms

  • Algorithms
  • Biomedical Engineering
  • Computer Communication Networks
  • Computer Systems
  • Humans
  • Imaging, Three-Dimensional / statistics & numerical data*
  • Knowledge Bases