The registration of corresponding patient volumes is often a pre-requisite for medical imaging tasks. Accurate alignment, however, usually results in high computational complexity and can hence take a considerable amount of time. This is particularly true with 3-D volume data which adds another dimension to the registration process. One possibility of keeping registration times feasible is to distribute computation among several processors so that it maybe accomplished in parallel. This chapter provides a short survey of parallel registration approaches which have been proposed together with some recent research adopting a blackboard architecture for distributed high performance image and volume registration purposes.
Key Terms in this Chapter
Blackboard Architecture: An artificial intelligence application based on and analogous to a group of experts seated in a room with a large blackboard working as a team to solve a common problem.
Similarity Metric: A measure used to quantitatively judge how well a transformed sensed (moving) image fits a reference (fixed) image by comparing intensities.
Fine-Grained Parallelism: A term used to describe an algorithm that has been divided into low-level components each of which can be hosted by a separate processor.
Distributed Agents: Software entities, designed to execute as independent threads and on distributed processors, capable of acting autonomously in order to achieve a pre-defined task.
Image Registration: The process whereby two images, differing by a spatial transformation, are brought into geometric alignment.
Coarse-Grained Parallelism: A term used to describe an algorithm that has been divided into high-level components each of which can be hosted by a separate processor.
Parallel Processing: The concurrent execution of the same task, split into components, on multiple processors in order to achieve faster processing speeds.