Fast parallel algorithms for 3D reconstruction of angiographic images

Abstract

The reconstruction of angiographic images can be seen as a discrete optimization problem where a blind search is not suitable. A branch-and-bound algorithm can be used to explore the space state using a priori information. The critical issue in parallel search algorithms is the distribution of the search space among the processors. We work with two control schemes: centralized and distributed. According to the data distribution we propose three different mappings: static, semistatic and iterative. We achieve good load balance and a nearly optimum speedup.