Design and implementation of the software architecture for a 3-D reconstruction system in medical imaging

The design and implementation of the reconstruction system in medical X-ray imaging is a challenging issue due to its immense computational demands. In order to ensure an efficient clinical workflow it is inevitable to meet high performance requirements. Hence, the usage of hardware acceleration is mandatory. The software architecture of the reconstruction system is required to be modular in a sense that different accelerator hardware platforms are supported and it must be possible to implement different parts of the algorithm using different acceleration architectures and techniques. This paper introduces and discusses the design of a software architecture for an image reconstruction system that meets the aforementioned requirements. We implemented a multi-threaded software framework that combines two software design patterns: the pipeline and the master/worker pattern. This enables us to take advantage of the parallelism in off-the-shelf accelerator hardware such as multi-core systems, the Cell processor, and graphics accelerators in a very flexible and reusable way.

1. MOTIVATION

Scanning devices in medical imaging acquire a huge amount of data, e.g. X-ray projection images from different angles around the patient. Modern C-arm devices, for instance, generate more than 2 GigaByte (GB) of projection data for volume reconstruction. The basic computational structure of a reconstruction system consists of a series of processing tasks on these data, which finally results in the reconstructed volume, consisting of many transaxial slices through the patient.