A review paper on GPU-based 3D-CT image reconstruction

CT imaging in interventional and minimally-invasive surgery requires high-performance computing solutions. Three dimension Computed Tomography (CT) reconstruction is computationally complex. Reconstruction of CT images is possible using, Application Specific Integrated Circuit (ASIC) or Field Programmable Gate Array (FPGA), but they are expensive, inflexible and not easy to upgrade. In recent years, GPUs have become an increasingly popular tool in computed tomography (CT) reconstruction. The modern Graphics Processing Unit (GPU) with its programmable hardware architecture, suitable for pipelining and high levels of parallel processing increases computational throughput, and provides off-the-shelf and effectively scalable solutions. This paper basically reviews the different performance optimization techniques for a GPU-based filtered-back projection reconstruction implementation using FDK algorithm.