Fast voxel line update for time-space image reconstruction

Recent applications of model-based iterative reconstruction(MBIR) algorithm to time-space Computed Tomography (CT) have shown that MBIR can greatly improve image quality by increasing resolution as well as reducing noise and some artifacts. Among the various iterative methods that have been studied for MBIR, iterative coordinate descent(ICD) has been found to have relatively low overall computational requirements due to its fast convergence. However, high computational cost and long reconstruction times remain as a barrier to the use of MBIR in practical applications. This disadvantage is especially prominent in time-space reconstruction because of the large volume of data. This thesis presents a new data structure, called VL-Buffer , for time-space reconstruction that significantly improves the cache locality while retaining good parallel performance. Experimental results show an average speedup of 40% using VL-Buffer