Abstract:The Common Unified Device Architecture (CUDA) introduced in 2007 by NVIDIA is a recent programming model making use of the unified shader design of the most recent graphics processing units (GPUs). The programming interface allows algorithm implementation using standard C language along with a few extensions without any knowledge about graphics programming using OpenGL, DirectX, and shading languages.We apply this novel technology to the Simultaneous Algebraic Reconstruction Technique (SART), which is an advan… Show more
“…The inputs were 364 1024×768 projections on a half circal trajectory. We reconstructed a 3D volume within the FOV with two different resolution, 256 3 and 512 3 . We tested the different running times for the Single projection method (S), Multiple projection method (M) and Hybrid ordering method (H).…”
Section: Resultsmentioning
confidence: 99%
“…al. [3] used this method in CUDA-based SART. This method is better when cache-miss penalty is larger than memory writing overhead.…”
Section: A Single Projection Methods For Each Projection For Each (Slmentioning
confidence: 99%
“…2) are mapped to thread blocks in CUDA. This volume-to-slabs decomposition has been used in [2][3][4]. Another type of mapping is based on decomposing the volume into horizontal tiles and each tile is mapped to a CUDA thread block, as used in [5], [6].…”
Section: Cone-beam Back-projectionmentioning
confidence: 99%
“…2) to ensure better cache hit-rate. Back-projection implementations [1][2][3][4][5][6] all use texture memory for projection data storage to deal with irregular memory fetching pattern. Using texture memory has several advantages.…”
Abstract-Graphic process units (GPUs) are well suited to computing-intensive tasks and are among the fastest solutions to perform Computed Tomography (CT) reconstruction. As previous research shows, the bottleneck of GPU-implementation is not the computational power, but the memory bandwidth. We propose a cache-aware memory-scheduling scheme for the backprojection, which can ensure a better load-balancing between GPU processors and the GPU memory. The proposed reshuffling method can be directly applied on existing GPU-accelerated CT reconstruction pipelines. The experimental results show that our optimization can achieve speedup ranging from 1.18-1.48. Our cache-optimization method is particular effective for lowresolution volumes with high resolution projections.
“…The inputs were 364 1024×768 projections on a half circal trajectory. We reconstructed a 3D volume within the FOV with two different resolution, 256 3 and 512 3 . We tested the different running times for the Single projection method (S), Multiple projection method (M) and Hybrid ordering method (H).…”
Section: Resultsmentioning
confidence: 99%
“…al. [3] used this method in CUDA-based SART. This method is better when cache-miss penalty is larger than memory writing overhead.…”
Section: A Single Projection Methods For Each Projection For Each (Slmentioning
confidence: 99%
“…2) are mapped to thread blocks in CUDA. This volume-to-slabs decomposition has been used in [2][3][4]. Another type of mapping is based on decomposing the volume into horizontal tiles and each tile is mapped to a CUDA thread block, as used in [5], [6].…”
Section: Cone-beam Back-projectionmentioning
confidence: 99%
“…2) to ensure better cache hit-rate. Back-projection implementations [1][2][3][4][5][6] all use texture memory for projection data storage to deal with irregular memory fetching pattern. Using texture memory has several advantages.…”
Abstract-Graphic process units (GPUs) are well suited to computing-intensive tasks and are among the fastest solutions to perform Computed Tomography (CT) reconstruction. As previous research shows, the bottleneck of GPU-implementation is not the computational power, but the memory bandwidth. We propose a cache-aware memory-scheduling scheme for the backprojection, which can ensure a better load-balancing between GPU processors and the GPU memory. The proposed reshuffling method can be directly applied on existing GPU-accelerated CT reconstruction pipelines. The experimental results show that our optimization can achieve speedup ranging from 1.18-1.48. Our cache-optimization method is particular effective for lowresolution volumes with high resolution projections.
“…Equation 1 is solved using Algorithm 1 by alternately minimizing the data consistency term Ax − p 2 and the regularization term R (x) for a fixed number of iterations N ART . In step 3 of Algorithm 1 data consistency is enforced by applying three iterations of the GPU-based Ordered Subsets-ART (OS-ART) method presented in [9]. In step 4 prior knowledge about the reconstructed volume is incorporated by applying operator T to the current volume estimation to reduce the penalty term R(x).…”
Tissue perfusion measurement using C-arm angiography systems capable of CT-like imaging (C-arm CT) is a novel technique with potentially high benefit for catheter-guided treatment of stroke in the interventional suite. New rapid scanning protocols with increased C-arm rotation speed enable fast acquisitions of C-arm CT volumes and allow for sampling the contrast flow with improved temporal resolution. However, the peak contrast attenuation values of brain tissue lie typically in a range of 5-30 HU. Thus perfusion imaging is very sensitive to noise. In this work we compare different denoising algorithms based on the algebraic reconstruction technique (ART) and introduce a novel denoising technique, which requires only iterative filtering in volume space and is computationally much more attractive. Our evaluation using a realistic digital brain phantom shows that all methods improve the perfusion maps perceptibly compared to Feldkamptype (FDK) reconstruction. The volume-based technique performs similarly to the ART-based methods: the Pearson correlation of reference and reconstructed blood flow maps increases from 0.61 for the FDK method to 0.81 for the best ART method and to 0.79 for the volume-based method. Furthermore results from a canine stroke model study are shown.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.