Simulation Platform for X-Ray Computed Tomography Based on Low-Power Systems
Reconstruction of Computed Tomography (CT) images is a computationally and memory demanding tool. The creation of new algorithms for the reduction of the X-Ray dose and the increasing resolution of the detectors have complicated the obtaining of a good performance. Accelerators have become essential for the processing of the algorithm in a reasonable time. Nowadays, with the emergence of new mobile architectures that are not only powerful but also energy efficient and the possibility of easily porting the already existing code thanks to different programming models they could become an alternative to desktop and high performance accelerators. We evaluate four different platforms for our simulation framework for CT images. The evaluation results demonstrate that although in terms of performance, low-power platforms are still far from GPGPUs, the reduction of the energy consumption to almost a half in the case of the Jetson TK1 is an evident incentive that can lead to the creation of smaller and mobile medical image scanners.
KeywordsComputed Tomography (CT) Iterative reconstruction Simulation
This work has been partially supported by the grant TIN2013-41350-P, Scalable Data Management Techniques for High-End Computing Systems from the Spanish Ministry of Economy and Competitiveness, and by the EU under the COST Programme Action IC1305, Network for Sustainable Ultrascale Computing (NESUS). We gratefully acknowledge the support of NVidia Corporation with the donation of the Tesla K40 GPU used for these projects.
- 1.Archirapatkave, V., Sumilo, H., See, S.C.W., Achalakul, T.: GPGPU acceleration algorithm for medical image reconstruction. In: 2014 IEEE International Symposium on Parallel and Distributed Processing with Applications, pp. 41–46 (2011)Google Scholar
- 7.Mendl, C.B., Eliuk, S., Noga, M., Boulanger, P.: Comprehensive analysis of high-performance computing methods for filtered back-projection (2013)Google Scholar
- 8.Mukherjee, S., Moore, N., Brock, J., Leeser, M.: CUDA and OpenCL implementations of 3D CT reconstruction for biomedical imaging. In: 2012 IEEE Conference on High Performance Extreme Computing (HPEC), pp. 1–6. IEEE (2012)Google Scholar
- 9.Park, H.G., Shin, Y.G., Lee, H.: A fully GPU-based ray-driven backprojector via a ray-culling scheme with voxel-level parallelization for cone-beam CT reconstruction. Technol. Cancer Res. Treat. tcrt-2012 (2014)Google Scholar
- 11.Serrano, E., Bermejo, G., Blas, J.G., Carretero, J.: High-performance X-ray tomography reconstruction algorithm based on heterogeneous accelerated computing systems. In: 2014 IEEE International Conference on Cluster Computing (CLUSTER), pp. 331–338. IEEE (2014)Google Scholar
- 12.Serrano, E., Bermejo, G., Garcia Blas, J., Carretero, J.: Evaluation of the feasibility of making large-scale X-ray tomography reconstructions on clouds. In: 2014 14th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid), pp. 748–754. IEEE (2014)Google Scholar
- 13.Siegl, C., Hofmann, H., Keck, B., Prümmer, M., Hornegger, J.: OpenCL: a viable solution for high-performance medical image reconstruction? In: SPIE Medical Imaging, p. 79612Q. International Society for Optics and Photonics (2011)Google Scholar
- 14.Stokke, K.R., Stensland, H.K., Griwodz, C., Halvorsen, P.: Energy efficient video encoding using the tegra K1 mobile processor. In: Proceedings of the 6th ACM Multimedia Systems Conference, pp. 81–84. ACM (2015)Google Scholar