ABSTRACT
Computed Tomography (CT) Image Reconstruction is an important technique used in a variety of domains, including medical imaging, electron microscopy, non-destructive testing and transportation security. Model-based Iterative Reconstruction (MBIR) using Iterative Coordinate Descent (ICD) is a CT algorithm that produces state-of-the-art results in terms of image quality. However, MBIR is highly computationally intensive and challenging to parallelize, and has traditionally been viewed as impractical in applications where reconstruction time is critical. We present the first GPU-based algorithm for ICD-based MBIR. The algorithm leverages the recently-proposed concept of SuperVoxels, and efficiently exploits the three levels of parallelism available in MBIR to better utilize the GPU hardware resources. We also explore data layout transformations to obtain more coalesced accesses and several GPU-specific optimizations for MBIR that boost performance. Across a suite of 3200 test cases, our GPU implementation obtains a geometric mean speedup of 4.43X over a state-of-the-art multi-core implementation on a 16-core iso-power CPU.
- X. Wang, A. Sabne, S. Kisner, A. Raghunathan, C. Bouman, and S. Midkiff, "High performance model based image reconstruction," in Proceedings of the 21st ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPoPP '16, (New York, NY, USA), pp. 2:1--2:12, ACM, 2016. Google ScholarDigital Library
- K. Sauer and C. Bouman, "A local update strategy for iterative reconstruction from projections," IEEE Transactions on Signal Processing, vol. 41(2), 1993. Google ScholarDigital Library
- J. B. Thibault, K. D. Sauer, C. A. Bouman, and J. Hsieh, "A three-dimensional statistical approach to improved image quality for multi-slice helical CT," Medical Physics, vol. 34(11), 2007. Google ScholarCross Ref
- DHS/ALERT, "Research and development of reconstruction advances in CT-based object detection systems." https://myfiles.neu.edu/groups/ALERT/strategic_studies/TO3_FinalReport.pdf, 2009.Google Scholar
- S. Degirmenci, D. G. Politte, C. Bosch, N. Tricha, and J. A. O'Sullivan, "Acceleration of iterative image reconstruction for X-ray imaging for security applications," in Proceedings of SPIE-IS&T Electronic Imaging, vol. 9401, 2015.Google Scholar
- P. Jin, E. Haneda, C. A. Bouman, and K. D. Sauer, "A model-based 3D multi-slice helical CT reconstruction algorithm for transportation security application," in Second International Conference on Image Formation in X-Ray Computed Tomography, 2012.Google Scholar
- S. J. Kisner, E. Haneda, C. A. Bouman, S. Skatter, M. Kourinny, and S. Bedford, "Model-based CT reconstruction from sparse views," in Second International Conference on Image Formation in X-Ray Computed Tomography, pp. 444--447, June 2012.Google Scholar
- P. Jin, C. A. Bouman, and K. D. Sauer, "A method for simultaneous image reconstruction and beam hardening correction," in 2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), pp. 1--5, 2013. Google ScholarCross Ref
- B. D. Man, S. Basu, J.-B. Thibault, J. Hsieh, J. A. Fessler, C. A. Bouman, and K. Sauer, "A study of different minimization approaches for iterative reconstruction in X-ray CT," in IEEE Nuclear Science Symposium, vol. 5, pp. 2708--2710, 2005.Google Scholar
- Z. Yu, J.-B. Thibault, C. A. Bouman, K. D. Sauer, and J. Hsieh, "Fast model-based X-ray CT reconstruction using spatially nonhomogeneous ICD optimization," IEEE Transactions on Image Processing, vol. 20(1), 2011. Google ScholarDigital Library
- J. A. Fessler, E. Ficaro, N. Clinthorne, and K. Lange, "Grouped-coordinate ascent algorithms for penalized-likelihood transmission image reconstruction," IEEE Transactions on Medical Imaging, vol. 16(2), 1997. Google ScholarCross Ref
- J. Zheng, S. S. Saquib, K. Sauer, and C. A. Bouman, "Parallelizable bayesian tomography algorithms with rapid, guaranteed convergence," IEEE Transactions on Image Processing, vol. 9(10), 2000. Google ScholarDigital Library
- J. E. Bowsher, M. Smith, J.Peter, and R. J. Jaszczak, "A comparison of OSEM and ICD for iterative reconstruction of SPECT brain images," Journal of Nuclear Medicine, vol. 79(5), 1998.Google Scholar
- J. Luitjens, "Faster parallel reductions on Kepler." https://devblogs.nvidia.com/parallelforall/\\faster-parallel-reductions-kepler/, 2014.Google Scholar
- Z. Yu, J. Thibault, C. A. Bouman, K. D. Sauer, and J. Hsieh, "Non-homogeneous ICD optimization for targeted reconstruction of volumetric CT," in Computational Imaging VI, part of the IS&T-SPIE Electronic Imaging Symposium, San Jose, CA, USA, January 28--29, 2008, Proceedings, p. 681404, 2008. Google ScholarCross Ref
- P. Jin, S. J. Kisner, T. Frese, and C. A. Bouman, "Model-based iterative reconstruction (MBIR) software for X-ray CT." Available from https://engineering.purdue.edu/ bouman/software/tomography/mbirct/, November 2013.Google Scholar
- X. Wang, K. A. Mohan, S. J. Kisner, C. A. Bouman, and S. P. Midkiff, "Fast voxel line update for time-space image reconstruction," in 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1209--1213, March 2016. Google ScholarDigital Library
- C.-J. Hsieh, K.-W. Chang, C.-J. Lin, S. S. Keerthi, and S. Sundararajan, "A dual coordinate descent method for large-scale linear SVM," in Proceedings of the 25th International Conference on Machine Learning, ICML '08, (New York, NY, USA), pp. 408--415, ACM, 2008. Google ScholarDigital Library
- J. F. Claerbout and F. Muir, "Robust modeling with erratic data," Geophysics, vol. 38, no. 5, pp. 826--844, 1973. Google ScholarCross Ref
- L. Wu, P. Babu, and D. P. Palomar, "Cognitive radar-based sequence design via SINR maximization," IEEE Transactions on Signal Processing, vol. 65(3), 2017. Google ScholarDigital Library
- N. Clinthorne, T. S. Pan, P. C. Chiao, W. L. Rogers, and J. A. Stamos, "Preconditioning methods for improved convergence rates in iterative reconstructions," IEEE Transactions on Medical Imaging, vol. 12(1), 1993. Google ScholarCross Ref
- J. Fessler and S. D. Booth, "Conjugate-gradient preconditioning methods for shift-variant PET image reconstruction," IEEE Transactions on Image Processing, vol. 8(5), 1999. Google ScholarDigital Library
- R. Gordon, R. Bender, and G. T. Herman, "Algebraic reconstruction techniques (ART) for three-dimensional electron microscopy and x-ray photography," Journal of Theoretical Biology, vol. 29, pp. 471--481, 1970. Google ScholarCross Ref
- J. Wang, T. Li, H. Lu, and Z. Liang, "Penalized weighted least-squares approach to sinogram noise reduction and image reconstruction for low-dose X-ray computed tomography," IEEE Transactions on Medical Imaging, vol. 25, pp. 1272--1283, Oct 2006. Google ScholarCross Ref
- B. Brendel, M. von Teuffenbach, P. B. Noël, F. Pfeiffer, and T. Koehler, "Penalized maximum likelihood reconstruction for x-ray differential phase-contrast tomography," Medical Physics, vol. 43, no. 1, pp. 188--194, 2016. Google ScholarCross Ref
- C. Kamphuis and F. J. Beekman, "Accelerated iterative transmission ct reconstruction using an ordered subsets convex algorithm," IEEE Transactions on Medical Imaging, vol. 17, pp. 1101--1105, Dec 1998. Google ScholarCross Ref
- M. Leeser, S. Mukherjee, and J. Brock, "Fast reconstruction of 3D volumes from 2D CT projection data with GPUs," BMC Research Notes, vol. 7, no. 1, pp. 1--8, 2014. Google ScholarCross Ref
- V. G. Nguyen, J. Jeong, and S. J. Lee, "GPU-accelerated iterative 3D CT reconstruction using exact ray-tracing method for both projection and backprojection," in 2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC), pp. 1--4, Oct 2013.Google Scholar
- G. C. Sharp, N. Kandasamy, H. Singh, and M. Folkert, "GPU-based streaming architectures for fast cone-beam CT image reconstruction and demons deformable registration," Physics in Medicine and Biology, vol. 52, no. 19, p. 5771, 2007. Google ScholarCross Ref
- H. Scherl, B. Keck, M. Kowarschik, and J. Hornegger, "Fast GPU-based CT reconstruction using the Common Unified Device Architecture (CUDA)," in 2007 IEEE Nuclear Science Symposium Conference Record, vol. 6, pp. 4464--4466, Oct 2007.Google Scholar
- F. Xu and K. Mueller, "Real-time 3D computed tomographic reconstruction using commodity graphics hardware," Physics in Medicine and Biology, vol. 52, no. 12, p. 3405, 2007. Google ScholarCross Ref
- E. Papenhausen and K. Mueller, "Rapid rabbit: Highly optimized GPU accelerated cone-beam CT reconstruction," in 2013 IEEE Nuclear Science Symposium and Medical Imaging Conference (2013 NSS/MIC), pp. 1--2, Oct 2013.Google Scholar
- J. H. Cho and J. A. Fessler, "Accelerating ordered-subsets image reconstruction for x-ray CT using double surrogates," 2012.Google ScholarCross Ref
- L. A. Flores, V. Vidal, P. Mayo, F. Rodenas, and G. Verdú, "Iterative reconstruction of CT images on GPUs," in 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 5143--5146, July 2013. Google ScholarCross Ref
- M. G. McGaffin and J. A. Fessler, "Alternating Dual Updates Algorithm for X-ray CT Reconstruction on the GPU," IEEE Transactions on Computational Imaging, vol. 1, pp. 186--199, Sept 2015. Google ScholarCross Ref
- S. V. Venkatakrishnan, L. F. Drummy, M. Jackson, M. D. Graef, J. Simmons, and C. A. Bouman, "Model-based iterative reconstruction for bright-field electron tomography," IEEE Transactions on Computational Imaging, vol. 1, pp. 1--15, March 2015. Google ScholarCross Ref
- S. V. Venkatakrishnan, L. F. Drummy, M. A. Jackson, M. D. Graef, J. Simmons, and C. A. Bouman, "A model based iterative reconstruction algorithm for high angle annular dark field-scanning transmission electron microscope (haadf-stem) tomography," IEEE Transactions on Image Processing, vol. 22, pp. 4532--4544, Nov 2013. Google ScholarDigital Library
- Y. Nesterov, "Efficiency of coordinate descent methods on huge-scale optimization problems," SIAM Journal on Optimization, vol. 22, no. 2, pp. 341--362, 2012. Google ScholarCross Ref
- A. Sabne, P. Sakdhnagool, and R. Eigenmann, "Effects of compiler optimizations in openmp to cuda translation," in International Workshop on OpenMP, pp. 169--181, Springer Berlin Heidelberg, 2012. Google ScholarDigital Library
- A. Sabne, P. Sakdhnagool, S. Lee, and J. S. Vetter, "Evaluating performance portability of OpenACC," in International Workshop on Languages and Compilers for Parallel Computing, pp. 51--66, Springer International Publishing, 2014.Google Scholar
Index Terms
- Model-based Iterative CT Image Reconstruction on GPUs
Recommendations
Model-based Iterative CT Image Reconstruction on GPUs
PPoPP '17Computed Tomography (CT) Image Reconstruction is an important technique used in a variety of domains, including medical imaging, electron microscopy, non-destructive testing and transportation security. Model-based Iterative Reconstruction (MBIR) using ...
GPU-Based Iterative Medical CT Image Reconstructions
The algebraic reconstruction technique (ART) is an iterative algorithm for CT (i.e., computed tomography) image reconstruction that delivers better image quality with less radiation dosage than the industry-standard filtered back projection (FBP). ...
An Enhanced Image Reconstruction Tool for Computed Tomography on GPUs
CF'17: Proceedings of the Computing Frontiers ConferenceThe algebraic reconstruction technique (ART) is an iterative algorithm for CT (i.e., computed tomography) image reconstruction that delivers better image quality with less radiation dosage than the industry-standard filtered back projection (FBP). ...
Comments