Union of Learned Sparsifying Transforms Based Low-Dose 3D CT Image Reconstruction

Xuehang Zheng, Saiprasad Ravishankar, Yong Long, Jeffrey A. Fessler

DOI:10.12059/Fully3D.2017-11-3108002

Published in:Fully3D 2017 Proceedings

Pages:69-72

Keywords:
We propose a new penalized weighted-least squares (PWLS) reconstruction method that exploits regularization based on an efficient Union of Learned TRAnsforms (PWLS-ULTRA). The union of square transforms is pre-learned from numerous 3D patches extracted from a dataset of CT volumes. The proposed PWLS-based cost function is optimized by alternating between a CT image reconstruction step, and a sparse coding and clustering step. The CT image reconstruction step is accelerated by a relaxed linearized augmented Lagrangian method with orderedsubsets that reduces the number of forward and backward projections. Simulations with 3D axial CT scans of the XCAT phantom show that for low-dose levels, the proposed method significantly improves the quality of reconstructed images compared to PWLS reconstruction with a nonadaptive edge-preserving regularizer (PWLS-EP). PWLS with regularization based on a union of learned transforms leads to better image reconstructions than using a single learned square transform.
Xuehang Zheng
University of Michigan- Shanghai Jiao Tong University Joint Institute
Saiprasad Ravishankar
University of Michigan- Shanghai Jiao Tong University Joint Institute
Yong Long
University of Michigan- Shanghai Jiao Tong University Joint Institute
Jeffrey A. Fessler
University of Michigan
  1. J.-B. Thibault, K. Sauer, C. Bouman, and J. Hsieh, “A three-dimensional statistical approach to improved image quality for multi-slice helical CT,” Med. Phys., vol. 34, pp. 4526–4544, Nov. 2007.
  2. Q. Xu, H. Yu, X. Mou, L. Zhang, J. Hsieh, and G. Wang, “Low-dose Xray CT reconstruction via dictionary learning,” IEEE Trans. Med. Imag., vol. 31, pp. 1682–1697, Sept. 2012.
  3. R. Rubinstein, T. Peleg, and M. Elad, “Analysis K-SVD: A dictionarylearning algorithm for the analysis sparse model,” IEEE Trans. Sig.Proc., vol. 61, pp. 661–677, Feb. 2013.
  4. M. Elad and M. Aharon, “Image denoising via sparse and redundant representations over learned dictionaries,” IEEE Trans. Im. Proc., vol. 15, pp. 3736–3745, Dec. 2006.
  5. M. Aharon, M. Elad, and A. Bruckstein, “K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation,” IEEE Trans. Sig. Proc., vol. 54, pp. 4311–4322, Nov. 2006.
  6. S. Ravishankar and Y. Bresler, “Learning sparsifying transforms,” IEEE Trans. Sig. Proc., vol. 61, pp. 1072–1086, Mar. 2013.
  7. S. Ravishankar and Y. Bresler, “`0 sparsifying transform learning with efficient optimal updates and convergence guarantees,” IEEE Trans. Sig. Proc., vol. 63, pp. 2389–2404, May 2015.
  8. L. Pfister and Y. Bresler, “Adaptive sparsifying transforms for iterative tomographic reconstruction,” in Proc. 3rd Intl. Mtg. on image formation in X-ray CT, pp. 107–110, 2014.
  9. B. Wen, S. Ravishankar, and Y. Bresler, “Structured overcomplete sparsifying transform learning with convergence guarantees and applications,” Intl. J. Comp. Vision, vol. 114, no. 2-3, pp. 137–167, 2015.
  10. X. Zheng, Z. Lu, S. Ravishankar, Y. Long, and J. A. Fessier, “Low dose CT image reconstruction with learned sparsifying transform,” in Proc. IEEE Wkshp. on Image, Video, Multidim. Signal Proc., pp. 1–5, July 2016.
  11. H. Nien and J. A. Fessler, “Relaxed linearized algorithms for faster X-ray CT image reconstruction,” IEEE Trans. Med. Imag., vol. 35, pp. 1090–1098, Apr. 2016.
  12. J.-B. Thibault, C. A. Bouman, K. D. Sauer, and J. Hsieh, “A recursive filter for noise reduction in statistical iterative tomographic imaging,” in Proc. SPIE, vol. 6065, pp. 60650X–1–60650X–10, 2006.
  13. H. Erdogan and J. A. Fessler, “Ordered subsets algorithms for trans-mission tomography,” Phys. Med. Biol., vol. 44, pp. 2835–2851, Nov.1999.
  14. S. Ravishankar and Y. Bresler, “MR image reconstruction from highly undersampled k-space data by dictionary learning,” IEEE Trans. Med. Imag., vol. 30, pp. 1028–1041, May 2011.
  15. W. P. Segars, M. Mahesh, T. J. Beck, E. C. Frey, and B. M. W. Tsui, “Realistic CT simulation using the 4D XCAT phantom,” Med. Phys., vol. 35, pp. 3800–3808, Aug. 2008.
  16. L. Fu, T. C. Lee, S. M. Kim, A. M. Alessio, P. E. Kinahan, Z. Chang, K. Sauer, M. K. Kalra, and B. D. Man, “Comparison between prelog and post-log statistical models in ultra-low-dose CT reconstruction,” IEEE Trans. Med. Imag., vol. 36, pp. 707–720, Mar. 2017.
  17. Z. Wang, A. C. Bovik, H. R. Sheikh, and E. P. Simoncelli, “Image quality assessment: from error visibility to structural similarity,” IEEE Trans. Im. Proc., vol. 13, pp. 600–612, Apr. 2004.
  18. J. H. Cho and J. A. Fessler, “Regularization designs for uniform spatial resolution and noise properties in statistical image reconstruction for 3D X-ray CT,” IEEE Trans. Med. Imag., vol. 34, pp. 678–689, Feb. 2015