FULLY3D Connecting our Tomographic People

Fully3D is the international community for the
people who are interested in tomographic image formation in radiology and nuclear medicine.

Sparse-View X-Ray CT Reconstruction Using L1 Regularization with Learned Sparsifying Transform

ll Yong Chun, Xuehang Zheng, Yong Long, Jeffrey Fessler

DOI:10.12059/Fully3D.2017-11-3109002

Published in:Fully3D 2017 Proceedings

Pages:115-119

Article Download
BibTeX EndNote
Keywords:
A major challenge in X-ray computed tomography (CT) is to reduce radiation dose while maintaining high quality of reconstructed images. To reduce the radiation dose, one can reduce the number of projection views (sparse-view CT); however, it becomes difficult to achieve high quality image reconstruction as the number of projection views decreases. Researchers have shed light on applying the concept of learning sparse representations from (high-quality) CT image dataset to the sparse-view CT reconstruction. We propose a new statistical CT reconstruction model that combines penalized weighted-least squares (PWLS) and `1 regularization with learned sparsifying transform (PWLS-ST-`1), and an algorithm for PWLS-ST-`1. Numerical experiments for sparse-view CT show that our model significantly improves the sharpness of edges of reconstructed images compared to the CT reconstruction methods using edgepreserving hyperbola regularizer and `2 regularization with learned ST.
​
ll Yong Chun
The University of Michigan, USA
​
Yong Long
University of Michigan - Shanghai Jiao Tong University Joint Institute, China
​
Xuehang Zheng
University of Michigan - Shanghai Jiao Tong University Joint Institute, China
​
Jeffrey Fessler
The University of Michigan, USA
  1. G. H. Chen et al., “Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic ct images from highly undersampled projection data sets,” Med. Phys., vol. 35, no. 2, pp. 660–663, Feb. 2008.
  2. I. Y. Chun and T. Talavage, “Efficient compressed sensing statistical X-ray/CT reconstruction from fewer measurements,” in Proc. 12th Intl. Mtg. on Fully 3D Image Recon. in Rad. and Nuc. Med, Lake Tahoe, CA, Jun. 2013, pp. 30–33.
  3. E. Y. Sidky et al., “Accurate image reconstruction from few-views and limited-angle data in divergent-beam CT,” J. X-ray Sci. Technol., vol. 14, no. 2, pp. 119–139, 2006.
  4. S. Ramani and J. A. Fessler, “A splitting-based iterative algorithm for accelerated statistical X-ray CT reconstruction,” IEEE Trans. Med. Imag., vol. 31, no. 3, pp. 677–688, Mar. 2012.
  5. M. Aharon et al., “K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation,” IEEE Trans. Signal Process., vol. 54, no. 11, pp. 4311–4322, Nov. 2006.
  6. S. Ravishankar and Y. Bresler, “`0 sparsifying transform learning with efficient optimal updates and convergence guarantees,” IEEE Trans. Signal Process., vol. 63, no. 9, pp. 2389–2404, May 2015.
  7. Q. Xu et al., “Low-dose X-ray CT reconstruction via dictionary learning,” IEEE Trans. Med. Imag., vol. 31, no. 9, pp. 1682–1697, Sep. 2012.
  8. X. Zheng et al., “Low dose CT image reconstruction with learned sparsifying transform,” in Proc. 12th IEE IVMSP Workshop, Bordeaux, France, Jul. 2016, pp. 1–5.
  9. S. Boyd et al., “Distributed optimization and statistical learning via the alternatingdirectionmethodofmultipliers,” Found.&TrendsinMachine Learning, vol. 3, no. 1, pp. 1–122, Jan. 2011.
  10. Q. Ding et al., “Modeling mixed Poisson-Gaussian noise in statistical image reconstruction for X-ray CT,” in Proc. 4th Intl. Mtg. on Image Formation in X-ray CT, Bamberg, Germany, pp. 399–402.
  11. C. Zhang et al., “Low-dose ct reconstruction via L1 dictionary learning regularization using iteratively reweighted least-squares,” Biomed. Eng. OnLine, vol. 15, no. 1, p. 66, Jun. 2016.
  12. J. B. Thibault et al., “A recursive filter for noise reduction in statistical iterative tomographic imaging,” in Proc. SPIE 6065, Computational Imaging IV, vol. 6065, Feb. 2006, p. 60650X.
  13. I. Y. Chun and B. Adcock, “Compressed sensing and parallel acquisition,” to appear in IEEE Trans. Inf. Theory, Mar. 2017. [Online]. Available: http://arxiv.org/abs/1601.06214
  14. I. Y. Chun et al., “Efficient compressed sensing SENSE pMRI reconstruction with joint sparsity promotion,” IEEE Trans. Med. Imag., vol. 35, no. 1, pp. 354–368, Jan. 2016.
  15. S. Ravishankar and Y. Bresler, “Efficient blind compressed sensing using sparsifying transforms with convergence guarantees and application to magnetic resonance imaging,” SIAM J. Imaging Sci., vol. 8, no. 4, pp. 2519–2557, Nov. 2015.
  16. W. P. Segars et al., “Realistic CT simulation using the 4D XCAT phantom,” Med. Phys., vol. 35, no. 8, pp. 3800–3808, Jul. 2008.
  17. C. C. Shaw, Cone beam computed tomography. Taylor & Francis, 2014.
  18. H. Nien and J. A. Fessler, “Relaxed linearized algorithms for faster Xray CT image reconstruction,” pp. 1090–1098, Apr. 2016.
  19. J. A. Fessler and W. L. Rogers, “Spatial resolution properties of penalized-likelihood image reconstruction methods: Space-invariant tomographs,” IEEE Trans. Image Process., vol. 5, no. 9, pp. 1346–58, Sep. 1996.
  20. 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, no. 2, pp. 678–689, Feb. 2015.
  21. I. Y. Chun and J. A. Fessler, “Convolutional dictionary learning: Acceleration and convergence,” under review for IEEE Trans. Image Process., Apr. 2017.
About Fully3D | Contact | Protocol |
Fully3D Support Team