Separation-based model for low-dose CT image denoising

Wenbin Chen; Junjie Bai; Xiaohua Gu; Yuyan Li; Yanling Shao; Quan Zhang; Yi Liu; Yanli Liu; Zhiguo Gui

Separation-based model for low-dose CT image denoising

View Fulltext

Author(s): Wenbin Chen¹ ; Junjie Bai^{1, 2} ; Xiaohua Gu¹ ; Yuyan Li¹ ; Yanling Shao³ ; Quan Zhang⁴ ; Yi Liu⁴ ; Yanli Liu⁴ ; Zhiguo Gui⁴
- Affiliations: 1: School of Electrical Engineering, Chongqing University of Science and Technology , Chongqing 401331 , People's Republic of China ;
  2: Fujian Provincial University Engineering Research Center for Industrial Automation, Fujian University of Technology , Fujian 350108 , People's Republic of China ;
  3: School of Science, North University of China , Taiyuan 030051 , People's Republic of China ;
  4: Shanxi Provincial Key Laboratory for Biomedical Imaging and Big Data , North University of China , Taiyuan 030051 , People's Republic of China
Source: Volume 2020, Issue 12, December 2020, p. 1198 – 1208
DOI: 10.1049/joe.2019.0996 , Online ISSN 2051-3305

This is an open access article published by the IET under the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0/)

Received 25/07/2019, Accepted 12/08/2020, Revised 14/07/2020, Published 08/10/2020

Low-dose computed tomography (LDCT) image often contains mottle noise and streak artefacts, which seriously interfere with clinical diagnosis. In this study, the separation-based (SEPB) method is proposed for mottle noise and streak artefacts suppression and structure preservation. In it, the LDCT image is decomposed into the structural image with residual mottle noise and the streak artefacts image with residual structural details by the image decomposition structural-preserving image smoothing method. The structural image is filtered by the K-singular value decomposition algorithm to remove the residual mottle noise, and the structural details in the streak artefacts image are extracted by the morphological component analysis theory. The extracted structural details are added to the filtered structural image to get the LDCT result image. Meanwhile, in the process of extracting the structural details, the streak artefacts dictionary learned from the streak artefacts image is corrected by the local intuitional fuzzy entropy to remove its structural atoms. The experiments are conducted on the modified Shepp–Logan phantom, the pelvis phantom and the clinical abdominal data to evaluate the proposed SEPB method. Compared to several comparative denoising methods, the experimental results show that the SEPB method has better performance in subjective visual effect and objective indicators.

References

1. 1)
  - 17. Li, Z., Yu, L., Trzasko, J. D., et al: ‘Adaptive nonlocal means filtering based on local noise level for CT denoising’, Med. Phys., 2014, 41, (1), pp. 1–16.
2. 2)
  - 10. Chen, Y., Gao, D., Nie, C., et al: ‘Bayesian statistical reconstruction for low-dose X-ray computed tomography using an adaptive-weighting nonlocal prior’, Comput. Med. Image Graph., 2009, 33, (7), pp. 495–500.
3. 3)
  - 4. Liu, Y., Gui, Z., Zhang, Q., ‘Noise reduction for low-dose X-ray CT based on fuzzy logical in stationary wavelet domain’, Opt. Int. J. Light Electron., 2013, 124, (18), pp. 3348–3352.
4. 4)
  - 24. Chen, H., Zhang, Y., Kalra, M. K., et al: ‘Low-dose CT with a residual encoder-decoder convolutional neural network’, IEEE Trans. Image Process., 2017, 36, (12), pp. 2524–2535.
5. 5)
  - 18. Chen, W., Shao, Y., Wang, Y., et al: ‘A novel total variation model for low-dose CT image denoising’, IEEE Access, 2018, 6, (1), pp. 78892–78903.
6. 6)
  - 15. Ma, J., Huang, J., Feng, Q., et al: ‘Low-dose computed tomography image restoration using previous normal-dose scan’, Med. Phys., 2011, 38, (10), pp. 5713–5731.
7. 7)
  - 9. Liu, Y., Shangguan, H., Zhang, Q., et al: ‘Median prior constrained TV algorithm for sparse view low-dose CT reconstruction’, Comput. Biol. Med., 2015, 60, pp. 117–131.
8. 8)
  - 23. Chen, H., Zhang, Y., Zhang, W., et al: ‘Low dose CT via convolutional neural network’, Biomed. Opt. Exp., 2017, 8, (2), pp. 679–694.
9. 9)
  - 7. Little, K.J., La RiviŁre, P.J.: ‘Sinogram restoration in compute tomography with an edge-preserving penalty’, Med. Phys., 2015, 42, (3), pp. 1307–1320.
10. 10)
  - 22. Chen, W., Shao, Y., Jia, L., et al: ‘Low-dose CT image denoising model based on sparse representation by stationarily classified sub-dictionaries’, IEEE Access, 2019, 7, (1), pp. 116859–116874.
11. 11)
  - 37. Wang, J.: ‘Noise Reduction for Low-Dose X-Ray Computed Tomography’, Stony Brook University, America, 2006.
12. 12)
  - 16. Chen, Y., Yang, Z., Hu, Y., et al: ‘Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means’, Phys. Med. Biol., 2012, 57, (9), pp. 2667–2688.
13. 13)
  - 27. Buades, A., Coll, B., Morel, J. M.: ‘A non-local algorithm for image denoising’. IEEE Computer Society Conf. on Computer Vision and Pattern Recognition, San Diego, CA, USA, 2005, pp. 60–65.
14. 14)
  - 3. Wang, J., Lu, H., Wen, J., et al: ‘Multiscale penalized weighted least-squares sinogram restoration for low-dose X-ray computed tomography’, IEEE Trans. Biomed. Eng., 2008, 55, (3), pp. 1022–1031.
15. 15)
  - 19. Wang, Y., Shao, Y., Gui, Z., et al: ‘A novel fractional-order differentiation model for low-dose CT image processing’, IEEE Access, 2016, 4, pp. 8487–8499.
16. 16)
  - 2. Becker, S.J., Elliston, C., Dewyngaert, K., et al: ‘Breast radiotherapy in the prone position primarily reduces the maximum out-of-field measured dose to the ipsilateral lung’, Med. Phys., 2012, 39, (5), pp. 2417–2423.
17. 17)
  - 21. Hashemi, S.M., Paul, N.S., Beheshti, S., et al: ‘Adaptively tuned iterative low dose CT image denoising’, Comput. Math. Methods Med., 2015, 2015, pp. 1–12.
18. 18)
  - 13. Gao, H., Yu, H., Osher, S., et al: ‘Multi-energy CT based on a prior rank, intensity and sparsity model (PRISM)’, Inverse Probl., 2011, 27, (11), pp. 1–30, Art. no. 115012.
19. 19)
  - 31. Mairal, J., Bach, F., Ponce, J., et al: ‘Online dictionary learning for sparse coding’. Int. Conf. Machine Learning, Montreal, Quebec, Canada, 2009, pp. 689–696.
20. 20)
  - 26. Sharifzadeh, F., Akbarizadeh, G., Seifi Kavian, Y., et al: ‘Ship classification in SAR images using a new hybrid CNN-MLP classifier’, J. of the Indian Soc. of Remote Sens., 2018, 47, pp. 551–562.
21. 21)
  - 34. Dabov, K., Foi, A., Katkovnik, V., et al: ‘Image denoising by sparse 3-D transform-domain collaborative filtering’, IEEE Trans. Image Process., 2007, 16, (8), pp. 2080–2095.
22. 22)
  - 33. Xu, L., Yan, Q., Xia, Y., et al: ‘Structure extraction from texture via relative total variation’, ACM Trans. Graph., 2012, 31, (6), p. 139.
23. 23)
  - 29. Aharon, M., Elad, M., Bruckstein, A.: ‘K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation’, IEEE Trans. Signal Process., 2006, 54, (11), pp. 4311–4322.
24. 24)
  - 5. Ehman, E.C., Guimaraes, L.S., Fidler, J.L., et al: ‘Noise reduction to decrease radiation dose and improve conspicuity of hepatic lesions at contrast-enhanced 80-kV hepatic CT using projection space denoising’, Amer. J. Roentgenol., 2012, 198, (2), pp. 405–411.
25. 25)
  - 25. Samadi, F., Akbarizadeh, G., Kaabi, H.: ‘Change detection in SAR images using deep belief network: a new training approach based on morphological images’, IET Image Process., 2019, 13, (12), pp. 2255–2264.
26. 26)
  - 12. Cai, J.F., Jia, X., Gao, H., et al: ‘Cine cone beam CT reconstruction using low-rank matrix factorization: algorithm and a proof-of-principle study’, IEEE Trans. Med. Image, 2014, 33, (8), pp. 1581–1591.
27. 27)
  - 1. Brenner, D.J., Hall, E.J.: ‘Cancer risks from CT scans: now we have data, what next’? Radiology, 2012, 265, (2), pp. 330–331.
28. 28)
  - 36. Dong, W., Zhang, L., Shi, G., et al: ‘Nonlocally centralized sparse representation for image restoration’, IEEE Trans. Image Process., 2013, 22, (4), pp. 1620–1630.
29. 29)
  - 6. Zhu, Y., Zhao, M., Zhao, Y., et al: ‘Noise reduction with low dose CT data based on a modified ROF model’, Opt. Express, 2012, 20, (16), pp. 17987–18004.
30. 30)
  - 8. Niu, S.Z., Wu, H., Yu, Z.F., et al: ‘Total generalized variation minimization based on projection data for low? Dose CT reconstruction’, J. Southern Med. Univ., 2017, 37, (12), pp. 1585–1591.
31. 31)
  - 35. Gu, S., Zhang, L., Zuo, W., et al: ‘Weighted nuclear norm minimization with application to image denoising’. IEEE Conf. on Computer Vision and Pattern Recognition, Columbus, OH, USA, 2014, pp. 2862–2869.
32. 32)
  - 11. Liu, Q., Zhang, M., Zhao, J., ‘Adaptive dictionary learning in sparse gradient domain for CT reconstruction’, IEEE Trans. Image Process., 2013, 22, (12), pp. 4652–4663.
33. 33)
  - 20. Kang, D., Slomka, P., Nakazato, R., et al: ‘Image denoising of low-radiation dose coronary CT angiography by an adaptive block-matching 3D algorithm’ SPIE, Lake Buena Vista, FL, USA, 2013.
34. 34)
  - 30. Starck, J.L., Elad, M., Donoho, D.L.: ‘Redundant multiscale transforms and their application for morphological component analysis’, Adv. Imaging Electron. Phys., 2004, 132, (4), pp. 287–348.
35. 35)
  - 38. Wang, Z., Bovik, A.C., Sheikh, H.R., et al: ‘Image quality assessment: from error visibility to structural similarity’, IEEE Trans. Image Process., 2004, 13, (4), pp. 600–612.
36. 36)
  - 32. Wang, Y., Gui, Z., Zhang, Q., et al: ‘Image denoising of PDE based on local intuitionistic fuzzy entropy’, Comput. Eng. Des., 2013, 34, (12), pp. 4256–4260.
37. 37)
  - 14. Wu, D., Kim, K., El Fakhri, G., et al: ‘Iterative low-dose CT reconstruction with priors trained by artificial neural network’, IEEE Trans. Med. Image, 2017, 36, (12), pp. 2479–2486.
38. 38)
  - 28. Karacan, L., Erdem, E., Erdem, A.: ‘Structural-preserving image smoothing via region covariances’, ACM Trans. Graph., 2013, 32, (6), pp. 1–11.

Login

Not registered yet?

Share

Tools

Login to add to favourites

Key

Separation-based model for low-dose CT image denoising

References

Related content