It is very interesting to reconstruct high-resolution computed tomography (CT) medical images that are very useful for clinicians to analyse the diseases. This study proposes an improved super-resolution method for CT medical images in the sparse representation domain with dictionary learning. The sparse coupled K-singular value decomposition (KSVD) algorithm is employed for dictionary learning purposes. Images are divided into two sets of low resolution (LR) and high resolution (HR), to improve the quality of low-resolution images, the authors prepare dictionaries over LR and HR image patches using the KSVD algorithm. The main idea behind the proposed method is that sparse coupled dictionaries learn about each patch and establish the relationship between sparse coefficients of LR and HR image patches to recover the HR image patch for LR image. The proposed method is compared to conventional algorithms in terms of mean peak signal-to-noise ratio and structural similarity index measurements by using three different data set images, including CT chest, CT dental and CT brain images. The authors also analysed the proposed improved method for different dictionary sizes and patch size to obtain a similar high-resolution image. These parameters play an essential role in the reconstruction of the HR images.

References

1. 1)
  - 20. Olshausen, B.A., David, J., Engan, K., et al: ‘Natural image statistics and efficient coding’, Network-Comput. Neural Syst., 1996, 7, pp. 333–3339.
2. 2)
  - 31. Seke, E., Anagün, Y., Adar, N.: ‘Multi-frame super-resolution algorithm using common vector approach’, IET Image Process., 2018, 12, (12), pp. 2292–2299.
3. 3)
  - 29. Wang, Y.S., Chen, M.Y.: ‘Single-image super-resolution reconstruction via learned geometric dictionaries and clustered sparse coding’, IEEE Trans. Image Process., 2012, 21, pp. 4016–4028.
4. 4)
  - 35. Guo, T.H.S., Mousavi, T.H., Vu, V.: ‘Deep wavelet prediction for image super-resolution’. IEEE Conf. for Computer Vision and Pattern Recognition Workshop, Honolulu, HI, USA, 2017, pp. 1100–1109.
5. 5)
  - 7. Yeganli, F., Nazzal, M., Ozkaramanli, H.: ‘Image super-resolution via sparse representation over multiple learned dictionaries based on edge sharpness and gradient phase angle’, Signal. Image. Video. Process., 2015, 9, pp. 285–293.
6. 6)
  - 25. Elad, M., Aharon, M.: ‘Image denoising via sparse and redundant representations over learned dictionaries’, IEEE Trans. Image Process., 2006, 15, pp. 3736–3745.
7. 7)
  - 36. Chaunghui, J., Qiyang, Z.: ‘Super-resolution CT image reconstruction based on dictionary learning and sparse representation’, Sci. Rep., 2018, 8, pp. 8799–8799.
8. 8)
  - 4. Liang, Z.: ‘3D MRI image super-resolution for brain combining rigid and large diffeomorphic registration’, IET Image Process., 2017, 11, pp. 1291–1301.
9. 9)
  - 33. Huang, Z., Li, Q., Zhang, T., et al: ‘Iterative weighted sparse representation for X-ray cardiovascular angiogram image denoising over learned dictionary’, IET Image Process., 2017, 12, (2), pp. 254–261.
10. 10)
  - 28. Yu, G.S., Sapiro, G.: ‘Image modeling and enhancement via structured sparse model selection’. Proc. IEEE Int. Conf. on Image Processing, Hong Kong, People's Republic of China, 2010, pp. 1641–1644. Available from: 10.1109/ICIP.2010.5653853.
11. 11)
  - 41. Sheikh, H.R., Sabir, M.F., Bovik, A.C.: ‘A statistical evaluation of recent full reference image quality assessment algorithms’, IEEE Trans. Image Process., 2006, 15, pp. 3440–3451.
12. 12)
  - 12. Zhang, H.: ‘Super-resolution reconstruction for multi-angle remote sensing images considering resolution differences’, Remote Sens., 2014, 6, pp. 637–657.
13. 13)
  - 21. Engan, K., Aase, S.O., Husøy, J.H., et al: ‘Multi-frame compression: theory and design’, Signal Process., 2000, 80, pp. 2121–2140.
14. 14)
  - 39. Pati, Y.C., Rezaiifar, R., Krishnaprasad, P.: ‘Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition signals, systems and computers’. Conf. Record of the 27th Asilomar Conf. on IEEE, Pacific Grove, CA, USA, 1993, pp. 40–44.
15. 15)
  - 38. Zhou, W., Bovik, A.C., Sheikh, H.R.: ‘Image quality assessment: from error visibility to structural similarity’, IEEE Trans. Image Process., 2004, 13, pp. 600–612.
16. 16)
  - 26. Dong, W.S., Zhang, L., Shi, G.M.: ‘Image deblurring and super-resolution-by adaptive sparse domain selection and adaptive regularization’, IEEE Trans. Image Process., 2011, 20, pp. 1838–1857.
17. 17)
  - 34. Huang, Z., Zhang, Y., Li, Q., et al: ‘Spatially adaptive denoising for X-ray cardiovascular angiogram images’, Biomed. Signal Proc. Control, 2018, 40, pp. 131–139.
18. 18)
  - 37. Yang, J.C., Wright, J.: ‘Image super-resolution via sparse representation’, IEEE Trans. Image, 2019, 19, pp. 2861–2873.
19. 19)
  - 32. Zhao, J., Sun, T., Cao, F.: ‘Image super-resolution via adaptive sparse representation and self-learning’, IET Comput. Vis., 2018, 12, (5), pp. 753–766.
20. 20)
  - 24. Chang, H.D.Y., Yeung, D.Y., Xiong, Y.: ‘Super-resolution through neighbor embedding’. Proc. IEEE Conf. on Computer Vision and Pattern Classification, Washington, DC, USA, 2004, vol. 1, pp. 275–282.
21. 21)
  - 6. Yun, S.J.: ‘Comparison of low-and standard-dose CT for the diagnosis of acute appendicitis: a meta-analysis’, Am. J. Roentgenol., 2017, 208, pp. 198–207.
22. 22)
  - 17. Ledig, C.: ‘Photo-realistic single image super-resolution using a generative adver- sarial network’. Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, Honolulu, HI, USA, 2017.
23. 23)
  - 13. Chambolle, A.: ‘An algorithm for total variation minimization and applications’, J. Math. Imaging Vis., 2004, 20, pp. 89–97.
24. 24)
  - 27. Feng, G.Z., Song, L.: ‘Learning dictionary via subspace segmentation for sparse representation’. Proc. IEEE Int. Conf. on Image- Processing (Icip), Brussels, Belgium, 2011, pp. 1245–1248. Available from: 10.1109/ICIP.2011. 6115658.
25. 25)
  - 5. Kennedy, A., Israel, O., Frenkel, A.: ‘Improved image fusion in PET/CT using hybrid image reconstruction and super-resolution’, Int. J. Biomed. Imaging, 2007, 2007, pp. 46846–46846.
26. 26)
  - 40. Yang, J., Wang, Z.: ‘Coupled dictionary training for image super-resolution’, IEEE Trans. Image Process., 2012, 21, pp. 3467–3478.
27. 27)
  - 18. Mairal, J., Bach, F., Ponce, J.: ‘Task-driven dictionary learning’, IEEE Trans. Pattern Anal. Mach. Int., 2012, 34, pp. 791–804.
28. 28)
  - 16. Zhao, J., Sun, T., Cao, F.: ‘Image super-resolution via adaptive sparse representation and self-learning’, IET Comput. Vis., 2018, 12, pp. 753–761.
29. 29)
  - 14. Freeman, B., Liu, C.: ‘Markov random fields for super-resolution and texture synthesis’, Adv. Markov Random Fields Vis. Image Process., 2011, 82, pp. 5–7.
30. 30)
  - 3. Seke, E., Anagün, Y., Adar, N.: ‘Multi-frame super-resolution algorithm using common vector approach’, IET Image Process., 2007, 2007, pp. 1–10.
31. 31)
  - 11. Dong, W., Zhang, L., Lukac, R.: ‘Sparse representation based image interpolation with nonlocal autoregressive modeling’, IEEE Trans. Image Process., 2013, 22, pp. 1382–1394.
32. 32)
  - 15. Shen, H., Zhang, L.: ‘A MAP-based algorithm for destriping and inpainting of remotely sensed images’, IEEE Trans. Geosci. Remote Sens., 2009, 47, pp. 1492–1502.
33. 33)
  - 23. Rubinstein, R., Zibulevsky, M., Elad, M.: ‘Efficient implementation of the K-SVD algorithm using batch orthogonal matching pursuit’ (Computer Science Department, Pennsylvania, 2008), Technion.
34. 34)
  - 10. Farsiu, S., Robinson, M.D., Elad, M.: ‘Fast and robust multiframe super-resolution’, IEEE Trans. Image, 2004, 13, pp. 1327–1344.
35. 35)
  - 9. Zhou, F., Yang, W., Liao, Q.: ‘Interpolation-based image super-resolution using multisurface fitting’, IEEE Trans. Image Process., 2012, 21, pp. 3312–3312.
36. 36)
  - 8. Deeba, F.: ‘Wavelet integrated residual dictionary training for single image super-resolution’, Multimedia Tools Appl., 2019, 78, pp. 27683–27701.
37. 37)
  - 2. Zhang, F.: ‘Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity’, Comput. Assist. Surg., 2019, 24, pp. 81–88.
38. 38)
  - 19. Mairal, J.: ‘Online dictionary learning for sparse coding’. Proc. 26th Annual Int. Conf. on Machine Learning, Montreal Quebec Canada, 2009.
39. 39)
  - 1. Qiu, T.: ‘Efficient medical image enhancement based on CNN-FBB model’, IET Image Process., 2019, 13, pp. 1736–1744.
40. 40)
  - 30. Ahmed, J., Shah, M.A.: ‘Single image super-resolution by directionally structured coupled dictionary learning’, EURASIP J. Image Video Process., 2016, 1, pp. 36–36.
41. 41)
  - 22. Elad, A.M., Bruckstein, M., Svd, K., et al: ‘An algorithm for designing overcomplete dictionaries for sparse representation’, IEEE Trans. Signal Process., 2006, 54, pp. 4311–43222.

Sparse representation based computed tomography images reconstruction by coupled dictionary learning algorithm

References

Related content