Adaptive-Order Regression-Based MR Image Super-Resolution

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 506)


To overcome the resolution limitation of magnetic resonance imaging (MRI), performing super-resolution (SR) on these clinical images is needed. Recently, a high-order regression-based SR framework demonstrates its advantage in producing fine details for MR image. However, the high time cost limits its application. To reduce time complexity, an adaptive-order strategy is proposed in this paper. Image structure tensor is used to classify the whole voxels into different groups. Afterward, the regression order is adaptively selected according to the classification result. Numerical experiments demonstrated that the proposed SR method can get a good balance between reconstruction quality and computation efficiency.


MRI Regression-based Super-resolution Adaptive order Structure tensor 



This work was supported in part by the National Natural Science Foundation of China under Grant 61602065, Sichuan province Key Technology Research and Development project under Grant 2017RZ0013, Scientific Research Foundation of the Education Department of Sichuan Province under Grant No.17ZA0062, J201608 supported by Chengdu University of Information and Technology (CUIT) Foundation for Leaders of Disciplines in Science, project 762001009 supported by Open Fund of CUIT, and project KYTZ201610 supported by the Scientific Research Foundation of CUIT.


  1. 1.
    Reeth EV, Tham IW, Tan CH, Poh CL (2012) Super-resolution in magnetic resonance imaging: a review. Concep Magn Reson Part A 40((6):306–325CrossRefGoogle Scholar
  2. 2.
    Jog A, Carass A, Prince JL (2016) Self super-resolution for magnetic resonance images. In: Proc. MICCAI, pp 553–560Google Scholar
  3. 3.
    Greenspan H (2009) Super-resolution in medical imaging. Comput J 52(1):43–63CrossRefGoogle Scholar
  4. 4.
    Buades A, Coll B, Morel JM (2005) A non local algorithm for image denoising. IEEE Comput Soc Conf Comput Vis Pattern Recognit 2:60–65zbMATHGoogle Scholar
  5. 5.
    Manjón JV, Coupé P, Buades A et al (2010) Non-local MRI upsampling. Med Image Anal 14:784–792CrossRefGoogle Scholar
  6. 6.
    Plenge E, Poot DH, Niessen WJ et al (2013) Super-resolution reconstruction using cross-scale self-similarity in multi-slice MRI. In: Proc. MICCAI, pp 123–130Google Scholar
  7. 7.
    Rousseau F (2010) A non-local approach for image super-resolution using intermodality priors. Med Image Anal 14(4):594–605CrossRefGoogle Scholar
  8. 8.
    Manjón JV, Coupé P, Buades A et al (2010) MRI superresolution using self-similarity and image priors. Int J Biomed Imaging:Article ID 425891Google Scholar
  9. 9.
    Coupé P, Manjón JV, Chamberland M et al (2013) Collaborative patch-based super-resolution for diffusion-weighted images. NeuroImage 83:245–261CrossRefGoogle Scholar
  10. 10.
    Jafari-Khouzani K (2014) MRI upsampling using feature-based nonlocal means approach. IEEE Trans Med Imag 33(10):1969–1985CrossRefGoogle Scholar
  11. 11.
    Jafari-Khouzani K, Gerstner E, Rosen B et al (2015) Upsampling dynamic contrast enhanced MRI. IEEE Int Symp Biomed Imaging:1032–1035Google Scholar
  12. 12.
    Hu J, Wu X, Zhou J (2017) Second-order regression-based MR image upsampling. Comput Math Methods Med:Article ID 6462832Google Scholar
  13. 13.
    Hu J, Luo Y (2014) Single-image superresolution based on local regression and nonlocal self-similarity. J Elect Imaging 23(3):033014–033014–14MathSciNetCrossRefGoogle Scholar
  14. 14.
    Choi B, Kim SD, Ra JB (2008) Region-based super-resolution using adaptive diffusion regularization. Opt Eng 47(2):027006-11–027006-11Google Scholar
  15. 15.
    Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG, part of Springer Nature 2019

Authors and Affiliations

  • Jing Hu
    • 1
  1. 1.Department of Computer ScienceChengdu University of Information TechnologyChengduPeople’s Republic of China

Personalised recommendations