Skip to main content
SpringerLink
Log in

Diffusion tensor imaging denoising based on Riemann nonlocal similarity

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

Diffusion tensor imaging (DTI) is a non-invasive magnetic resonance imaging technique and a special type of magnetic resonance imaging, which has been widely used to study the diffusion process in the brain. The signal-to-noise ratio of DTI data is relatively low, the shape and direction of the noisy tensor data are destroyed. This limits the development of DTI in clinical applications. In order to remove the Rician noise and preserve the diffusion tensor geometry of DTI, we propose a DTI denoising algorithm based on Riemann nonlocal similarity. Firstly, DTI tensor is mapped to the Riemannian manifold to preserve the structural properties of the tensor. The Riemann similarity measure is used to search for non-local similar blocks to form similar patch groups. Then the Gaussian mixture model is used to learn the prior distribution of patch groups. Finally, the noisy patch group is denoised by Bayesian inference and the denoised patch group is reconstructed to obtain the final denoised image. The denoising experiments of real and simulated DTI data are carried out to verify the feasibility and effectiveness of the proposed algorithm. The experimental results show that our algorithm not only effectively removes the Rician noise in the DTI image, but also preserves the nonlinear structure of the DTI image. Comparing to the existing denoising algorithms, our algorithm has better improvement of the principal diffusion direction, lower absolute error of fractional anisotropy and higher peak signal-to-noise ratio.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

References

  • Assemlal H-E, Tschumperlé D, Brun L, Siddiqi K (2011) Recent advances in diffusion MRI modeling: angular and radial reconstruction. Med Image Anal 15(4):369–396

    Article  Google Scholar 

  • Bao L, Robini M, Liu W, Zhu Y (2013) Structure-adaptive sparse denoising for diffusion-tensor MRI. Med Image Anal 17(4):442–457

    Article  Google Scholar 

  • Castaño-Moraga CA, Lenglet C, Deriche R, Ruiz-Alzola J (2007) A Riemannian approach to anisotropic filtering of tensor fields. Signal Process 87(2):263–276

    Article  MATH  Google Scholar 

  • Celledoni E, Eidnes S, Owren B, Ringholm T (2018) Dissipative numerical schemes on Riemannian manifolds with applications to gradient flows. SIAM J Sci Comput 40(6):A3789–A3806

    Article  MathSciNet  MATH  Google Scholar 

  • Chefd’Hotel C, Tschumperlé D, Deriche R, Faugeras O (2004) Regularizing flows for constrained matrix-valued images. J Math Imaging Vis 20(1–2):147–162

    Article  MathSciNet  MATH  Google Scholar 

  • Coulon O, Alexander DC, Arridge S (2004) Diffusion tensor magnetic resonance image regularization. Med Image Anal 8(1):47–67

    Article  Google Scholar 

  • Ding Z, Gore JC, Anderson AW (2005) Reduction of noise in diffusion tensor images using anisotropic smoothing. Magn Reson Med 53(2):485–490

    Article  Google Scholar 

  • Fedorov V, Ballester C (2017) Affine non-local means image denoising. IEEE Trans Image Process 26(5):2137–2148

    Article  MathSciNet  MATH  Google Scholar 

  • Govindaraj VV (2019) High performance multiple sclerosis classification by data augmentation and AlexNet transfer learning model. J Med Imaging Health Inform 9(9):2012–2021

    Article  Google Scholar 

  • Grassi DC, Conceição DM, Leite CD, Andrade CS (2018) Current contribution of diffusion tensor imaging in the evaluation of diffuse axonal injury. Arquivos de neuro-psiquiatria 76(3):189–199

    Article  Google Scholar 

  • Hong J (2019) Detecting cerebral microbleeds with transfer learning. Mach Vis Appl 30(7–8):1123–1133

    Article  Google Scholar 

  • Huang CT (2015) Bayesian inference for neighborhood filters with application in denoising. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1657–1665

  • Jayasumana S, Hartley R, Salzmann M, Li H, Harandi M (2013) Kernel methods on the Riemannian manifold of symmetric positive definite matrices. In: IEEE conference on computer vision and pattern recognition, IEEE, pp 73–80

  • Kong Y, Li Y, Wu J, Shu H (2016) Noise reduction of diffusion tensor images by sparse representation and dictionary learning. Biomed Eng Online 15(1):5

    Article  Google Scholar 

  • Krajsek K, Menzel MI, Scharr H (2016) A Riemannian Bayesian framework for estimating diffusion tensor images. Int J Comput Vis 120(3):272–299

    Article  MathSciNet  MATH  Google Scholar 

  • Liu S, Li P, Liu M, Hu Q, Shi M, Zhao J (2017) DTI image denoising based on complex shearlet domain and complex diffusion anisotropic filtering. In: International conference in communications, signal processing, and systems. Springer, pp 706–713

  • Liu S, Hu Q, Li P, Zhao J, Liu M, Zhu Z (2018a) Speckle suppression based on weighted nuclear norm minimization and grey theory. IEEE Trans Geosci Remote Sens 57(5):2700–2708

    Article  Google Scholar 

  • Liu S, Hu Q, Li P, Zhao J, Wang C, Zhu Z (2018b) Speckle suppression based on sparse representation with non-local priors. Remote Sens 10(3):439

    Article  Google Scholar 

  • Liu S, Li P, An Y, Hu Q, Zhao J (2018c) DTI denoising based on structure tensor and anisotropic smoothing. J Chin Comput Syst 39:1927–1931

    Google Scholar 

  • Liu S, Zhao C, An Y, Li P, Zhao J, Zhang Y (2019) Diffusion tensor imaging denoising based on riemannian geometric framework and sparse Bayesian learning. J Med Imaging Health Inform 9(9):1993–2003

    Article  Google Scholar 

  • Ma H, Nie Y (2018) Mixed noise removal algorithm combining adaptive directional weighted mean filter and improved adaptive anisotropic diffusion model. Math Probl Eng 2018:1–19

    Article  Google Scholar 

  • Mairal J, Bach FR, Ponce J, Sapiro G, Zisserman A (2009) Non-local sparse models for image restoration. ICCV, Citeseer, pp 54–62

    Google Scholar 

  • Notohamiprodjo M, Glaser C, Herrmann KA, Dietrich O, Attenberger UI, Reiser MF, Schoenberg SO, Michaely HJ (2008) Diffusion tensor imaging of the kidney with parallel imaging: initial clinical experience. Investig Radiol 43(10):677–685

    Article  Google Scholar 

  • Pan C (2018) Multiple sclerosis identification by convolutional neural network with dropout and parametric ReLU. J Comput Sci 28:1–10

    Article  MathSciNet  Google Scholar 

  • Pennec X (2006) Intrinsic statistics on Riemannian manifolds: basic tools for geometric measurements. J Math Imaging Vis 25(1):127

    Article  MathSciNet  MATH  Google Scholar 

  • Pennec X, Fillard P, Ayache N (2006) A Riemannian framework for tensor computing. Int J Comput Vis 66(1):41–66

    Article  MATH  Google Scholar 

  • Peyré G, Bougleux S, Cohen L (2008) Non-local regularization of inverse problems. In: European conference on computer vision. Springer, pp 57–68

  • Poupon C, Mangin J-F, Clark CA, Frouin V, Régis J, Le Bihan D, Bloch I (2001) Towards inference of human brain connectivity from MR diffusion tensor data. Med Image Anal 5(1):1–15

    Article  Google Scholar 

  • Su B, Liu Q, Chen J, Wu X (2014) Non-local mean denoising in diffusion tensor space. Exp Ther Med 8(2):447–453

    Article  Google Scholar 

  • Tschumperle D, Deriche R (2001) Diffusion tensor regularization with constraints preservation. In: IEEE computer society conference on computer vision and pattern recognition, IEEE, pp 15–19

  • Wang Z, Vemuri BC, Chen Y, Mareci TH (2004) A constrained variational principle for direct estimation and smoothing of the diffusion tensor field from complex DWI. IEEE Trans Med Imaging 23(8):930–939

    Article  Google Scholar 

  • Weissman A (2013) Optimizing information using the EM algorithm in item response theory. Ann Oper Res 206(1):627–646

    Article  MathSciNet  MATH  Google Scholar 

  • Wu LN (2008) Improved image filter based on SPCNN. Sci China Ser F-Inf Sci 51(12):2115–2125

    Article  Google Scholar 

  • Yu X (2019) Utilization of DenseNet201 for diagnosis of breast abnormality. Mach Vis Appl 30(7–8):1135–1144

    Article  Google Scholar 

  • Yu G, Sapiro G, Mallat S (2011) Solving inverse problems with piecewise linear estimators: from Gaussian mixture models to structured sparsity. IEEE Trans Image Process 21(5):2481–2499

    MathSciNet  MATH  Google Scholar 

  • Zhao G (2018) Smart pathological brain detection by synthetic minority oversampling technique, extreme learning machine, and jaya algorithm. Multim Tools Appl 77(17):22629–22648

    Article  Google Scholar 

  • Zoran D, Weiss Y (2011) From learning models of natural image patches to whole image restoration. In: International conference on computer vision, IEEE, pp 479–486

Download references

Acknowledgements

This work was supported in part by National Natural Science Foundation of China under Grant 61572063 and 61401308, Natural Science Foundation of Hebei Province under Grant F2016201142, F2019201151 and F2018210148, Opening Foundation of Machine vision Engineering Research Center of Hebei Province under Grant 2018HBMV02, Science Research Project of Hebei Province under Grant QN2016085 and QN2017306, Natural Science Foundation of Hebei University under Grant 2014-303 and 8012605, Fundamental Research Funds for the Central Universities under Grant K18JB00130. This work was also supported by the High-Performance Computing Center of Hebei University.

Author information

Authors and Affiliations

  1. College of Electronic and Information Engineering, Hebei University, Baoding, 071000, Hebei, China

    Shuaiqi Liu & Chuanqing Zhao

  2. Machine Vision Technology Creation Center of Hebei Province, Baoding, 071000, Hebei, China

    Shuaiqi Liu & Chuanqing Zhao

  3. Dean’s Office, Hebei University, Baoding, 071002, China

    Ming Liu

  4. College of Computer and Information, Beijing Jiaotong University, Beijing, 100044, China

    Qi Xin

  5. Department of Mathematics, University of Leicester, Leicester, LE1 7RH, UK

    Shui-Hua Wang

Authors
  1. Shuaiqi Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chuanqing Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ming Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qi Xin
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Shui-Hua Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Qi Xin or Shui-Hua Wang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, S., Zhao, C., Liu, M. et al. Diffusion tensor imaging denoising based on Riemann nonlocal similarity. J Ambient Intell Human Comput 14, 5369–5382 (2023). https://doi.org/10.1007/s12652-019-01642-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-019-01642-2

Keywords

Search

Navigation