Abstract
Purpose
To test if the proposed deep learning based denoising method denoising convolutional neural networks (DnCNN) with residual learning and multi-channel strategy can denoise three dimensional MR images with Rician noise robustly.
Materials and methods
Multi-channel DnCNN (MCDnCNN) method with two training strategies was developed to denoise MR images with and without a specific noise level, respectively. To evaluate our method, three datasets from two public data sources of IXI dataset and Brainweb, including T1 weighted MR images acquired at 1.5 and 3 T as well as MR images simulated with a widely used MR simulator, were randomly selected and artificially added with different noise levels ranging from 1 to 15%. For comparison, four other state-of-the-art denoising methods were also tested using these datasets.
Results
In terms of the highest peak-signal-to-noise-ratio and global of structure similarity index, our proposed MCDnCNN model for a specific noise level showed the most robust denoising performance in all three datasets. Next to that, our general noise-applicable model also performed better than the rest four methods in two datasets. Furthermore, our training model showed good general applicability.
Conclusion
Our proposed MCDnCNN model has been demonstrated to robustly denoise three dimensional MR images with Rician noise.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Martin-Fernandez M, Villullas S. The EM method in a probabilistic wavelet-based MRI denoising. Comput Math Methods Med. 2015;2015:182659.
Chang L, ChaoBang G, Xi Y. A MRI denoising method based on 3D nonlocal means and multidimensional PCA. Comput Math Methods Med. 2015;2015:232389.
Zhang X, Xu Z, Jia N, et al. Denoising of 3D magnetic resonance images by using higher-order singular value decomposition. Med Image Anal. 2015;19(1):75–86.
Manjon JV, Coupe P, Buades A. MRI noise estimation and denoising using non-local PCA. Med Image Anal. 2015;22(1):35–47.
Baselice F, Ferraioli G, Pascazio V. A 3d MRI denoising algorithm based on Bayesian theory. Biomed Eng Online. 2017;16(1):25.
Bhujle HV, Chaudhuri S. Laplacian based non-local means denoising of MR images with rician noise. Magn Reson Imaging. 2013;31(9):1599–610.
Chang YN, Chang HH. Automatic brain MR image denoising based on texture feature-based artificial neural networks. Biomed Mater Eng. 2015;26(Suppl 1):S1275–82.
Golshan HM, Hasanzadeh RP. An optimized LMMSE based method for 3D MRI denoising. IEEE ACM Trans Comput Biol Bioinform. 2015;12(4):861–70.
Varadarajan D, Haldar JP. A majorize-minimize framework for Rician and non-central chi MR images. IEEE Trans Med Imaging. 2015;34(10):2191–202.
Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process. 2017;26(7):3142–55.
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition; 2015. arXiv:1512.03385.
Coupe P, Yger P, Prima S, Hellier P, Kervrann C, Barillot C. An optimized blockwise nonlocal means denoising filter for 3D magnetic resonance images. IEEE Trans Med Imaging. 2008;27(4):425–41.
Coupe P, Hellier P, Prima S, Kervrann C, Barillot C. 3D wavelet subbands mixing for image denoising. Int J Biomed Imaging. 2008;2008:590183.
Manjon JV, Coupe P, Buades A, Louis Collins D, Robles M. New methods for MRI denoising based on sparseness and self-similarity. Med Image Anal. 2012;16(1):18–27.
Wu X, Yang Z, Peng J, Zhou J. Global denoising for 3D MRI. Biomed Eng Online. 2016;15(1):54.
Zhang X, Hou G, Ma J, et al. Denoising MR images using non-local means filter with combined patch and pixel similarity. PLoS One. 2014;9(6):e100240.
Aksam Iftikhar M, Jalil A, Rathore S, Hussain M. Robust brain mri denoising and segmentation using enhanced non-local means algorithm. Int J Imaging Syst Technol. 2014;24(1):52–66.
Gudbjartsson H, Patz S. The Rician distribution of noisy MRI data. Magn Reson Med. 1995;34(6):910–4 [Erratum in: Magn Reson Med 1996;36(2):332].
Konishi Y, Kanazawa Y, Usuda T, Matsumoto Y, Hayashi H, Matsuda T, Ueno J, Harada M. Simple noise reduction for diffusion weighted images. Radiol Phys Technol. 2016;9(2):221–6.
Denton EL, Chintala S, Fergus R, et al. Deep generative image models using a laplacian pyramid of adversarial networks. Adv Neural Inf Process Syst. 2015:1486–94. https://arxiv.org/abs/1506.05751.
Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets. Adv Neural Inf Process Syst. 2014:2672–80. https://arxiv.org/abs/1406.2661.
Funding
This project is not funded by any Grants.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethical approval
The local ethics committee waived the need for review board approval and written informed consent, considering the retrospective character of this study.
Conflict of interest
There is no conflict of interest.
About this article
Cite this article
Jiang, D., Dou, W., Vosters, L. et al. Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network. Jpn J Radiol 36, 566–574 (2018). https://doi.org/10.1007/s11604-018-0758-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11604-018-0758-8