Abstract
The general procedure of image denoising is solving an inverse problem with some statistic prior information as the regularization. We propose a novel noise removal method for Magnetic Resonance (MR) images based on the Fuzzy Gaussian Mixture Model (FGMM) Clustering of image patches. In this method, the FGMM, which is an extension of the Gaussian Mixture Model (GMM), has been trained using overlapping clean patches randomly selected from the image database firstly. Then the objective function, which is the sum of the image corruption model and the prior model, is constructed. We optimize the objective using the “Half Quadratic Splitting” method and obtain an expression of iteration to restore the whole image. Finally, we use the proposed method to denoise Magnetic Resonance (MR) images. The experimental results show that the proposed method achieves good performance in MR image denoising.
Supported by Macau Science and Technology development fund (FDCT): FDCT/196/2017/A3.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ahishakiye, E., Gijzen, M.B.V., Tumwiine, J., Obungoloch, J.: A dictionary learning approach for noise-robust image reconstruction in low-field magnetic resonance imaging. In: 2020 IST-Africa Conference (IST-Africa), pp. 1–12, May 2020. iSSN: 2576–8581
Alekya, K., Vijayalakshmi, K., Radha, N., Nandan, D.: Colour image de-noising analysis based on improved non-local mean filter. In: Kumar, A., Mozar, S. (eds.) ICCCE 2020. LNEE, vol. 698, pp. 1169–1178. Springer, Singapore (2021). https://doi.org/10.1007/978-981-15-7961-5_108
Buades, A., Coll, B., Morel, J.M.: Non-local means denoising. Image Process. Line 1, 208–212 (2011)
Chen, Z., Zhou, Z., Adnan, S.: Joint low-rank prior and difference of Gaussian filter for magnetic resonance image denoising. Med. Biolog. Eng. Comput. 59(3), 607–620 (2021)
Cheng, K., Du, J., Zhou, H., Zhao, D., Qin, H.: Image super-resolution based on half quadratic splitting. Infrared Phys. Technol. 105, 103193 (2020)
Collins, D.L., et al.: Design and construction of a realistic digital brain phantom. IEEE Trans. Med. Imaging 17(3), 463–468 (1998). https://doi.org/10.1109/42.712135. Conference Name: IEEE Transactions on Medical Imaging
Dong, W., Li, X., Zhang, L., Shi, G.: Sparsity-based image denoising via dictionary learning and structural clustering. In: CVPR 2011, pp. 457–464, June 2011. https://doi.org/10.1109/CVPR.2011.5995478. iSSN: 1063-6919
Goyal, B., Agrawal, S., Sohi, B., Dogra, A.: Noise Reduction in MR brain image via various transform domain schemes. Res. J. Pharm. Technol. 9(7), 919 (2016). https://doi.org/10.5958/0974-360X.2016.00176.1
Guo, L., Chen, L., Chen, C.L.P.: Shadowed non-local image guided filter. In: Ninth International Conference on Graphic and Image Processing (ICGIP 2017), vol. 10615, p. 1061552. International Society for Optics and Photonics, April 2018. https://doi.org/10.1117/12.2302633. https://www.spiedigitallibrary.org/conference-proceedings-of-spie/10615/1061552/Shadowed-non-local-image-guided-filter/10.1117/12.2302633.short
Guo, L., Chen, L., Li, T., Chen, C.L.P.: Fuzzy non-local image guided filter and averaging. In: 2017 International Conference on Fuzzy Theory and Its Applications (iFUZZY), pp. 1–6, November 2017. https://doi.org/10.1109/iFUZZY.2017.8311801. iSSN: 2377-5831
Guo, L., Chen, L., Wu, Y., Chen, C.L.P.: Image guided Fuzzy C-means for image segmentation. In: 2016 International Conference on Fuzzy Theory and Its Applications (iFuzzy), pp. 1–6, November 2016. https://doi.org/10.1109/iFUZZY.2016.8004969. iSSN: 2377-5831
He, R., Zheng, W., Tan, T., Sun, Z.: Half-quadratic-based iterative minimization for robust sparse representation. IEEE Trans. Pattern Anal. Mach. Intell. 36(2), 261–275 (2014). https://doi.org/10.1109/TPAMI.2013.102. Conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence
Heo, Y.C., Kim, K., Lee, Y.: Image denoising using non-local means (NLM) approach in magnetic resonance (MR) imaging: a systematic review. Appl. Sci. 10(20), 7028, January 2020
Ichihashi, H., Miyagishi, K., Honda, K.: Fuzzy c-means clustering with regularization by K-L information. In: 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297), vol. 2, pp. 924–927, December 2001. https://doi.org/10.1109/FUZZ.2001.1009107
Kalavathi, P., Priya, T.: Removal of impulse noise using Histogram-based localized wiener filter for MR brain image restoration. In: 2016 IEEE International Conference on Advances in Computer Applications (ICACA), pp. 4–8, October 2016. https://doi.org/10.1109/ICACA.2016.7887913
Lin, L., Meng, X., Liang, X.: Reduction of impulse noise in MRI images using block-based adaptive median filter. In: 2013 IEEE International Conference on Medical Imaging Physics and Engineering, pp. 132–134, October 2013. https://doi.org/10.1109/ICMIPE.2013.6864519
Manjón, J.V., Coupé, P., Buades, A.: MRI noise estimation and denoising using non-local PCA. Med. Image Anal. 22(1), 35–47 (2015)
Manjón, J.V., Coupé, P., Buades, A., Louis Collins, D., Robles, M.: New methods for MRI denoising based on sparseness and self-similarity. Med. Image Anal. 16(1), 18–27 (2012)
Miyamoto, S., Umayahara, K.: Fuzzy clustering by quadratic regularization. In: 1998 IEEE International Conference on Fuzzy Systems Proceedings. IEEE World Congress on Computational Intelligence (Cat. No.98CH36228), vol. 2, pp. 1394–1399, May 1998. https://doi.org/10.1109/FUZZY.1998.686323. iSSN: 1098-7584
Mustafi, A., Ghorai, S.K.: A novel blind source separation technique using fractional Fourier transform for denoising medical images. Optik 124(3), 265–271 (2013)
Nayak, D.R., Dash, R., Majhi, B.: Brain MR image classification using two-dimensional discrete wavelet transform and AdaBoost with random forests. Neurocomputing 177, 188–197 (2016)
Orujov, F., Maskeliūnas, R., Damaševičius, R., Wei, W.: Fuzzy based image edge detection algorithm for blood vessel detection in retinal images. Appl. Soft Comput. 94, 106452 (2020)
Singh, D., Kaur, A.: Fuzzy based fast non local mean filter to denoise Rician noise. Mater. Today Proc. (2021)
Wang, H., Cen, Y., He, Z., He, Z., Zhao, R., Zhang, F.: Reweighted low-rank matrix analysis with structural smoothness for image denoising. IEEE Trans. Image Process. 27(4), 1777–1792 (2018). https://doi.org/10.1109/TIP.2017.2781425. Conference Name: IEEE Transactions on Image Processing
Wei, H., Chen, L., Xu, L.: Tensor decomposition for poisson image denoising. In: 2019 International Conference on Fuzzy Theory and Its Applications (iFUZZY), pp. 158–162, November 2019. https://doi.org/10.1109/iFUZZY46984.2019.9066222. iSSN: 2377-5831
Zoran, D., Weiss, Y.: From learning models of natural image patches to whole image restoration. In: 2011 International Conference on Computer Vision, pp. 479–486. IEEE, Barcelona, November 2011. https://doi.org/10.1109/ICCV.2011.6126278. http://ieeexplore.ieee.org/document/6126278/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Shi, Z., Chen, L. (2021). MR Image Denoising by FGMM Clustering of Image Patches. In: Peng, Y., Hu, SM., Gabbouj, M., Zhou, K., Elad, M., Xu, K. (eds) Image and Graphics. ICIG 2021. Lecture Notes in Computer Science(), vol 12889. Springer, Cham. https://doi.org/10.1007/978-3-030-87358-5_48
Download citation
DOI: https://doi.org/10.1007/978-3-030-87358-5_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87357-8
Online ISBN: 978-3-030-87358-5
eBook Packages: Computer ScienceComputer Science (R0)