An Improved Denoising of Medical Images Based on Hybrid Filter Approach and Assess Quality Metrics

Abstract:

Degradation of images and segmentation are the two most demanding fields for medical image processing, particularly when explicitly applied. The involvement of noise not only deteriorates the visual quality but also the precision of the segmentation which is vital to the medical diagnosis process of development. The complicated and monotonous main task is to manually denoise medical images such as CT, ultrasound and large numbers of clinical routine MRI images. The medical image must be denoised automatically. The proposed approach is associated with less complexity, this follows from the fact that, the design of system and time for optimization. Results show their efficacy for noise removal in medical ultrasound and MRI images .The final results of the proposed scheme in terms of noise reduction and structural preservation are excellent. However the proposed scheme is compared with existing methods and the performance of the proposed method in terms of visual quality, image quality index, peak SNR and PSNR is shown to be superior to existing methods.

• Periodical: Journal of Biomimetics, Biomaterials and Biomedical Engineering (Volume 44)
• Pages: 27-36
• DOI: https://doi.org/10.4028/www.scientific.net/JBBBE.44.27
• Online since: February 2020
• Authors: Mopidevi Suneetha, Mopidevi Subbarao*
• Keywords: CT, Denoising, MRI, Non-Local Means Filter, Wavelet Domain

References

[1] L. I. Rudin, S. Osher, and E. Fatemi, Nonlinear total variation-based noise removal algorithms,, Physica D: Nonlinear Phenomena, vol. 60, no. 1-4, p.259–268, (1992).

DOI: 10.1016/0167-2789(92)90242-f

[2] G. Aubert and P. Kornprobst, Mathematical Problems in Image Processing, Partial Differential Equations and the Calculus of Variations, vol. 147 of Applied Mathematical Sciences, Springer Science + Business Media, LLC, New York, NY, USA, 2ndedition, (2006).

DOI: 10.1007/978-0-387-44588-5

[3] T. F. Chan and J. Shen, Image Processing and Analysis: Variational, PDE, Wavelet, and Stochastic Methods, Society for Industrial and Applied Mathematics, Philadelphia, PA, USA,(2005).

DOI: 10.1186/1475-925x-5-38

[4] J. Xu, A. Feng, Y. Hao, X. Zhang, and Y. Han, Image deblurring and denoising by an improved variational model,, International Journal of Electronics and Communications, vol. 70, no. 9, p.1128–1133, (2016).

DOI: 10.1016/j.aeue.2016.05.008

[5] L. Jiang, J. Huang, X.-G. LV, and J. Liu, Alternating direction method for the high-order total variation-based Poisson noise removal problem,, Numerical Algorithms, vol. 69, no. 3, p.495–516, (2015).

DOI: 10.1007/s11075-014-9908-y

[6] M. Elad and M. Aharon, Image denoising via sparse and redundant representations over learned dictionaries,, IEEE Transactions on Image Processing, vol. 15, no. 12, p.3736–3745,(2006).

DOI: 10.1109/tip.2006.881969

[7] N. Mustafa, J. Ping, S. Ahmed, and M. Giess, Medical image de-noising schemes using wavelet transform with fixed formthresholding,, International Journal of Advanced ComputerScience and Applications, vol. 6, no. 10, p.173–178, (2015).

DOI: 10.14569/ijacsa.2015.061024

[8] W. Jifara, F. Jiang, S. Rho, M. Cheng, and S. Liu, Medicalimagedenoising using convolutional neural network: a residual learning approach,, The Journal of Supercomputing, p.1–15,(2017).

DOI: 10.1007/s11227-017-2080-0

[9] F. Zhang, N. Cai, J. Wu, G. Cen, H. Wang, and X. Chen, Image denoising method based on a deep convolution neuralnetwork,, IET Image Processing, vol. 12, no. 4, p.485–493, (2018).

DOI: 10.1049/iet-ipr.2017.0389

[10] K. Isogawa, T. Ida, T. Shiodera, and T. Takeguchi, Deep shrinkage convolutional neural network for adaptive noise reduction,, IEEE Signal Processing Letters, vol. 25, no. 2, p.224–228, (2018).

DOI: 10.1109/lsp.2017.2782270

[11] Liu C, Szeliski R, Kang SB, Zitnick CL, Freeman WT. Automatic estimation and removal of noise from a single image. IEEE Transactions on Pattern Analysis and MachineIntelligence. 2008 Feb; 30(2).

DOI: 10.1109/tpami.2007.1176

[12] Anutam, Rajni. Performance analysis of image denoisingwith wavelet thresholding methods for different levels ofdecomposition. The International Journal of Multimediaand Its Applications. 2014 Jun; 6(3).

DOI: 10.5121/ijma.2014.6303

[13] A. Piˇzurica, W. Philips, I. Lemahieu, and M. Acheroy, Despeckling SAR images using wavelets and a new class of adaptive shrinkage functions,, Proc. IEEE Internat. Conf. on Image Proc., ICIP 2001, Thessaloniki, Grece, Oct (2001).

DOI: 10.1109/icip.2001.958467

[14] A. Buades, B. Coll, and J Morel.On image denoising methods.Technical Report 2004- 15, CMLA, (2004).

[15] A. Buades, B. Coll, and J Morel.A non-local algorithm for image denoising.IEEE International Conference on Computer Vision and Pattern Recognition, (2005).

DOI: 10.1109/cvpr.2005.38

[16] A. Foi and G. Boracchi, Foveated self-similarity in nonlocal image filtering,, in SPIE Human Vision and Electronic Imaging XVII, vol. 8291. Burlingame, California, USA: SPIE, (2012).

DOI: 10.1117/12.912217

[17] A. Buades, B. Coll, and J. Morel, A review of image denoising algorithms, with a new one,, Multiscale Modeling Simulation, vol. 4, no. 2, p.490, (2005).

DOI: 10.1137/040616024