Adaptive fuzzy hexagonal bilateral filter for brain MRI denoising
- 22 Downloads
Magnetic resonance image (MRI) plays a crucial role in medical applications for visual analysis and processing. Rician noise which arises from the MRI during acquisition can affect the quality of the image. This crucial issue should be addressed by denoising method. The proposed adaptive rician noise removal based on the bilateral filter using fuzzy hexagonal membership function improves the denoising efficiency at various noise variances and preserves the fine structures and edges. The fuzzy weights were obtained with the local mean (μi) and global mean (μg) by constructing hexagonal membership function for local order filter and bilateral filter. Bilateral filter is used to preserve the edges by smoothening the noises in MRI image and local filter is used to preserve the edges and retrieve the structural information. Brain MRI images are restored by multiplying its corresponding fuzzy weight with the restored image of local order filter and bilateral filter. Experiments on synthetic and clinical Brain MRI data were done at different noise levels by the proposed method and the existing methods. The result shows that the proposed method restores the image in better visual quality and can be well utilized for the diagnostic purpose at both low and high densities of rician noise.
KeywordsMagnetic resonance imaging Rician noise Fuzzy logic Denoising Membership function Bilateral filtering
The authors are grateful for the financial support provided by University Grants Commission (UGC) under Rajiv Gandhi National Fellowship, New Delhi, India. Grant number: F1-17.1/2016-17/RGNF-2015-17-SC-TAM-23661.
Compliance with ethical standards
Conflict of interest
There is no conflict of interest.
- 1.Abazari R, Lakestani M (2017) Fourier based discrete Shearlet transform for speckle noise reduction in medical ultrasound images. Current Medical Imaging. https://doi.org/10.2174/157340561366617040515082
- 2.Abazari R, Lakestani M (2018) A hybrid denoising algorithm based on shearlet transform method and Yaroslavsky’s filter. Multimed Tools Appl. https://doi.org/10.1007/s11042-018-5648-7
- 4.Alhihi M, Khosravi MR (2018) Operating task redistribution in hyperconverged networks. International Journal of Electrical and Computer Engineering 8(3):1629–1635Google Scholar
- 9.Chen Y, Yang J, Zhang Y, Shu H et al (2016) Structure-adaptive fuzzy estimation for random-valued impulse noise suppression. IEEE Trans Circuits Syst Video Technol. https://doi.org/10.1109/TCSVT.2016.2615444
- 14.http://www.insight-journal.org/midas/. Accessed 01 July 2017
- 16.Isik A, Firat D (2017) Bilateral intra-areolar polythelia. Breast J. https://doi.org/10.1111/tbj.12838
- 19.Kaur P, Singh G, Kaur P (2017) A review of Denoising medical images using machine learning approaches. Current Medical Imaging. https://doi.org/10.2174/1573405613666170428154156
- 20.Khan SU, Ullah N, Ahmed I, Chai WY, Khan A (2017) MRI images enhancement using genetic programming based hybrid noise removal filter approach. Current Medical Imaging. https://doi.org/10.2174/1573405613666170619093021
- 21.Khosravi MR, Akbarzadeh O, Salari SR, Samadi S, Rostami H (2017) An introduction to ENVI tools for synthetic aperture radar (SAR) image despeckling and quantitative comparison of denoising filters. In: IEEE international conference on power, control, signals and instrumentation engineering (ICPCSI), IndiaGoogle Scholar
- 24.Lim JS (1990) Two-dimensional signal and image processing. Prentice Hall, Englewood Cliffs, pp 469–476Google Scholar
- 25.Lim JS (1990) Two-dimensional signal and image processing. Prentice Hall, Englewood Cliffs, p 548Google Scholar
- 28.Misra D, Sarker S, Dhabal S, Ganguly A (2013) Effect of using genetic algorithm to de-noise MRI images corrupted with Rician noise. In: IEEE international conference on emerging trends in computing, communication and nanotechnology, Tirunelveli, India, pp 146–151Google Scholar
- 31.Phophalia A, Mitra SK (2015) Rough set based bilateral filter design for denoising brain MR images. Appl Soft Comput. https://doi.org/10.1016/j.asoc.2015.04.005
- 38.Zhang Y-D, Pan C, Sun J, Tang C (2018) Multiple sclerosis identification by convolutional neural network with drop out and parametric ReLU. J Comput Sci. https://doi.org/10.1016/j.jocs.2018.07.03