Advertisement

Multimedia Tools and Applications

, Volume 78, Issue 10, pp 12689–12722 | Cite as

A survey of denoising techniques for multi-parametric prostate MRI

  • Gaurav GargEmail author
  • Mamta Juneja
Article

Abstract

Denoising is one of active area of research in the image-processing domain since last decade. Internal and external conditions of acquisition device are the main source of noise in an image during the procurement process, which is often impossible to avoid in practical situations. Since many different image denoising algorithms have been recommended till date, but the issue of noise elimination remains an undefended challenge. The main objective of this paper is to study and analyze the behavior of different denoising filters for multi-parametric (mp) prostate MRI so that the appropriate filter can be selected unanimously. This study evaluates the performance of fifteen denoising filters (Anisotropic, Median, Wiener, Gaussian, Mean, Wavelet, Contourlet, Bilateral, Curvelet, WHMT, NLM, GFOE, LMMSE, CURE-LET and ARF) w.r.t mp-prostate MRI i.e. T2w, DCE and DWI images in the presence of Gaussian and Rician noise. Evaluation is done in both variable and fixed level of noise. Both subjective and objective quality assessment parameters are considered for determining the final rating of filters executed over 300 mp-MRI images. This study concludes that anisotropic and NLM filter should be opted for denoising task because of their structural and other crucial details preserving capability.

Keywords

Filters Denoising Multi-parametric MRI Noise Prostate 

Notes

Compliance with ethical standards

Ethical statement

The data used in this research article is openly available and provided by [22].

Conflict of interest

There is no biomedical financial interests or potential conflicts of interest.

References

  1. 1.
    Aja-Fernandez S, Alberola-Lopez C, Westin CF (2008) Noise and signal estimation in magnitude MRI and Rician distributed images: a LMMSE approach. IEEE Trans Image Process 17(8):1383–1398.  https://doi.org/10.1109/TIP.2008.925382 MathSciNetCrossRefGoogle Scholar
  2. 2.
    Andersen AH (1995) On the Rician distribution of noisy MRI data. Magn Reson Med 34(6):910–914.  https://doi.org/10.1002/mrm.1910360222 CrossRefGoogle Scholar
  3. 3.
    Barbu A (2009) Training an active random field for real-time image denoising. IEEE Trans Image Process 18(11):2451–2462.  https://doi.org/10.1109/TIP.2009.2028254 MathSciNetzbMATHCrossRefGoogle Scholar
  4. 4.
    Blu T, Luisier F (2007) The SURE-LET approach to image denoising. IEEE Trans Image Process 16(11):2778–2786.  https://doi.org/10.1109/TIP.2007.906002 MathSciNetCrossRefGoogle Scholar
  5. 5.
    Buades A, Coll B, Morel JM (2005) A non-local algorithm for image denoising. IEEE Comput Soc Conf Comput Vision Pattern Recogn (CVPR) 2:60–65.  https://doi.org/10.1109/CVPR.2005.38 zbMATHCrossRefGoogle Scholar
  6. 6.
    Burrus CS, Gopinath RA, Guo H, Odegard JE, Selesnick IW (1998) Introduction to wavelets and wavelet transforms: a primer.(Vol. 1). Prentice Hall, New JerseyGoogle Scholar
  7. 7.
    Cahan A, Cimino JJ (2017) A learning health care system using computer-aided diagnosis. J Med Internet Res 19(3). doi: https://doi.org/10.2196/jmir.6663
  8. 8.
    Candes EJ, Donoho DL (1999) Curvelets. Available from: http://www.stat.stanford.edu/donoho/Reports/1999/Curvelets.pdf. Accessed on 15 September 2016
  9. 9.
    Cattin DP (2013) Image restoration: introduction to signal and image processing. MIAC, University of Basel. Retrieved Oct;11:93Google Scholar
  10. 10.
    Do MN, Vetterli M (2005) The contourlet transform: an efficient directional multiresolu-tion image representation. IEEE Trans Image Process 14(12):2091–2106.  https://doi.org/10.1109/TIP.2005.859376 CrossRefGoogle Scholar
  11. 11.
    Dosselmann R, Yang XD (2011) A comprehensive assessment of the structural similarity index. SIViP 5(1):81–91.  https://doi.org/10.1007/s11760-009-0144-1 CrossRefGoogle Scholar
  12. 12.
    Fabijanska A (2016) A novel approach for quantification of time intensity curves in a DCE-MRI image series with an application to prostate cancer. Comput Biol Med 73:119–130.  https://doi.org/10.1016/j.compbiomed.2016.04.010
  13. 13.
    Garg G, Juneja M (2016) Anatomical visions of prostate Cancer in Different modalities. Indian J Sci Technol 9(44). doi: https://doi.org/10.17485/ijst/2016/v9i44/105093
  14. 14.
    Garg G, Juneja M (2018) A survey of prostate segmentation techniques in different imaging modalities. Curr Med Imag Rev 14(1):19–46.  https://doi.org/10.2174/1573405613666170504145842 CrossRefGoogle Scholar
  15. 15.
    Garg G, Juneja M (2018) A survey on computer-aided detection techniques of prostate Cancer. In: progress in advanced computing and intelligent engineering, springer, Singapore (pp 115-125). doi: https://doi.org/10.1007/978-981-10-6875-112
  16. 16.
    Garg G, Juneja M (2018) Cancer detection with prostate zonal segmentation - a review. In: proceedings of the international conference on computing and communication systems, springer, Singapore (pp 829-835). doi: https://doi.org/10.1007/978-981-10-6890-479
  17. 17.
    Gonzalez RC, Woods RE, Eddins SL (2004) Digital image processing using MATLAB. Pearson Prentice Hall, Upper Saddle River, New JerseyGoogle Scholar
  18. 18.
    Haddad RA, Akansu AN (1991) A class and image processing. IEEE Trans Fast Gaussian Binomial Filters Speech Signal Process 39(3):723–727.  https://doi.org/10.1109/78.80892 CrossRefGoogle Scholar
  19. 19.
    Hore A, Ziou D (2010) Image quality metrics: PSNR vs. SSIM. In: IEEE 20th international conference on pattern recognition (icpr) (pp 2366-2369). doi: https://doi.org/10.1109/ICPR.2010.579
  20. 20.
    Huang T, Yang GJ, Tang G (1979) A fast two-dimensional median filtering algorithm. IEEE Trans Acoust Speech Signal Process 27(1):13–18.  https://doi.org/10.1109/TASSP.1979.1163188 CrossRefGoogle Scholar
  21. 21.
    Kaur R, Juneja M (2018) A survey of kidney segmentation techniques in CT images. Curr Med Imag Rev 14(2):238–250.  https://doi.org/10.2174/1573405613666161221164146 CrossRefGoogle Scholar
  22. 22.
    Lemaitre G, Mart R, Freixenet J, Vilanova JC, Walker PM, Meriaudeau F (2015) Computer-aided detection and diagnosis for prostate cancer based on mono and multi-parametric MRI: a review. Comput Biol Med 60:8–31.  https://doi.org/10.1016/j.compbiomed.2015.02.009 CrossRefGoogle Scholar
  23. 23.
    Lemaitre G, Massich J, Mart R, Freixenet J, Vilanova JC, Walker PM, Sidibe D, Meriaudeau F (2015) A boosting approach for prostate cancer detection using multi-parametric MRI. Proc: SPIE 9534, twelfth international conference on quality control by arti cial vision (pp 95340A). doi: https://doi.org/10.1117/12.2182772
  24. 24.
    Lemaitre G, Rastgoo M, Massich J, Vilanova JC, Walker PM, Freixenet J, Meyer-Baese A, Meriaudeau F, Mart R (2016) Normalization of t2w-mri prostate images using rician a priori. Proc: SPIE 9785, medical imaging:computer-aided diagnosis (pp 978529).  https://doi.org/10.1117/12.2216072
  25. 25.
    Lim JS (1990) Two-dimensional signal and image processing. Prentice Hall, Englewood Cli s, NJ 710 pGoogle Scholar
  26. 26.
    Luisier F, Blu T, Unser M (2007) A new SURE approach to image denoising: Interscale or-thonormal wavelet thresholding. IEEE Trans Image Process 16(3):593–606.  https://doi.org/10.1109/TIP.2007.891064 MathSciNetCrossRefGoogle Scholar
  27. 27.
    Luisier F, Blu T, Wolfe PJ (2012) A CURE for noisy magnetic resonance images: Chi-square unbiased risk estimation. IEEE Trans Image Process 21(8):3454–3466.  https://doi.org/10.1109/TIP.2012.2191565 MathSciNetzbMATHCrossRefGoogle Scholar
  28. 28.
    Macovski A (1996) Noise in MRI. Magn Reson Med 36(3):494–497.  https://doi.org/10.1002/mrm.1910360327 CrossRefGoogle Scholar
  29. 29.
    Manjon JV (2017) MRI Preprocessing. In: Imaging Biomarkers,Springer International Publishing (pp 53–63). doi: https://doi.org/10.1007/978-3-319-43504-65
  30. 30.
    Mohan J, Krishnaveni V, Guo Y (2014) A survey on the magnetic resonance image denoising methods. Biomed Sign Survey Process Magnet Contrl Reson 9:56–69.  https://doi.org/10.1016/j.bspc.2013.10.007 CrossRefGoogle Scholar
  31. 31.
    Oza SD, Joshi KR (2016) Performance analysis of Denoising filters for MR images. In: advances in computing applications, springer Singapore (pp 87-96). doi: https://doi.org/10.1007/978-981-10-2630-06
  32. 32.
    Perona P, Malik J (1990) Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Mach Intell 12(7):629–639.  https://doi.org/10.1109/34.56205 CrossRefGoogle Scholar
  33. 33.
    Redpath TW (1998) Signal-to-noise ratio in MRI. Br J Radiol 71(847):704–707.  https://doi.org/10.1259/bjr.71.847.9771379 CrossRefGoogle Scholar
  34. 34.
    Rodriguez AO (2004) Principles of magnetic resonance imaging. Revista mexicana de fsica 50(3):272–286Google Scholar
  35. 35.
    Romberg JK, Choi H, Baraniuk RG (2001) Bayesian tree-structured image modeling using wavelet domain hidden Markov models. IEEE Trans Image Process 10(7):1056–1068.  https://doi.org/10.1109/83.931100 CrossRefGoogle Scholar
  36. 36.
    Roth S, Black MJ (2005) Fields of experts: a framework for learning image priors. IEEE Conf Comput Vision Pattern Recogn (CVPR) 2:860–867.  https://doi.org/10.1109/CVPR.2005.160 CrossRefGoogle Scholar
  37. 37.
    Starck JL, Candes EJ, Donoho DL (2002) The curvelet transform for image denoising. IEEE Trans Image Process 11(6):670–684.  https://doi.org/10.1109/TIP.2002.1014998 MathSciNetzbMATHCrossRefGoogle Scholar
  38. 38.
    Thakur N, Juneja M (2017) Clustering based approach for segmentation of optic cup and optic disc for detection of glaucoma. Curr Med Imag Rev 13(1):99–105.  https://doi.org/10.2174/1573405612666160606124044 CrossRefGoogle Scholar
  39. 39.
    Tomasi C, Manduchi R (1998) Bilateral filtering for gray and color images. In: IEEE international conference on computer vision pp 839–846. doi: https://doi.org/10.1109/ICCV.1998.710815
  40. 40.
    Trigui R, Miteran J, Sellami L, Walker P, Hamida AB (2016) A classification approach to prostate cancer localization in 3T multi-parametric MRI. In: IEEE international conference on advanced Technologies for Signal and Image Processing (ATSIP) (pp 113-118). doi: https://doi.org/10.1109/ATSIP.2016.7523064
  41. 41.
    Trigui R, Mitran J, Walker PM, Sellami L, Hamida AB (2017) Automatic classification and localization of prostate cancer using multi-parametric MRI/MRS. Biomed Sign Process Contrl 31:189–198.  https://doi.org/10.1016/j.bspc.2016.07.015 CrossRefGoogle Scholar
  42. 42.
    Weiss Y, Freeman WT (2007) What makes a good model of natural images?. In: IEEE conference on computer vision and pattern recognition (CVPR) (pp 1-8). Doi: http://doi.ieeecomputersociety.org/10.1109/CVPR.2007.383092
  43. 43.
    Wright GA (1997) Magnetic resonance imaging. IEEE Signal Process Mag 14(1):56–66.  https://doi.org/10.1109/79.560324 MathSciNetCrossRefGoogle Scholar
  44. 44.
    Zhu H, Li Y, Ibrahim JG, Shi X, An H, Chen Y, Gao W, Lin W, Rowe DB, Peterson BS (2009) Regression models for identifying noise sources in magnetic resonance images. J Am Stat Assoc 104(486):623–637.  https://doi.org/10.1198/jasa.2009.0029 MathSciNetzbMATHCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Computer Science and Engineering, University Institute of Engineering and TechnologyPanjab UniversityChandigarhIndia

Personalised recommendations