Advertisement

An Automatic Parameter Decision System of Bilateral Filtering with GPU-Based Acceleration for Brain MR Images

  • Herng-Hua Chang
  • Yu-Ju Lin
  • Audrey Haihong Zhuang
Article
  • 39 Downloads

Abstract

Bilateral filters have been extensively utilized in a number of image denoising applications such as segmentation, registration, and tissue classification. However, it requires burdensome adjustments of the filter parameters to achieve the best performance for each individual image. To address this problem, this paper proposes a computer-aided parameter decision system based on image texture features associated with neural networks. In our approach, parallel computing with the GPU architecture is first developed to accelerate the computation of the conventional bilateral filter. Subsequently, a back propagation network (BPN) scheme using significant image texture features as the input is established to estimate the GPU-based bilateral filter parameters and its denoising process. The k-fold cross validation method is exploited to evaluate the performance of the proposed automatic restoration framework. A wide variety of T1-weighted brain MR images were employed to train and evaluate this parameter-free decision system with GPU-based bilateral filtering, which resulted in a speed-up factor of 208 comparing to the CPU-based computation. The proposed filter parameter prediction system achieved a mean absolute percentage error (MAPE) of 6% and was classified as “high accuracy”. Our automatic denoising framework dramatically removed noise in numerous brain MR images and outperformed several state-of-the-art methods based on the peak signal-to-noise ratio (PSNR). The usage of image texture features associated with the BPN to estimate the GPU-based bilateral filter parameters and to automate the denoising process is feasible and validated. It is suggested that this automatic restoration system is advantageous to various brain MR image-processing applications.

Keywords

Image denoising Image texture CUDA Neural networks Bilateral filter Automation 

Notes

Funding

This work was supported in part by the Ministry of Science and Technology of Taiwan under Grant No. MOST 104-2221-E-002-095 and Grant No. MOST 106-2221-E-002-082.

References

  1. 1.
    Younis A, Ibrahim M, Kabuka M, John N: An artificial immune-activated neural network applied to brain 3D MRI segmentation. J Digit Imaging 21:69–88, 2008CrossRefGoogle Scholar
  2. 2.
    Jang U, Nam Y, Kim D-H, Hwang D: Improvement of the SNR and resolution of susceptibility-weighted venography by model-based multi-echo denoising. Neuroimage 70:308–316, 2013CrossRefPubMedGoogle Scholar
  3. 3.
    Macovski A: Noise in MRI. Magn Reson Med 36:494–497, 1996CrossRefPubMedGoogle Scholar
  4. 4.
    Aja-Fernández S, Tristán-Vega A, Alberola-López C: Noise estimation in single- and multiple-coil magnetic resonance data based on statistical models. Magnetic Resonance Imaging 27:1397–1409, 2009CrossRefPubMedGoogle Scholar
  5. 5.
    Aja-Fernandez S, Alberola-Lopez C, Westin CF: Noise and signal estimation in magnitude MRI and Rician distributed images: a LMMSE approach. Image processing. IEEE Transactions on 17:1383–1398, 2008Google Scholar
  6. 6.
    Manjón JV, Carbonell-Caballero J, Lull JJ, García-Martí G, Martí-Bonmatí L, Robles M: MRI denoising using non-local means. Med Image Anal 12:514–523, 2008CrossRefPubMedGoogle Scholar
  7. 7.
    He L, Greenshields IR: A nonlocal maximum likelihood estimation method for Rician noise reduction in MR images. IEEE Trans Med Imag 28:165–172, 2009CrossRefGoogle Scholar
  8. 8.
    Liu H, Yang C, Pan N, Song E, Green R: Denoising 3D MR images by the enhanced non-local means filter for Rician noise. Magn Reson Imaging 28:1485–1496, 2010CrossRefPubMedGoogle Scholar
  9. 9.
    Manjón JV, Coupé P, Martí-Bonmatí L, Collins DL, Robles M: Adaptive non-local means denoising of MR images with spatially varying noise levels. J Magn Reson Imaging 31:192–203, 2010CrossRefPubMedGoogle Scholar
  10. 10.
    Pizurica A, Philips W, Lemahieu I, Acheroy M: A versatile wavelet domain noise filtration technique for medical imaging. IEEE Trans Med Imaging 22:323–331, 2003CrossRefPubMedGoogle Scholar
  11. 11.
    Kim J, Leira EC, Callison RC, Ludwig B, Moritani T, Magnotta VA, Madsen MT: Toward fully automated processing of dynamic susceptibility contrast perfusion MRI for acute ischemic cerebral stroke. Comput Methods Programs Biomed 98:204–213, 2010CrossRefPubMedGoogle Scholar
  12. 12.
    Malinsky M, Peter R, Hodneland E, Lundervold AJ, Lundervold A, Jan J: Registration of FA and T1-weighted MRI data of healthy human brain based on template matching and normalized cross-correlation. J Digit Imaging 26:774–785, 2013CrossRefPubMedPubMedCentralGoogle Scholar
  13. 13.
    Perona P, Malik J: Scale-space and edge detection using anisotropic diffusion. IEEE Trans Pattern Anal Machine Intell 12:629–639, 1990CrossRefGoogle Scholar
  14. 14.
    Ferrari R: Off-line determination of the optimal number of iterations of the robust anisotropic diffusion filter applied to denoising of brain MR images. Med Biol Eng Comput 51:71–88, 2013CrossRefPubMedGoogle Scholar
  15. 15.
    Tomasi C, Manduchi R: Bilateral filtering for gray and color images. Proc. Computer Vision, 1998 Sixth International Conference on: CityGoogle Scholar
  16. 16.
    Anand CS, Sahambi JS: MRI denoising using bilateral filter in redundant wavelet domain. IEEE Proc TENCON:1–6, 2008Google Scholar
  17. 17.
    Chang H-H, Chu W-C: Restoration algorithm for image noise removal using double bilateral filtering. Journal of Electronic Imaging 21:023028–023021, 2012CrossRefGoogle Scholar
  18. 18.
    Dong G, Acton ST: On the convergence of bilateral filter for edge-preserving image smoothing. Signal processing letters. IEEE 14:617–620, 2007Google Scholar
  19. 19.
    Zhang B, Allebach JP: Adaptive bilateral filter for sharpness enhancement and noise removal. Image processing. IEEE Transactions on 17:664–678, 2008Google Scholar
  20. 20.
    Farzana E, Tanzid M, Mohsin KM, Bhuiyan MIH: Bilateral filtering with adaptation to phase coherence and noise. SIViP 7:367–376, 2013CrossRefGoogle Scholar
  21. 21.
    Walker SA, Miller D, Tanabe J: Bilateral spatial filtering: refining methods for localizing brain activation in the presence of parenchymal abnormalities. Neuroimage 33:564–569, 2006CrossRefPubMedGoogle Scholar
  22. 22.
    Rydell J, Knutsson H, Borga M: Bilateral filtering of fMRI data. Selected topics in signal processing. IEEE Journal of 2:891–896, 2008Google Scholar
  23. 23.
    Hamarneh G, Hradsky J: Bilateral filtering of diffusion tensor magnetic resonance images. Image processing. IEEE Transactions on 16:2463–2475, 2007Google Scholar
  24. 24.
    McPhee KC, Denk C, Al-Rekabi Z, Rauscher A: Bilateral filtering of magnetic resonance phase images. Magn Reson Imaging 29:1023–1029, 2011CrossRefPubMedGoogle Scholar
  25. 25.
    Jaramillo R, Lentini M, Paluszny M: Improving the performance of the Prony method using a wavelet domain filter for MRI Denoising. Comput Math Methods Med 2014:10, 2014CrossRefGoogle Scholar
  26. 26.
    Wells JR, Dobbins JT: Frequency response and distortion properties of nonlinear image processing algorithms and the importance of imaging context. Med Phys 40:091906, 2013CrossRefPubMedGoogle Scholar
  27. 27.
    Kala R, Deepa P: Removal of rician noise in MRI images using bilateral filter by fuzzy trapezoidal membership function. Proc. 2017 4th International Conference on Advanced Computing and Communication Systems (ICACCS): City, 6–7 Jan. 2017 YearGoogle Scholar
  28. 28.
    Szczypiński PM, Strzelecki M, Materka A, Klepaczko A: MaZda—a software package for image texture analysis. Comput Methods Programs Biomed 94:66–76, 2009CrossRefPubMedGoogle Scholar
  29. 29.
    López-Rubio E, Florentín-Núñez MN: Kernel regression based feature extraction for 3D MR image denoising. Med Image Anal 15:498–513, 2011CrossRefPubMedGoogle Scholar
  30. 30.
    Yang X, Fei B: Multiscale segmentation of the skull in MR images for MRI-based attenuation correction of combined MR/PET. J Am Med Inform Assoc 20:1037–1045, 2013CrossRefPubMedPubMedCentralGoogle Scholar
  31. 31.
    Haykin SS: Neural Networks And Learning Machines: Pearson Education Upper Saddle River, 2009Google Scholar
  32. 32.
    Virmani J, Kumar V, Kalra N, Khandelwal N: Neural network ensemble based CAD system for focal liver lesions from B-mode ultrasound. J Digit Imaging 27:520–537, 2014CrossRefPubMedPubMedCentralGoogle Scholar
  33. 33.
    Wang J, Kato F, Yamashita H, Baba M, Cui Y, Li R, Oyama-Manabe N, Shirato H: Automatic estimation of volumetric breast density using artificial neural network-based calibration of full-field digital mammography: feasibility on Japanese women with and without breast cancer. J Digit Imaging 30:215–227, 2017CrossRefPubMedGoogle Scholar
  34. 34.
    Lin Y-J, Chang H-H: Investigation of significant attributes based on image feature and texture analysis for automatic noise reduction in MRI. The 15th international conference on biomedical engineering (ICBME 2013). IFMBE Proc 43:589–592, 2013CrossRefGoogle Scholar
  35. 35.
    General Purpose GPU Programming (GPGPU), http://www.gpgpu.org, 2016
  36. 36.
    Park IK, Singhal N, Lee MH, Cho S, Kim C: Design and performance evaluation of image processing algorithms on GPUs. IEEE Transactions on Parallel and Distributed Systems 22:91–104, 2011CrossRefGoogle Scholar
  37. 37.
    Gonzalez RC, Woods RE: Digital Image Processing: Pearson, 2010Google Scholar
  38. 38.
    Mallat SG: A theory for multiresolution signal decomposition: the wavelet representation. Pattern analysis and machine intelligence. IEEE Transactions on 11:674–693, 1989Google Scholar
  39. 39.
    Chang T, Kuo C-C: Texture analysis and classification with tree-structured wavelet transform. Image processing. IEEE Transactions on 2:429–441, 1993Google Scholar
  40. 40.
    Haar A: Zur theorie der orthogonalen funktionensysteme. Mathematische Annalen 69:331–371, 1910CrossRefGoogle Scholar
  41. 41.
    Haralick RM, Shanmugam K, Dinstein IH: Textural features for image classification. Systems, man and cybernetics, IEEE Transactions on SMC. 3:610–621, 1973Google Scholar
  42. 42.
    Antel SB, Collins DL, Bernasconi N, Andermann F, Shinghal R, Kearney RE, Arnold DL, Bernasconi A: Automated detection of focal cortical dysplasia lesions using computational models of their MRI characteristics and texture analysis. NeuroImage 19:1748–1759, 2003CrossRefPubMedGoogle Scholar
  43. 43.
    Howarth P, Ruger S: Robust texture features for still-image retrieval. Vision, image and signal processing. IEE Proceedings 152:868–874, 2005Google Scholar
  44. 44.
    Chen W, Giger ML, Li H, Bick U, Newstead GM: Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance images. Magnetic Resonance in Medicine 58:562–571, 2007CrossRefPubMedGoogle Scholar
  45. 45.
    Wei S, Yanling H, Zhizhong L, Peng W: The research of satellite cloud image recognition base on variational method and texture feature analysis. Proc. Industrial Electronics and Applications, 2007 ICIEA 2007 2nd IEEE Conference on: City, 23–25 May 2007 YearGoogle Scholar
  46. 46.
    Fisher RA, Genetiker S, Genetician S, Britain G, Généticien S: Statistical Methods for Research Workers: Oliver and Boyd Edinburgh, 1970Google Scholar
  47. 47.
    Breiman L, Friedman JH, Olshen RA, Stone CJ: Classification and Regression Trees. Monterey, CA: Wadsworth & Brooks/Cole Advanced Books & Software, 1984Google Scholar
  48. 48.
    NVIDIA CUDA ZONE, http://www.nvidia.com/cuda, 2016
  49. 49.
    Nickolls J, Buck I, Garland M, Skadron K: Scalable parallel programming with CUDA. Queue 6:40–53, 2008CrossRefGoogle Scholar
  50. 50.
    Hecht-Nielsen R: Theory of the backpropagation neural network. Proc. Neural Networks, 1989 IJCNN, International Joint Conference on: City, 0–0 1989 YearGoogle Scholar
  51. 51.
    Rumelhart DE, Hinton GE, Williams RJ: Learning representations by back-propagating errors. Nature 323:533–536, 1986CrossRefGoogle Scholar
  52. 52.
    McClelland JL, Rumelhart DE, Group PR: Parallel distributed processing. Explorations in the microstructure of cognition 2, 1986Google Scholar
  53. 53.
    Levenberg K: A method for the solution of certain problems in least squares. Quarterly of applied mathematics 2:164–168, 1944CrossRefGoogle Scholar
  54. 54.
    Marquardt DW: An algorithm for least-squares estimation of nonlinear parameters. Journal of the Society for Industrial & Applied Mathematics 11:431–441, 1963CrossRefGoogle Scholar
  55. 55.
    Suzuki K, Abe H, MacMahon H, Doi K: Image-processing technique for suppressing ribs in chest radiographs by means of massive training artificial neural network (MTANN). Medical imaging. IEEE Transactions on 25:406–416, 2006Google Scholar
  56. 56.
    Lewis CD: Industrial and business forecasting methods: a practical guide to exponential smoothing and curve fitting: Butterworth Scientific London, 1982Google Scholar
  57. 57.
    Stone M: Cross-validatory choice and assessment of statistical predictions. Journal of the Royal Statistical Society Series B (Methodological):111–147, 1974Google Scholar
  58. 58.
    MGH: Internet Brain Segmentation Repository (IBSR), http://www.cma.mgh.harvard.edu/ibsr/, 2015
  59. 59.
    McGill University: BrainWeb: Simulated Brain Database, http://www.bic.mni.mcgill.ca/brainweb/, 2015
  60. 60.
    Abdi H, Williams LJ: Principal component analysis. Wiley Interdisciplinary Reviews: Computational Statistics 2:433–459, 2010CrossRefGoogle Scholar

Copyright information

© Society for Imaging Informatics in Medicine 2018

Authors and Affiliations

  1. 1.Computational Biomedical Engineering Laboratory (CBEL), Department of Engineering Science and Ocean EngineeringNational Taiwan UniversityTaipeiTaiwan
  2. 2.Department of Radiation Oncology, Keck Medical SchoolUniversity of Southern CaliforniaLos AngelesUSA

Personalised recommendations