MRI is a popularly used technique for diagnosing muscle and skeletal disorders, especially of the knee. For accuracy in diagnosis, the rician noisy knee image needs to be filtered using efficient denoising algorithm. In recent years, the spatial neighborhood bilateral filter is being explored by researchers for its capacity to retain edges and tissue structures. It is noted that increase in image resolution slows down performance of the bilateral filter effectively discouraging its use. The research work proposes a cost-effective accelerated solution to the problem by implementing CUDA-based bilateral filter as applied to T2-weighted sagittal knee MRI slice. The work suggests use of GPU shared memory for optimized implementation and better speedup. The speedup achieved for 3.96 Mpixel knee MR image is 114.27 times more than that of its CPU counterpart. The results indicate average occupancy of 90.15% for image size of 6302 pixels, indicating effective parallelization. Also, over varying rician noise levels, the average PSNR achieved is 21.83455 dB indicating good filter performance.


Knee MRI Bilateral filter CUDA GPU Memory optimization Occupancy index 



The research work acknowledges the extensive support provided by the management of Army Institute of Technology, Pune, India and of the research center, College of Engineering, Pune, India.


  1. 1.
  2. 2.
    Rodrigues MB, Camanho GL (2010) Mri evaluation of knee cartilage. Rev Bras Orthop 45(4):340–346CrossRefGoogle Scholar
  3. 3.
    Joshi KR, Oza SD (2018) MRI denoising for healthcare In: Kolekar MH, and Vinod Kumar (eds) Biomedical signal and image processing in patient care. IGI Global, pp 65–85Google Scholar
  4. 4.
    Oza SD, Joshi KR (2016) Performance analysis of denoising filters for MR images. In: Chakrabarti A, Sharma N, Balas VE (eds) Advances in computing applications. Springer, Singapore, pp 86–96 CrossRefGoogle Scholar
  5. 5.
    Tomasi C, Manduchi R (1998) Bilateral filtering for gray and colour images. In: Proceedings of the international conference on computer vision. IEEE, pp 839–46Google Scholar
  6. 6.
    Dougherty G (ed) (2011) Medical image processing: techniques and applications. Springer-Verlag, New YorkGoogle Scholar
  7. 7.
    Mohana J, Krishnavenib V, Guoc Y (2014) A survey on the magnetic resonance image denoising methods. Biomedical Signal Processing and Control, Elsevier, vol 9, pp 56–69Google Scholar
  8. 8.
    Rakhshan V (2014) Image resolution in the digital era: notion and clinical implications. J Dent Shiraz Univ Med Sci 15(4):153–155Google Scholar
  9. 9.
    Scholl I, Aach T, Deserno TM et al (2011) Challenges of medical image processing. Comput Sci Res Dev 26(5), Springer-VerlagGoogle Scholar
  10. 10.
    Shi L, Liu W, Zhang H, Xie Y, Wang D (2012) A survey of GPU-based medical image computing techniques. Quant Imaging Med Surg 2(3):188–206. AME Publishing CompanyGoogle Scholar
  11. 11.
    Moulika S, Boonna W (2011) The role of GPU computing in medical image analysis and visualization. In: Proceeding of Medical Imaging, vol 7967, SPIEGoogle Scholar
  12. 12.
    Kalaiselvi T, Sriramakrishnan P, Somasundaram K (2017) Survey of using GPU CUDA programming model in medical image analysis. Inf Med Unlocked 9:133–144. ElsevierGoogle Scholar
  13. 13.
    Gravel P, Beaudoin G, De Guise JA (2004) A method for modeling noise in medical images. IEEE transactions on medical imaging 23(10)CrossRefGoogle Scholar
  14. 14.
    Gudbjartsson H, Partz S (2008) The rician distribution of noisy MRI data. In: HHS public access manuscript, PMCGoogle Scholar
  15. 15.
    Paris S, Kornprobst P, Tumblin J, Durand F (2008) Bilateral filtering: theory and applications. Comput Graph Vision 4(1):1–73CrossRefGoogle Scholar
  16. 16.
    Zhang M (2006) Bilateral filtering in image processing, a thesis. Beijing University of Posts and CommunicationsGoogle Scholar
  17. 17.
    Lekan M (2009) Impact of bilateral filter parameters on medical image noise reduction and edge preservation, a thesis. University of Toledo, Health Sciences CampusGoogle Scholar
  18. 18.
    Agarwal D, Wilf S, Dhungel A, Prasad SK (2012) Acceleration of bilateral filtering algorithm for many core and multicore architectures. In: Proceedings of IEEE 41st international conference on Parallel Processing (ICPP), pp 352–359Google Scholar
  19. 19.
    Larsson J (2015) A case study of parallel bilateral filtering on the GPU. Master Thesis, Malardalen UniversityGoogle Scholar
  20. 20.
    Nvidia CUDA C (2012) Programming guide version 4.2Google Scholar
  21. 21.
    CUDA C (2012) Best practices guide DG-05603-001_v5.0. Design guideGoogle Scholar
  22. 22.
  23. 23.
    CUDA Kernel occupancy : a detailed outlook. Application note, einfochipsGoogle Scholar
  24. 24.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.E&Tc DepartmentArmy Institute of TechnologyPuneIndia
  2. 2.E&Tc DepartmentPES Modern College of EngineeringPuneIndia

Personalised recommendations