350 rub
Journal Dynamics of Complex Systems - XXI century №3 for 2016 г.
Article in number:
Study of noise reduction algorithms at various artificial noises on MRI images
Keywords: MRI image denoising algorithms brain tumor peak signal to noise ratio (PSNR)
Authors:
A.R.A. Abdulraqeb - Post-graduate Student, Vladimir State University named after A.&N. Stoletovs. E-mail: atef_alsanawy@hotmail.com L.T. Sushkova - Dr. Sc. (Eng.), Head of Department, Vladimir State University named after A.&N. Stoletovs. E-mail: ludm@vlsu.ru M.M. Abounassif - Consultant Diagnostic Radiology, King Saud Medical City, MOH, Riyadh, Saudi Arabia. E-mail: mabounassif@ksmc.med.sa P.J. Parameaswari - Ph.D., Biostatistician, King Saud Medical City, MOH, Riyadh, Saudi Arabia. E-mail: parameaswari@ksmc.med.sa M.A. Muteb - Ph.D., Research Center Director, King Saud Medical City, MOH, Riyadh, Saudi Arabia. E-mail: parameaswari@ksmc.med.sa
Abstract:
The aim of this research was to compare the often used denoising algorithm on MRI images of patients of specialized clinics from two different geographical locations (Vladimir & Riyadh) and find the optimal algorithm for the preprocessing stage for further segmentation, and treatment planning. The original images were noised separately by adding Gaussian noise with zero mean and 0.01 variance, multiplicative noise with zero mean and 0.04 variance, salt and pepper with zero mean and 0.05 variance and later denoised by Average, Gaussian, Wiener, Median, wavelet Haar filters. The denoising algorithms were compared with Peak signal to noise Ratio (PSNR). It was found that in the case of images noised by Gaussian and Salt and Pepper noises, median filter reduced majority of the noises and had the maximum average of PSNR value. In the case of images without noise, Gaussian filter with a standard deviation of 0.5 had the maximum average of PSNR value. In the case of images noised by the multiplicative noise, the average filter had the maximum average of PSNR value followed by median and Gaussian filters.
Pages: 36-44
References

 

  1. Anisha S.R., Venugopala Krishnan J. Comparison of various filters for noise removal in MRI brain image.2015 International Conference on Futuristic Trends in Computing and Communication. 2015. P. 68−73.
  2. Oulhaj H., Amine A., Aziza M., Aboutajdine D. Noise reduction in medical imaging - comparison of noise removal algorithms. International Conference on Mathematics and Computer Science. 2012. P. 344−349.
  3. Ramesh Jain, Rangachar Kasturi, Brian G. Schunck. Machine vision. McGraw-Hill. Inc. 1995. 572 p.
  4. Balafar M.A., Review Of Noise Reducing Algorithms For Brain MRI Images. International Journal on Technical and Physical Problems of Engineering. 2012. Issue 13. V. 4. № 4. P. 54−59.
  5. A. Anilet Bala, Chiranjeeb Hati, CH Punith. Image Denoising Method Using curvelet Transform and Wiener Filter. International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering. V. 3. Issue 1.January 2014. P. 6943−6950.
  6. Maryam Amirmazlaghani, Hamidreza Amindavar. A Novelwavelet Domain Statistical Approach for Denoising SAR Images ICIP. 2009.
  7. Bhumika Gupta, Mr. Shailendra Singh Negi. Image Denoising with Linear and Non-Linear Filters: A REVIEW // IJCSI International Journal of Computer Science Issues. V. 10. Issue 6. № 2. November 2013. P. 1694−0814.
  8. Pushpavalli R., Sivarajde G., Image Denoising Using A New Hybrid NeuroFuzzy Filtering Technique // International journal of scientific & technology research V. 2. issue 5. may 2013.
  9. Yong-Hwan Lee, Sang-Burm Rhee. Wavelet-based Image Denoising with Optimal Filter // International Journal of Information Processing Systems V. 1. № 1. 2005.
  10. Siti Noraini Sulaiman, Siti Mastura Che Ishak, Iza Sazanita Isa, Norhazimi Hamzah. Denoising of Noisy MRI Brain Imageby Using Switching-based Clustering Algorithm. Energy, Environment, Biology and Biomedicine. 2014. P. 33−39.
  11. Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins. Digital image processing using MATLAB. second edition. Gatesmark. LLC. 2009. P. 845.
  12. http://www.mathworks.com/help/images/ref/fspecial.html (date of access 01.03.2016).
  13. Kanwaljot Singh Sidhu, Baljeet Singh Khaira, Ishpreet Singh Virk. Medical Image Denoising In The Wavelet Domain Using Haar And DB3 Filtering. International Refereed Journal of Engineering and Science. 2012. V. 1. Issue 1. P. 001−008.
  14. Priya C. Nair, Suganthi G. Comparative Analysis of Various Denoising Techniques for MRI Images. International Journal of Science and Research. 2013. Issue 8. V. 4. P. 1437−1440.
  15. Ruchika Chandel, Gaurav Gupta. Image Filtering Algorithms and Techniques: A Review // International Journal of Advanced Research in Computer Science and Software Engineering. 2013. Issue 10. V. 3. P. 198−202.
  16. Ramesh Jain, Rangachar Kasturi, Brian G. Schunck. Machine vision. (McGraw-Hill. Inc. 1995).
  17. Ajay Kumar Nain, Surbhi Singhania, Shailender Gupta, Bharat Bhushan. A Comparative Study of Mixed Noise Removal Techniques. International Journal of Signal Processing, Image Processing and Pattern Recognition. V. 7. № 1. (2014). P. 405−414.
  18. www.spss.com date of access (01.03.2016).
  19. Tanimoto T. (17 Nov 1958). An Elementary Mathematical theory of Classification and Prediction // Internal IBM. Technical Report. 1957.