Noise Estimation for MRI Images with Revised Theory on Histograms of Second-order Derivatives

Main Article Content

Wai Ti Chan

Abstract

Previous research by the author in the use of histograms of second-order derivatives showed that the differences between pixels in MRI images can be determined without referring to the ground truth for the purpose of noise reduction. Yet, the results of the previous research also showed that the methodologies used could not prevent false positives and negatives. A technique has been developed to involve multiple conditions that utilize the statistics of the histograms and the circumstances of neighbours in the vicinity of a pixel. The confusion matrix for this method shows that the technique has marginal but consistent improvement across the noise levels that are tested, compared to prior methods.


 


Manuscript received: 8 Dec 2022 | Revised: 20 Feb 2023 | Accepted: 27 Apr 2023 | Published: 30 Apr 2023

Article Details

How to Cite
Chan, W. T. (2023). Noise Estimation for MRI Images with Revised Theory on Histograms of Second-order Derivatives. International Journal on Robotics, Automation and Sciences, 5(1), 6–12. https://doi.org/10.33093/ijoras.2023.5.1.2
Section
Articles

References

W.T. Chan, K.S. Sim, and F.S. Abas, "Contrast Measurement with Histograms of Second-order Derivatives of Pixels for Magnetic Resonance Images," Engineering Letters, vol. 27, no. 2, pp. 390–395, 2019.

URL: https://www.engineeringletters.com/issues_v27/issue_2/EL_27_2_16.pdf

W.T. Chan, K.S. Sim, and F.S. Abas, "Pixel Filtering and Reallocation with Histograms of Second-order Derivatives of Pixel Values for Electron Microscope Images," International Journal of Innovative Computing Information and Control, vol. 14, no. 3, pp. 915–928, 2018.

DOI: https://doi.org/10.33093/ijoras.2023.5.1.2

W.T. Chan and K.S. Sim, "Termination Factor for Iterative Noise Reduction in MRI Images Using Histograms of Second-order Derivatives," IAENG International Journal of Computer Science, vol. 48, no. 1, pp. 174–180, 2021.

DOI: https://www.iaeng.org/IJCS/issues_v48/issue_1/IJCS_48_1_19.pdf

W.T. Chan, "Conditional Noise Filter for MRI Images with Revised Theory on Second-order Histograms," International Journal on Robotics, Automation and Sciences, vol. 3, pp. 25–32, 2021.

DOI: https://doi.org/10.33093/ijoras.2021.3.5

A. Tharwat, "Classification Assessment Methods," Applied Computing and Informatics, vol. 17, no. 1, pp. 168–192, 2018.

DOI: https://doi.org/10.1016/J.ACI.2018.08.003

S. Jeyalaksshmi and S. Prasanna, "Measuring Distinct Regions of Grayscale Image Using Pixel Values," International Journal of Engineering and Technology, vol. 7, no. 1.1, pp. 121–124, 2018.

DOI: https://doi.org/10.14419/IJET.V7I1.1.9210

V. Lakshmanan, "Global and Local Image Statistics," Automating the Analysis of Spatial Grids, Springer, pp. 91-128, 2012.

DOI: https://doi.org/10.1007/978-94-007-4075-4_4

S.M. Boca and J.T. Leek, "A Direct Approach to Estimating False Discovery Rates Conditional on Covariates," PeerJ, vol. 6, no. e6035, 2018.

DOI: https://doi.org/10.1101/035675

J.V. Manjón and P. Coupé, "MRI Denoising Using Deep Learning," International Workshop on Patch-based Techniques in Medical Imaging, pp. 12-19, 2018.

DOI: https://doi.org/10.1007/978-3-030-00500-9_2

M. Fayaz, J. Haider, M.B. Qureshi, M.S. Qureshi, S. Habib, and J. Gwak, "An Effective Classification Methodology for Brain MRI Classification Based on Statistical Features, DWT and Blended ANN," IEEE Access, vol. 9, pp. 159146–159159, 2021.

DOI: https://doi.org/10.1109/ACCESS.2021.3132159