Enhancement of medical MRI images based on fractal operators
Abstract
This paper presents texture enhancement algorithms for medical images. MRI brain scans often contain large, low-contrast grey areas that hold important information for doctors. Improving the texture helps highlight these areas for more detailed analysis. The study found that fractal operators are especially effective for processing medical images. The mathematical basis of these operators is explained through the Grünwald-Letnikov fractional derivatives. The process of creating fractal differential masks and applying them to enhance images is described. The fractal-based approach improves image qualities such as contrast, correlation, energy, and homogeneity. It was concluded that this method is well-suited for MRI image enhancement, both visually and based on metrics, making it a practical solution for real-world applications.
References
McRobbie, D.W., Moore, E.A., Graves, M.J., Prince, M.R. MRI from Picture to Proton. 2nd ed. Cambridge University Press, 2007
Sobel, Irwin & Feldman, Gary. (1973). A 3×3 isotropic gradient operator for image processing. Pattern Classification and Scene Analysis. 271-272.
Prewitt, J. M. S. "Object Enhancement and Extraction." In Picture Processing and Psychopictorics, edited by B. S. Lipkin and A. Rosenfeld, 75-149. New York: Academic Press, 1970.
Marr, D., and E. Hildreth. "Theory of Edge Detection." Proceedings of the Royal Society of London. Series B, Biological Sciences 207, no. 1167 (1980): 187-217.
Y. -F. Pu, J. -L. Zhou and X. Yuan, "Fractional Differential Mask: A Fractional Differential-Based Approach for Multiscale Texture Enhancement," in IEEE Transactions on Image Processing, vol. 19, no. 2, pp. 491-511, Feb. 2010, doi: 10.1109/TIP.2009.2035980.
