Intensity standardization is an important preprocessing step in automatedanalysis of MRI. A popular method by Nyul et al. uses apiece-wise linear approximation of histogram matching. We showthat this method is a non-uniform trapezoidal Riemann approximationof the ideal histogram matching operation, and suggest thathistogram matching is no better than histogram equalization for intensitystandardization in MRI. Experimental results are derived usingsynthetic data.
CITATION STYLE
Knight, J., Taylor, G. W., & Khademi, A. (2017). Equivalence of histogram equalization, histogram matching and the Nyul algorithm for intensity standardization in MRI. Journal of Computational Vision and Imaging Systems, 3(1). https://doi.org/10.15353/vsnl.v3i1.170
Mendeley helps you to discover research relevant for your work.