Simultaneous Correction of Intensity Inhomogeneity in Multi-Channel MR Images

Abstract

Intensity inhomogeneity in MR images is an undesired phenomenon, which often hampers different steps of quantitative analysis such as segmentation or registration. In this paper we propose a novel fully automated method for retrospective correction of intensity inhomogeneity. The basic assumption is that inhomogeneity correction could be improved by combining the information from multiple MR channels. Intensity inhomogeneities are simultaneously removed in a four-step iterative procedure. First, the probability distribution of intensities for two channel images is calculated. In the second step, intensity correction forces, that tend to minimize image entropies, are estimated for every image voxel. Third, inhomogeneity correction fields are obtained by regularization and normalization of all voxel forces, and last, corresponding partial inhomogeneity corrections are performed separately for each channel. The method was quantitatively evaluated on simulated and real MR brain images. The results show substantial improvement in comparison with the two state-of-the-art methods.

Intensity Inhomogeneity Correction of Structural MR Images: A Data-Driven Approach to Define Input Algorithm Parameters

“…These weights are assigned by the simulator depending on the pulse sequence parameters chosen, and can reproduce MR image contrast in a realistic manner ( Collins et al, 1998 ; Kwan et al, 1999 ). We used default settings of simulator parameters to generate an INU- and noise-free T1-weighted image in order to make our results comparable with previous studies on INU correction ( Sled et al, 1998 ; Arnold et al, 2001 ; Ashburner and Friston, 2005 ; Vovk et al, 2005 , 2006 ; Ying et al, 2009 ; Tustison et al, 2010 ; Ganzetti et al, 2016 ). The image was obtained using Spoiled Fast Low Angle Shot (SFLASH) pulse sequence, with TR = 18 ms, TE = 10 ms and α = 30°.…”

Image Enhancement Technique Applied to Low-field MR Brain Images

“…A tumor is a mass of tissue that grows out of control of the normal forces that regulate growth [1]. Most Research in developed countries show that the number of people who develop brain tumors and die from them has increased rapidly over past three decades.…”