@article{Chang2022, 
author = {Xia Chang and Haixia Zhao and Zhenxia Xue},
title = {MRI image enhancement based on feature clustering in the NSCT domain},
year = {2022},
journal = {AIMS Mathematics},
volume = {7},
number = {8},
pages = {15633-15658},
keywords = {MRI image enhancement, feature clustering, NSCT Transform, nonlinear gain function},
url = {https://www.sciopen.com/article/10.3934/math.2022856},
doi = {10.3934/math.2022856},
abstract = {The noise and low clarity in magnetic resonance imaging (MRI) images impede the doctor's diagnosis. An MRI image enhancement method is proposed in the non-subsampled contourlet transform (NSCT) domain. The coefficients of the NSCT are classified as noise component, weak edges component and strong edges component by feature clustering. We modified the transform coefficients to enhance the MRI images. The coefficients corresponding to noise are set to zero, the coefficients corresponding to strong edges are essentially unchanged, and the coefficients corresponding to weak edges are enhanced by a simplified nonlinear gain function. It is shown that the proposed MRI image enhancement method has advantages in visual quality and objective evaluation indexes compared to the state-of-the-art methods.}
}