Enhancement of Medical Images Based on Guided Filter in Nonsubsampled Shearlet Transform Domain

In order to deal with the pseudo-Gibbs phenomenon and noise interference in image processing, a medical image enhancement approach based on the nonsubsampled shearlet transform (NSST) theory is proposed in this paper. The whole process of the method can be divided into the following steps: First, the original image is decomposed into one low-frequency sub-band and some high-frequency sub-bands; Second, the guided filter is used to adjust the low-frequency sub-band coefficients to enhance the contrast of the image, and the adaptive threshold is utilized to remove the noise of the high-frequency sub-bands coefficients; Third, the processed coefficients are reconstructed with the inverse nonsubsampled shearlet transform, and the enhanced image is obtained. Extensive simulation results demonstrate the effectiveness of the proposed algorithm on enhancing the medical images compared to the state-of-the-art approaches.