A Practical Medical Image Enhancement Algorithm Based on Nonsubsampled Contourlet Transform

Image enhancement technique can effectively make the medical image clear, which is conducive to the later diagnosis and treatment of diseases. During the process of medical image enhancement, there will be the pseudo-Gibbs phenomenon and noise interference, these factors can affect the enhanced effect. A novel medical image enhancement algorithm based on guided filter and nonsubsampled contourlet transform (NSCT) is proposed in this paper, this method can overcome these drawbacks to some extent. Firstly, the input image is decomposed into low-frequency as well as high-frequency components by NSCT transform; Secondly, the guided filter is used to deal with low-frequency sub-band coefficients, while the improved adaptive threshold is adopted to remove the noise contained in high-frequency sub-band coefficients; Thirdly, the processed coefficients are reconstructed with the NSCT inverse transform, and the enhanced image is obtained. The experimental results show that the proposed algorithm has a superior effect on medical image enhancement compared to current approaches.