Method of Improved Fuzzy Contrast Combined Adaptive Threshold in NSCT for Medical Image Enhancement

Abstract

Noises and artifacts are introduced to medical images due to acquisition techniques and systems. This interference leads to low contrast and distortion in images, which not only impacts the effectiveness of the medical image but also seriously affects the clinical diagnoses. This paper proposes an algorithm for medical image enhancement based on the nonsubsampled contourlet transform (NSCT), which combines adaptive threshold and an improved fuzzy set. First, the original image is decomposed into the NSCT domain with a low-frequency subband and several high-frequency subbands. Then, a linear transformation is adopted for the coefficients of the low-frequency component. An adaptive threshold method is used for the removal of high-frequency image noise. Finally, the improved fuzzy set is used to enhance the global contrast and the Laplace operator is used to enhance the details of the medical images. Experiments and simulation results show that the proposed method is superior to existing methods of image noise removal, improves the contrast of the image significantly, and obtains a better visual effect.

Contrast enhancement of medical images using fuzzy set theory and nonsubsampled shearlet transform

“…On the other hand, the objective analysis involve the comparison of different evaluation indicators, including the information entropy, peak signal‐to‐noise ratio (PSNR), root mean square error (RMSE) and the processing time (Time). Finally, we compare the proposed method with the contrast algorithms, including contrast enhancement using brightness preserving bi‐histogram equalization (HE), adaptive multiscale retinex for image contrast enhancement (MSR), a medical image enhancement method using adaptive thresholding in NSCT domain combined unsharp masking (NSCT‐UM) and method of improved fuzzy contrast combined adaptive threshold in NSCT for medical image enhancement (NSCT‐FU) …”

“…Finally, we compare the proposed method with the contrast algorithms, including contrast enhancement using brightness preserving bi-histogram equalization (HE), 23 adaptive multiscale retinex for image contrast enhancement (MSR), 24 a medical image enhancement method using adaptive thresholding in NSCT domain combined unsharp masking (NSCT-UM) 25 and method of improved fuzzy contrast combined adaptive threshold in NSCT for medical image enhancement (NSCT-FU). 22 Figures 1-3 illustrate the enhanced effect of the three group images. In Figure 1, the obtained image using the HE algorithm is brighter, however the information of the edge details are unclear; the MSR algorithm excessive increases the brightness of the image, and the detail information appears distorted; Although the enhanced brightness of the obtained image using the NSCT-UM algorithm is moderate, the details and edge information are not clear; moreover, the detail information of NSCT-FU algorithm is also unclear.…”

“…Reshmalakshmi and Sasikumar used a logarithm‐type membership function to address the problem associated with some lower gray values being forcibly set to zero in Pal algorithm and used tangent and cosine functions as nonlinear enhancement operators to improve the clarity of the image. Zhou et al proposed a novel fuzzy contrast method to address the limitations of the algorithm proposed by Li Jiuxian; this method was combined with nonsubsampled contourlet transform to perform image processing and achieved better processing results; however, it was computationally heavy. At present, removal of noises, enhancement image clarity and detailed information are important issues that must be addressed.…”

Remote Sensing Image Enhancement Based on Non-Local Means Filter in NSCT Domain

“…The NSCT transform has many merits such as time-frequency locality, multi-resolution, multi-direction, and anisotropy, which can sparsely represent the image. The NSCT has since been widely applied in image fusion and image enhancement [23,24]. In this paper, a novel remote sensing enhancement approach based on a non-local means filter in NSCT domain is proposed.…”

Adaptive Smoothness Constraint Image Multilevel Fuzzy Enhancement Algorithm

“…Image segmentation can extract the target of interest and remove the background of non-interest. Most of the energy functions of interest are non-convex and have multiple minimum values, resulting in most methods finding only approximate solutions (Ramos Gandolfi et al 2018;Sanchez Camacho & Martinez Morales 2017;Wang et al 2018;Zhou et al 2017). Therefore, the minimization process is often difficult.…”