Research on Realization of Medical Image Restoration Based on Blind Equalization Algorithm

2020 ◽  
Vol 10 (4) ◽  
pp. 809-813
Author(s):  
Ting Han ◽  
Ruo-Han Zhao ◽  
Mo Dong
Keyword(s):  
Image Restoration ◽  
Medical Image ◽  
Medical Images ◽  
Blind Equalization ◽  
Diagnostic Errors ◽  
Degradation Process ◽  
Restoration Algorithm ◽  
Equalization Algorithm ◽  
Improvement Effect ◽  
Blind Restoration

In order to study the realization of medical image restoration, this study mainly adopts blind equalization algorithm to analyze medical images, and observes the improvement effect of blind equalization technology on medical images. In the process of medical image formation, it is unavoidable to be affected by point spread function, which leads to image degradation and brings great difficulties to diagnosis, and the results of degradation are often unpredictable. The results show that the blind restoration algorithm can restore the image when the degradation process of the medical image is uncertain, which makes the medical image clearer and more accurate, brings great convenience to the diagnosis, and also reduces the diagnostic errors caused by the unclear image.

Application of Constraint CMA Blind Equalization Algorithm in the Medical Image Restoration

2012 ◽  
Vol 263-266 ◽  
pp. 2109-2112
Author(s):  
Jin Zhang ◽  
Ya Jie Mao ◽  
Li Yi Zhang ◽  
Yun Shan Sun
Keyword(s):  
Image Restoration ◽  
Cost Function ◽  
Medical Image ◽  
Signal To Noise Ratio ◽  
Blind Equalization ◽  
Optimal Solution ◽  
The Novel ◽  
Constant Modulus ◽  
Signal To Noise ◽  
Equalization Algorithm

A constraint constant module blind equalization algorithm for medical image based on dimension reduction was proposed. The constant modulus cost function applied to medical image was founded. In order to improve the effect of image restoration, a constraint item was introduced to restrict cost function, and it guarantees that the algorithm converge the optimal solution. Compared to the traditional methods, the novel algorithm improves peak signal to noise ratio and restoration effects. Computer simulations demonstrate the effectiveness of the algorithm.

scholarly journals Neural Network Blind Equalization Algorithm Applied in Medical CT Image Restoration

2013 ◽  
Vol 2013 ◽  
pp. 1-10 ◽  
Author(s):  
Yunshan Sun ◽  
Liyi Zhang ◽  
Jin Zhang ◽  
Lijuan Shi
Keyword(s):  
Neural Network ◽  
Image Restoration ◽  
Blind Equalization ◽  
Ct Image ◽  
Original Image ◽  
Equalization Algorithm ◽  
Convergence Performance ◽  
And Performance ◽  
Blind Image ◽  
Method Analysis

A new algorithm for iterative blind image restoration is presented in this paper. The method extends blind equalization found in the signal case to the image. A neural network blind equalization algorithm is derived and used in conjunction with Zigzag coding to restore the original image. As a result, the effect of PSF can be removed by using the proposed algorithm, which contributes to eliminate intersymbol interference (ISI). In order to obtain the estimation of the original image, what is proposed in this method is to optimize constant modulus blind equalization cost function applied to grayscale CT image by using conjugate gradient method. Analysis of convergence performance of the algorithm verifies the feasibility of this method theoretically; meanwhile, simulation results and performance evaluations of recent image quality metrics are provided to assess the effectiveness of the proposed method.

scholarly journals Noise Estimation using Kalman Filter in Image Restoration

2019 ◽  
Vol 8 (6S2) ◽  
pp. 888-891
Keyword(s):  
Image Processing ◽  
Kalman Filter ◽  
Image Restoration ◽  
Medical Image ◽  
Blind Deconvolution ◽  
Medical Images ◽  
Medical Image Processing ◽  
Noise Removal ◽  
Original Image ◽  
Degraded Image

Medical image processing plays a vital role in medical sciences from the past decades. Medical image processing becomes simple and useful with the advancement of image processing techniques. Medical images are used to observe the information related to inside the organs of human body. For better diagnoses and analysis of disease the image should be clear, noise free and more informative also. Usually medical images are corrupted by different noises in image acquisition and transmission process. The basic challenge in medical image processing is noise removal without losing diagnostic information. Image restoration is the one of the technique to recover the original image from the degraded image. In this paper, we are proposing a kalman filter to estimate the noise function from the degraded image and to reconstruct the original image. Here we are taking into account that the medical image was corrupted by the gaussian, speckle and salt & pepper noise. The simulation result infers that the proposed blind deconvolution method can be able to suppress the noise well and also preserve edge information without losing diagnostic data.

scholarly journals “A Novel Medical Image Blind Equalization Algorithm”

2012 ◽  
Vol 1 ◽  
pp. 371-376
Author(s):  
Yanqin Li ◽  
Liyi Zhang ◽  
Yunshan Sun
Keyword(s):  
Medical Image ◽  
Blind Equalization ◽  
Equalization Algorithm

scholarly journals Unpaired medical image colorization using generative adversarial network

2021 ◽  
Author(s):  
Yihuai Liang ◽  
Dongho Lee ◽  
Yan Li ◽  
Byeong-Seok Shin
Keyword(s):  
Loss Function ◽  
Medical Image ◽  
Color Image ◽  
Medical Images ◽  
Diagnostic Errors ◽  
Training Image ◽  
Input Image ◽  
Generative Adversarial Network ◽  
Adversarial Network

AbstractWe consider medical image transformation problems where a grayscale image is transformed into a color image. The colorized medical image should have the same features as the input image because extra synthesized features can increase the possibility of diagnostic errors. In this paper, to secure colorized medical images and improve the quality of synthesized images, as well as to leverage unpaired training image data, a colorization network is proposed based on the cycle generative adversarial network (CycleGAN) model, combining a perceptual loss function and a total variation (TV) loss function. Visual comparisons and experimental indicators from the NRMSE, PSNR, and SSIM metrics are used to evaluate the performance of the proposed method. The experimental results show that GAN-based style conversion can be applied to colorization of medical images. As well, the introduction of perceptual loss and TV loss can improve the quality of images produced as a result of colorization better than the result generated by only using the CycleGAN model.

Sign in / Sign up

Export Citation Format

Share Document