Noise ECG generation method based on generative adversarial network

Huang, Shaobin; Wang, Peng; Li, Rongsheng

doi:10.1016/j.bspc.2022.104444

Cited by 6 publications

(4 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In network design, popular methods are convolution neural network [137], encoder-decoder structure with residual learning [60], and generative adversarial network [153]. Newly developed networks mostly focused on attention mechanism.…”

Section: Ultrasound Denoising Deep Learningmentioning

confidence: 99%

“…Khor et al [53] utilized wavelet representation to overcome boundary blurring for deep learning method, in which modules of wavelet band normalization and wavelet residual channel attention were designed in a targeted manner to learn band features effectively. Recently, cycle-consistent generative adversarial network for medical image synthesis and analysis [154], [155] has been explored to transfer the noisy ultrasound images to the noise-free images [153] by selecting clinical images as noisy images and the high-quality images that were despeckled with Gabor-based AD as the noise-free images for training CycleGAN. However, there is no widely accepted denoising methods for high-quality image generation, the unavailability of noise-free clinical ultrasound images poses a significant obstacle to CycleGAN's training.…”

Section: Ultrasound Denoising Deep Learningmentioning

confidence: 99%

See 1 more Smart Citation

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Liu,

Dong,

Qin

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Section: Ultrasound Denoising Deep Learningmentioning

confidence: 99%

Section: Ultrasound Denoising Deep Learningmentioning

confidence: 99%

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Liu,

Dong,

Qin

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…This model uses noise images and noise-free images as input, allowing outstanding results in noise reduction while preserving details. However, the study faces some challenges such as the possibility of instability in training and difficulty in dealing with severe noise, which may affect the accuracy of the results in some cases [9]. Finally, in 2023, an advanced framework for ultrasound image enhancement with an improved hybrid search algorithm and a new kinematic clustering processing chain is presented.…”

Section: Introductionmentioning

confidence: 99%

Anisotropic Diffusion Method for Speckle Noise Reduction in Breast Ultrasound Images

2024

IJIES

View full text Add to dashboard Cite

Breast ultrasound is an important technology for detecting breast lesions, but it faces a challenge in the form of speckle noise that negatively affects the quality of images. Effective methods are needed to eliminate this noise without compromising the image's fine edges and important features. In this work, we present a cutting-edge methodology based on a deep understanding of the dynamics of breast ultrasound images and the challenges of speckle noise. The method uses two separate stages of processing with two nonlinear filters. The first filter, the anisotropic diffusion filter, smooths out edges and boosts image contrast by lowering noise while keeping the tissue's structure. In the second stage, the SRAD filter is applied to remove residual noise and refine the image, increasing its clarity and improving the ability to visualize subtle lesions. This improved approach was evaluated using a comprehensive set of quantitative indices. The results confirmed the significant performance improvement provided, with the lowest MSE value of 0.2 and the highest PSNR of 59.3. Also, it reached the optimal value in the UQI and SSI, which indicates the robustness of the method in maintaining the quality of the structural image. The results confirm the value of the proposed approach and herald its promising potential for improving medical diagnostic results using breast ultrasound.

show abstract

“…Denoising is an intricate process that aims to remove noise from an image while maintaining its quality and intricate details. The primary classifications of noise in images include Impulse Noise (IN) [2][3] [4], Additive White Gaussian Noise (AWGN) [3] [4], and Speckle Noise [5][6] [7], and Speckle Noise. There are two types of impulse noise: Salt and Pepper Noise (SPN) [8] [9][10] [11] and Random Valued Impulse Noise (RVIN) [12] [13].…”

Section: Introductionmentioning

confidence: 99%

Enhancing Image Clarity with the Combined Use of REDNet and Attention Channel Module

Halim,

Putra Kusuma

2024

IJCDS

View full text Add to dashboard Cite

The primary aim of our study is to improve the efficacy of image denoising, specifically in situations when there is a limited availability of data, such as the BSD68 dataset. Insufficient data presents a challenge in achieving optimal outcomes due to the complexity involved in constructing models. In order to tackle this difficulty, we provide a method that incorporates Channel Attention, Batch Normalization, and Dropout approaches into the current REDNet framework. Our investigation indicates enhancements in performance parameters, such as PSNR (Peak Signal to Noise Ratio) and SSIM (Structural Similarity Index), across various levels of noise. With a noise level of 15, we obtained a Peak Signal-to-Noise Ratio (PSNR) of 34.9858 dB and a Structural Similarity Index (SSIM) of 0.9371. At a noise level of 25, our tests yielded a PSNR of 31.7886 decibels and an SSIM of 0.8876. In addition, at a noise level of 50, we achieved a Peak Signal-to-Noise Ratio (PSNR) of 27.9063 decibels and a Structural Similarity Index (SSIM) of 0.7754. The incorporation of Channel Attention, Batch Normalization, and Dropout has been demonstrated to be a crucial element in enhancing the efficacy of image denoising. The Channel Attention approach enables the model to choose and concentrate on crucial information inside the image, while Batch Normalization and Dropout techniques provide stability and mitigate overfitting issues throughout the training process. Our research highlights the effectiveness of these three strategies and emphasizes their integration as a novel way to address the constraints presented by the scarcity of data in image denoising jobs. This emphasizes the significant potential in creating dependable and effective image denoising methods when dealing with circumstances when there is a limited dataset.

show abstract

Noise ECG generation method based on generative adversarial network

Cited by 6 publications

References 26 publications

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Is denoising necessary for ultrasound image segmentation deep learning: review and benchmark

Anisotropic Diffusion Method for Speckle Noise Reduction in Breast Ultrasound Images

Enhancing Image Clarity with the Combined Use of REDNet and Attention Channel Module

Contact Info

Product

Resources

About