De-noising Method Research Articles

Research on motion impedance cardiography de-noising method based on two-step spectral ensemble empirical mode decomposition and canonical correlation analysis

Impedance cardiography (ICG) is essential in evaluating cardiac function in patients with cardiovascular diseases. Aiming at the problem that the measurement of ICG signal is easily disturbed by motion artifacts, this paper introduces a de-noising method based on two-step spectral ensemble empirical mode decomposition (EEMD) and canonical correlation analysis (CCA). Firstly, the first spectral EEMD-CCA was performed between ICG and motion signals, and electrocardiogram (ECG) and motion signals, respectively. The component with the strongest correlation coefficient was set to zero to suppress the main motion artifacts. Secondly, the obtained ECG and ICG signals were subjected to a second spectral EEMD-CCA for further denoising. Lastly, the ICG signal is reconstructed using these share components. The experiment was tested on 30 subjects, and the results showed that the quality of the ICG signal is greatly improved after using the proposed denoising method, which could support the subsequent diagnosis and analysis of cardiovascular diseases.

Enhanced Wavelet-Based Medical Image Denoising with Bayesian-Optimized Bilateral Filtering

Medical image denoising is essential for improving the clarity and accuracy of diagnostic images. In this paper, we present an enhanced wavelet-based method for medical image denoising, aiming to effectively remove noise while preserving critical image details. After applying wavelet denoising, a bilateral filter is utilized as a post-processing step to further enhance image quality by reducing noise while maintaining edge sharpness. The bilateral filter’s effectiveness heavily depends on its parameters, which must be carefully optimized. To achieve this, we employ Bayesian optimization, a powerful technique that efficiently identifies the optimal filter parameters, ensuring the best balance between noise reduction and detail preservation. The experimental results demonstrate a significant improvement in image denoising performance, validating the effectiveness of our approach.

Self-Supervised Learning for Generic Raman Spectrum Denoising.

Raman and surface-enhanced Raman scattering (SERS) spectroscopy are highly specific and sensitive optical modalities that have been extensively investigated in diverse applications. Noise reduction is demanding in the preprocessing procedure, especially for weak Raman/SERS spectra. Existing denoising methods require manual optimization of parameters, which is time-consuming and laborious and cannot always achieve satisfactory performance. Deep learning has been increasingly applied in Raman/SERS spectral denoising but usually requires massive training data, where the true labels may not exist. Aiming at these challenges, this work presents a generic Raman spectrum denoising algorithm with self-supervised learning for accurate, rapid, and robust noise reduction. A specialized network based on U-Net is established, which first extracts high-level features and then restores key peak profiles of the spectra. A subsampling strategy is proposed to refine the raw Raman spectrum and avoid the underlying biased interference. The effectiveness of the proposed approach has been validated by a broad range of spectral data, exhibiting its strong generalization ability. In the context of photosafe detection of deep-seated tumors, our method achieved signal-to-noise ratio enhancement by over 400%, which resulted in a significant increase in the limit of detection thickness from 10 to 18 cm. Our approach demonstrates superior denoising performance compared to the state-of-the-art denoising methods. The occlusion method further showed that the proposed algorithm automatically focuses on characterized peaks, enhancing the interpretability of our approach explicitly in Raman and SERS spectroscopy.

An adaptive parameter-free seismic data denoising approach by combining general cross-validation thresholding and pixel connectivity in synchrosqueezed domain

High signal-to-noise ratio (SNR) seismic waveform data are conductive to various studies in seismology. Seismic denoising aims to enhance SNR by eliminating additive noise through signal processing while preserving important features of the seismic signal. Conventional parametric seismic denoising methods often require selecting appropriate parameters to achieve optimal results, which may be limiting when dealing with various types and scales of seismic data. Here, we develop an adaptive parameter-free denoising method by combining general cross-validation (GCV) thresholding and pixel connectivity in synchrosqueezed (SS) domain. In this denoising framework, the synchrosqueezed continuous wavelet transform (SS-CWT) is first applied to obtain a high-resolution time–frequency representation. Then, the GCV approach, which allows for choosing the (nearly) optimal threshold without relying on any prior knowledge about the noise level, is employed to attenuate most of the low-energy noise. After that, the relatively isolated high-energy residual noise remaining in the SS-CWT spectrum is removed using pixel connectivity thresholding. Finally, the inverse SS-CWT is applied to the thresholded spectrum to obtain the denoised seismic record. As the thresholds for GCV and pixel connectivity are derived from the spectrum characteristics of the data being analyzed, the proposed denoising approach is highly adaptive and parameter-free. We demonstrate the effectiveness and versatility of the proposed denoising framework using synthetic data and real seismic data from diverse monitoring scenarios, including land, ocean, and emerging distributed acoustic sensing (DAS). The results indicate that the method is a stable and efficient tool for seismic data denoising.Graphical

A dual encoder LDCT image denoising model based on cross-scale skip connections

LDCT image denoising is crucial in medical imaging as it aims to minimize patient radiation exposure while maintaining diagnostic image quality. However, current convolutional neural network-based denoising methods struggle to incorporate global contexts, often focusing solely on local features. This limitation poses a significant challenge. To address this, a dual encoder denoising model is introduced that utilizes the Transformer model’s proficiency in capturing long-range dependencies and global context. This model integrates the Transformer branch and the convolutional branch in the encoder. By concatenating the features of these two different branches, the model can capture both global and local image features, substantially enhancing denoising efficacy. A cross-scale skip connection mechanism is introduced to integrate the encoder’ s low-level features with the decoder’ s high-level features, enriching contextual information and preserving image details. In addition, to meet the requirements of multi-scale feature fusion, the decoder is equipped with different multi-scale convolution modules to optimize feature processing. The number of layers in these modules gradually decreases as the depth of the decoder increases. In order to enhance the discriminative ability of the model, a multi-scale discriminator is also introduced, which effectively improves the recognition ability of the image by extracting features from four different scales. Consequently, our approach demonstrates remarkable performance in reducing noise and improving LDCT image quality, as evidenced by the substantial improvements in PSNR (17.75%) and SSIM (7.31%) values.

Lightweight Infrared Image Denoising Method Based on Adversarial Transfer Learning.

A lightweight infrared image denoising method based on adversarial transfer learning is proposed. The method adopts a generative adversarial network (GAN) framework and optimizes the model through a phased transfer learning strategy. In the initial stage, the generator is pre-trained using a large-scale grayscale visible light image dataset. Subsequently, the generator is fine-tuned on an infrared image dataset using feature transfer techniques. This phased transfer strategy helps address the problem of insufficient sample quantity and variety in infrared images. Through the adversarial process of the GAN, the generator is continuously optimized to enhance its feature extraction capabilities in environments with limited data. Moreover, the generator structure incorporates structural reparameterization technology, edge convolution modules, and progressive multi-scale attention block (PMAB), significantly improving the model's ability to recognize edge and texture features. During the inference stage, structural reparameterization further optimizes the network architecture, significantly reducing model parameters and complexity and thereby improving denoising efficiency. The experimental results of public and real-world datasets demonstrate that this method effectively removes additive white Gaussian noise from infrared images, showing outstanding denoising performance.

Quantitative assessment of kidney split function and mean transit time in healthy patients using dynamic 18F-FDG PET/MRI studies with denoising and deconvolution methods making use of Legendre polynomials

PurposeOur objective was to assess a deconvolution and denoising technique based on Legendre polynomials compared to matrix deconvolution on dynamic 18F-FDG renography of healthy patients.MethodThe study was carried out and compared to the data of 24 healthy patients from a published study who underwent examinations with 99mTc-MAG3 planar scintigraphy and 18F-FDG PET/MRI. Due to corruption issues in some data used in the published article, post-publication measurements were provided. We have been warned that post-publication data were treated differently. The smoothing method switched from Bezier to Savitzky–Golay and the deconvolution from matrix-based (with Tikhonov Regularization) to Richardson–Lucy. A comparison of the split function and mean transit times of the published and post-publication data against our method based on Legendre polynomials was performed.ResultsFor split function, we only observed a good agreement between the processing methods for the 99mTc-MAG3 and the post-published data. No correlation was found between the split functions obtained on the 99mTc-MAG3 and the 18F-FDG, contrary to the published study. However, all calculated split function values for 18F-FDG and 99mTc-MAG3 were within the established normal range. For the mean transit time, the correlation was moderate with published data and very good with the post-publication measurements for both 99mTc-MAG3 and 18F-FDG. Bias of the Bland–Altman analysis of the mean transit times for 99mTc-MAG3 versus 18F-FDG was 1.1 min (SD 1.7 min) for the published data, − 0.11 min (SD 1.9 min) for the post-publication results and .05 min (SD 1.9 min) for our method.ConclusionsThe processing methods used in the original publication and in the post-publication work were quite complex and required adaptation of the fitting parameters for each individual and each type of examination. Our method did not require any specific adjustment; the same unmodified and fully automated algorithm was successfully applied to all data.

A new frequency domain denoising method for coal mine transient electromagnetic measuring data

Abstract Due to limitation of space in mine tunnel, only a 2m × 2m rectangle coil can be employed to collect the electromagnetic signals for the mine transient electromagnetic analysis. Hence, a small emission magnetic moment and weak detection signal strength will increase the electromagnetic analysis difficulty. Moreover, the transient electromagnetic response signal in mines exhibits exponential decay over time, with late-stage amplitudes being notably small, which makes these signals susceptible to noise interference. As a result, it is necessary to study effective noise removal methods to enhance the signal-to-noise ratio of the late-stage electromagnetic data. Addressing this challenge task, this study proposes a new method for frequency domain denoising of transient electromagnetic data. This new method utilizes the Fourier Transform to convert the original transient electromagnetic data from the time domain to the frequency domain, and then, the noise is identified and removed through the frequency characters. Lastly, the processed frequency domain information is transformed to the time domain by the Fourier Inverse Transform to restore the time domain signals. The effect of this frequency domain denoising method is demonstrated through numerical simulations and underground coal mine field data to show significant noise reduction performance on the abnormality detection in the underground coal mine.

A Deep-learning-based Auto Encoder-Decoder Model for Denoising Electrocardiogram Signals

Learning-based denoising techniques have become superior to the traditional assumption-based denoising methods in this modern era. Also, with the advancement of wearable technologies and remote electrocardiogram (ECG) monitoring systems, the requirement for optimal storage has increased due to the limited availability of hardware resources. Therefore, denoising and compression both are essential at the preprocessing stage of the ECG signal. Deep learning-based denoising auto encoder-decoder (DAED) models guarantee cutting-edge performance for these tasks. This article presents a lightweight, adaptive, hybrid Convolutional Neural Network-Gated Recurrent Unit (CNN-GRU) based DAED model that achieves a signal compression ratio of 64 with high signal-to-noise ratio improvement for the elimination of ECG noises. The novelty of this work lies in the customization of the CNN layers and utilization of the advantages of the GRU layer in a proper channel for compression and denoising ECG signals. The comparative study with other complex deep learning-based DAED arrangements and state-of-the-art denoising techniques shows the proposed model has simplicity in construction and an improved signal-to-noise ratio with minimum mean square error.

Learnable dual attention fusion network for borehole distributed acoustic sensing systems data reconstruction

As the demand for nonrenewable oil and gas resources has increased, distributed acoustic sensing systems (DAS) have been widely used in the acquisition of vertical seismic profiles. Complicated subsurface conditions produce many types of noise with strong energy. The effective reflection and refraction signals are absorbed by the inelastic medium during the transmission process, resulting in significant energy loss and aliased frequency characteristics. However, satisfactory processing results and quality cannot be achieved through conventional denoising methods. In recent years, the rapid development of deep-learning methods with attention mechanisms has attracted significant attention. Noise reduction and signal reconstruction technologies with multiple attention mechanisms within the framework of joint-domain features have become important development directions in DAS data processing. An attention mechanism can help the network ignore useless information and pay attention to useful information in the same way that humans can. In this study, we discuss a novel learnable dual attention fusion network that combines local and patch-based nonlocal attention mechanisms based on ResBlock modules, making the extraction process of the network learnable and selective. In addition, the novel network can focus on local and global details. We also use a residual learning strategy to simplify the training process and gradually establish the best mapping based on the L2 loss function. All experimental results of the simulation and actual records show that our novel network has better denoising and effective signal restoration abilities. Moreover, it can recover the up-going and down-going wavefields and attenuate different types of noise with less effective energy loss.

SPECT-MPI iterative denoising during the reconstruction process using a two-phase learned convolutional neural network

PurposeThe problem of image denoising in single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) is a fundamental challenge. Although various image processing techniques have been presented, they may degrade the contrast of denoised images. The proposed idea in this study is to use a deep neural network as the denoising procedure during the iterative reconstruction process rather than the post-reconstruction phase. This method could decrease the background coefficient of variation (COV_bkg) of the final reconstructed image, which represents the amount of random noise, while improving the contrast-to-noise ratio (CNR).MethodsIn this study, a generative adversarial network is used, where its generator is trained by a two-phase approach. In the first phase, the network is trained by a confined image region around the heart in transverse view. The second phase improves the network’s generalization by tuning the network weights with the full image size as the input. The network was trained and tested by a dataset of 247 patients who underwent two immediate serially high- and low-noise SPECT-MPI.ResultsQuantitative results show that compared to post-reconstruction low pass filtering and post-reconstruction deep denoising methods, our proposed method can decline the COV_bkg of the images by up to 10.28% and 12.52% and enhance the CNR by up to 54.54% and 45.82%, respectively.ConclusionThe iterative deep denoising method outperforms 2D low-pass Gaussian filtering with an 8.4-mm FWHM and post-reconstruction deep denoising approaches.

Investigating deep learning strategies for fast denoising of 5D cardiac photon-counting micro-CT images


Photon-counting detectors (PCDs) for CT imaging use energy thresholds to simultaneously acquire projections at multiple energies, making them suitable for spectral imaging and material decomposition. Unfortunately, setting multiple energy thresholds results in noisy analytical reconstructions due to low photon counts in high-energy bins. Iterative reconstruction provides high quality photon-counting CT (PCCT) images but requires enormous computation time for 5D (3D + energy + time) in vivo cardiac imaging. 

Approach. 
We recently introduced UnetU, a deep learning (DL) approach that accurately denoises axial slices from 4D (3D + energy) PCCT reconstructions at various acquisition settings. In this study, we explore UnetU configurations for 5D cardiac PCCT denoising, focusing on singular value decomposition (SVD) modifications along the energy and time dimensions and alternate network architectures such as 3D U-net, FastDVDNet, and Swin Transformer UNet. We compare our networks to multi-energy non-local means (ME NLM), an established PCCT denoising algorithm. 

Main results. 
Our evaluation, using real mouse data and the digital MOBY phantom, revealed that all DL methods were more than 16 times faster than iterative reconstruction. DL denoising with SVD along the energy dimension was most effective, consistently providing low root mean square error and spatio-temporal reduced reference entropic difference, alongside strong qualitative agreement with iterative reconstruction. This superiority was attributed to lower effective rank along the energy dimension than the time dimension in 5D cardiac PCCT reconstructions. ME NLM sometimes outperformed DL with time SVD or time and energy SVD, but lagged behind iterative reconstruction and DL with energy SVD. Among alternate DL architectures with energy SVD, none consistently outperformed UnetU Energy (2D). 

Significance. 
Our study establishes UnetU Energy as an accurate and efficient method for 5D cardiac PCCT denoising, offering a 32-fold speed increase from iterative reconstruction. This advancement sets a new benchmark for DL applications in cardiovascular imaging.

A low-dose CT image denoising method based on state space model

Abstract Low-dose CT medical imaging techniques introduce noise while reducing radiation risks, necessitating denoising processing. However, existing mainstream denoising methods face a difficult trade-off between preserving image detail information and accurately removing noise. To address this issue, we propose a low-dose CT image denoising method based on a state space model. Firstly, a dynamic edge information enhancement module is introduced to automatically extract edge information from images using a learnable LoG operator and fuse it into feature layers at different scales to suppress edge information loss caused by denoising processes. Secondly, a U-net encoder based on state space estimation is designed to dynamically model spatial relationships between pixels through neighborhood filtering, enabling consideration of local differences in pixel values during denoising and better preservation of edges and textures. Compared to existing denoising methods, our approach achieves stable noise removal in low-dose CT images while preserving the original texture structure.

SpotGF: Denoising spatially resolved transcriptomics data using an optimal transport-based gene filtering algorithm

Spatially resolved transcriptomics (SRT) combines gene expression profiles with the physical locations of cells in their native states but suffers from unpredictable spatial noise due to cell damage during cryosectioning and exposure to reagents for staining and mRNA release. To address this noise, we developed SpotGF, an algorithm for denoising SRT data using optimal transport-based gene filtering. SpotGF quantifies diffusion patterns numerically, distinguishing widespread expression genes from aggregated expression genes and filtering out the former as noise. Unlike conventional denoising methods, SpotGF preserves raw sequencing data, thereby avoiding false positives that can arise from imputation. Additionally, SpotGF demonstrates superior performance in cell clustering, identifying potential marker genes, and annotating cell types. Overall, SpotGF has the potential to become a crucial preprocessing step in the downstream analysis of SRT data. The SpotGF software is freely available at GitHub. A record of this paper's transparent peer review process is included in the supplemental information.

STORM image denoising and information extraction.

Stochastic optical reconstruction microscopy (STORM) is extensively utilized in the fields of cell and molecular biology as a super-resolution imaging technique for visualizing cells and molecules. Nonetheless, the imaging process of STORM is frequently susceptible to noise, which can significantly impact the subsequent image analysis. Moreover, there is currently a lack of a comprehensive automated processing approach for analyzing protein aggregation states from a large number of STORM images. This paper initially applies our previously proposed denoising algorithm, UNet-Att, in STORM image denoising. This algorithm was constructed based on attention mechanism and multi-scale features, showcasing a remarkably efficient performance in denoising. Subsequently, we propose a collection of automated image processing algorithms for the ultimate feature extractions and data analyses of the STORM images. The information extraction workflow effectively integrates automated methods of image denoising, objective image segmentation and binarization, and object information extraction, and a novel image information clustering algorithm specifically developed for the morphological analysis of the objects in the STORM images. This automated workflow significantly improves the efficiency of the effective data analysis for large-scale original STORM images.

Enhancing bone scan image quality: an improved self-supervised denoising approach.

Bone scans play an important role in skeletal lesion assessment, but gamma cameras exhibit challenges with low sensitivity and high noise levels. Deep learning (DL) has emerged as a promising solution to enhance image quality without increasing radiation exposure or scan time. However, existing self-supervised denoising methods, such as Noise2Noise (N2N), may introduce deviations from the clinical standard in bone scans. This study proposes an improved self-supervised denoising technique to minimize discrepancies between DL-based denoising and full scan images. 
Retrospective analysis of 351 whole-body bone scan data sets was conducted. In this study, we used N2N and Noise2FullCount (N2F) denoising models, along with an interpolated version of N2N (iN2N). Denoising networks were separately trained for each reduced scan time from 5 to 50%, and also trained for mixed training datasets, which include all shortened scans. We performed quantitative analysis and clinical evaluation by nuclear medicine experts.
The denoising networks effectively generated images resembling full scans, with N2F revealing distinctive patterns for different scan times, N2N producing smooth textures with slight blurring, and iN2N closely mirroring full scan patterns. Quantitative analysis showed that denoising improved with longer input times and mixed count training outperformed fixed count training. Traditional denoising methods lagged behind DL-based denoising. N2N demonstrated limitations in long-scan images. Clinical evaluation favored N2N and iN2N in resolution, noise, blurriness, and findings, showcasing their potential for enhanced diagnostic performance in quarter-time scans.
The improved self-supervised denoising technique presented in this study offers a viable solution to enhance bone scan image quality, minimizing deviations from clinical standards. The method's effectiveness was demonstrated quantitatively and clinically, showing promise for quarter-time scans without compromising diagnostic performance. This approach holds potential for improving bone scan interpretations, aiding in more accurate clinical diagnoses.

A deep learning method for simultaneous denoising and missing wedge reconstruction in cryogenic electron tomography

Cryogenic electron tomography is a technique for imaging biological samples in 3D. A microscope collects a series of 2D projections of the sample, and the goal is to reconstruct the 3D density of the sample called the tomogram. Reconstruction is difficult as the 2D projections are noisy and can not be recorded from all directions, resulting in a missing wedge of information. Tomograms conventionally reconstructed with filtered back-projection suffer from noise and strong artefacts due to the missing wedge. Here, we propose a deep-learning approach for simultaneous denoising and missing wedge reconstruction called DeepDeWedge. The algorithm requires no ground truth data and is based on fitting a neural network to the 2D projections using a self-supervised loss. DeepDeWedge is simpler than current state-of-the-art approaches for denoising and missing wedge reconstruction, performs competitively and produces more denoised tomograms with higher overall contrast.

Predictive performance of denoising algorithms in S&P 500 and Bitcoin returns

This paper aims to investigate the effectiveness of both the Hankel matrix and the Wavelet denoise methods to address the issue of denoising volatility in datasets, specifically squared returns, and to enhance the accuracy of post-sample forecasting. When converting data from levels to volatility, noise levels are amplified, and the forecasting models suffer from structural bias, leading to reduced accuracy gains. The main challenge in denoising operations is preserving systemic impulses while extracting sporadic and unpredictable components. While conventional denoising algorithms struggle to distinguish systemic patterns from noise, the Hankel matrix approach surpasses them in performance, resulting in improved predictive accuracy. Additionally, this paper explores the Wavelet denoise method, which is found to be less effective than the Hankel matrix approach for GARCH models. The empirical work showcases the denoising process and the accuracy improvements achieved in various datasets for GARCH models. By implementing the Hankel matrix approach, simulations reveal a notable accuracy gain of over 10%.

A Review of Image Denoising Using Fuzzy and Wiener Filters in the Wavelet Domain

This paper focuses on image denoising using fuzzy wavelet domain transforms, reviewing recent advancements in this area. Wavelet transforms have become a powerful tool in image denoising, with one of the most widely used techniques involving thresholding wavelet coefficients. The paper proposes a hybrid denoising method that combines the wavelet transform, median filtering, and nonlinear diffusion. Additionally, a novel fuzzy filter is introduced to reduce additive noise in digital color images. Two distinct image denoising techniques are discussed: the first employs an Asymmetrical Triangular Moving Average Filter (TMAV) with a HAAR wavelet transform, while the second utilizes an Asymmetrical Triangular Median Filter (TMED) with the HAAR wavelet transform.

Synthetic minority oversampling and iterative fluorescence-suppression integrated algorithm for Raman spectrum pesticide detection system

Raman spectrum preprocessing method for automatic denoising and suppression of the fluorescent background. In this method, noise is reduced using wavelet transform, and a modified polynomial curve fitting method is implemented such that an algorithm can independently identify the optimal curve parameters for fluorescent background suppression. To address the problem of imbalanced datasets, the present study employed a synthetic minority oversampling technique to increase the volume of data in minority classes. This technique enables the prediction of pesticides that are otherwise difficult to detect, and the prediction accuracy is comparable to that of detection with large data volumes. The proposed convolutional neural network model was verified to accurately identify the type of single pesticides and composition of mixed pesticides. The prediction accuracy for mixed pesticides reached 99.1%.