Artifact Removal Research Articles

A universal and effective variational method for destriping: application to light-sheet microscopy, FIB-SEM, and remote sensing images

Stripe artifacts are a common problem for various imaging techniques such as light-sheet fluorescence microscopy (LSFM), electron microscopy, and remote sensing. These artifacts are characterized by their elongated shapes, compromised image quality, and impede further analysis. To address the primary challenge of removing the stripe artifacts while preserving the object structures we present an improved variational method for stripe removal with intuitive parametrization. Comparison against previously published methods on images from LSFM, FIB-SEM, and remote sensing by visual inspection and quantitative metrics demonstrates the superior capability of the approach. Based on synthetic LSFM data obtained by simulation of physical light-propagation we enriched our analysis by the comparison of processed images to ground truth data and quantitatively confirmed that our method outperforms existing solutions in terms of improved removal of artifacts and retention of image structures. The open availability of our solution and the flexibility in handling variations in stripe orientation and thickness ensure its broad applicability across diverse imaging scenarios.

How does Independent Component Analysis Preprocessing Affect EEG Microstates?

Over recent years, electroencephalographic (EEG) microstates have been increasingly used to investigate, at a millisecond scale, the temporal dynamics of large-scale brain networks. By studying their topography and chronological sequence, microstates research has contributed to the understanding of the brain's functional organization at rest and its alteration in neurological or mental disorders. Artifact removal strategies, which differ from study to study, may alter microstates topographies and features, possibly reducing the generalizability and comparability of results across research groups. The aim of this work was therefore to test the reliability of the microstate extraction process and the stability of microstate features against different strategies of EEG data preprocessing with Independent Component Analysis (ICA) to remove artifacts embedded in the data. A normative resting state EEG dataset was used where subjects alternate eyes-open (EO) and eyes-closed (EC) periods. Four strategies were tested: (i) avoiding ICA preprocessing altogether, (ii) removing ocular artifacts only, (iii) removing all reliably identified physiological/non physiological artifacts, (iv) retaining only reliably identified brain ICs. Results show that skipping the removal of ocular artifacts affects the stability of microstate evaluation criteria, microstate topographies and greatly reduces the statistical power of EO/EC microstate features comparisons, however differences are not as prominent with more aggressive preprocessing. Provided a good-quality dataset is recorded, and ocular artifacts are removed, microstates topographies and features can capture brain-related physiological data and are robust to artifacts, independently of the level of preprocessing, paving the way to automatized microstate extraction pipelines.

Using artifact suppression OCT based on polarization multiplexing for tomographic imaging of LCD screens

Defect detection in the inner layers of liquid crystal display (LCD) panels is crucial for the quality control of displays. Optical coherence tomography (OCT), a nondestructive, high-resolution tomographic imaging technique, has been applied in the inspection of display panels. However, the artifacts that arise in imaging multilayer samples remain a challenge. In this study, we propose and validate a method for artifact removal in coherent imaging of multilayer refractive samples. These samples exhibit complex autocorrelation artifacts due to self-interference and multiple reflections. Two orthogonally polarized reference beams with fixed phase shifts, combined with the proposed algorithm, are employed to suppress the autocorrelation in the sample light path. To address the issue of mirror artifacts caused by real spectrum signals, the intensity ratio of the two orthogonally polarized reference beams is adjusted, allowing distinction between real signals and mirror artifacts, thus achieving full-range imaging. Experiments were conducted to measure 3D images of multilayer quartz glass sheets, inclined ceramic blocks, and LCD panels, validating the reliability of the proposed approach and demonstrating its advantages in display defect detection.

Dual-Modality Transformer with Time Series Imaging for Robust Epileptic Seizure Prediction

Automated EEG classification algorithms for seizures can facilitate the clinical diagnosis of epilepsy, enabling more expedient and precise classification. However, existing EEG signal preprocessing methods oriented towards artifact removal and signal enhancement have demonstrated suboptimal accuracy and robustness. In response to this challenge, we propose an Adaptive Dual-Modality Learning Model (ADML) for epileptic seizure prediction by combining time series imaging with Transformer-based architecture. Our approach effectively captures both temporal dependencies and spatial relationships in EEG signals through a specialized attention mechanism. Evaluated on the CHB-MIT and Bonn datasets, our method achieves 98.7% and 99.2% accuracy, respectively, significantly outperforming existing approaches. The model demonstrates strong generalization capability across datasets while maintaining computational efficiency. Cross-dataset validation confirms the robustness of our approach, with consistent performance above 96% accuracy. These results suggest that our dual-modality approach provides a reliable and practical solution for clinical epileptic seizure prediction.

Optimization of sparse-view CT reconstruction based on convolutional neural network.

Sparse-view CT shortens scan time and reduces radiation dose but results in severe streak artifacts due to insufficient sampling data. Deep learning methods can now suppress these artifacts and improve image quality in sparse-view CT reconstruction. The quality of sparse-view CT reconstructed images can still be improved. Additionally, the interpretability of deep learning-based optimization methods for these reconstruction images is lacking, and the role of different network layers in artifact removal requires further study. Moreover, the optimization capability of these methods for reconstruction images from various sparse views needs enhancement. This study aims to improve the network's optimization ability for sparse-view reconstructed images, enhance interpretability, and boost generalization by establishing multiple network structures and datasets. In this paper, we developed a sparse-view CT reconstruction images improvement network (SRII-Net) based on U-Net. We added a copy pathway in the network and designed a residual image output block to boost the network's performance. Multiple networks with different connectivity structures were established using SRII-Net to analyze the contribution of each layer to artifact removal, improving the network's interpretability. Additionally, we created multiple datasets with reconstructed images of various sampling views to train and test the proposed network, investigating how these datasets from different sampling views affect the network's generalization ability. The results show that the proposed method outperforms current networks, with significant improvements in metrics like PSNR and SSIM. Image optimization time is at the millisecond level. By comparing the performance of different network structures, we've identified the impact of various hierarchical structures. The image detail information learned by shallow layers and the high-level abstract feature information learned by deep layers play a crucial role in optimizing sparse-view CT reconstruction images. Training the network with multiple mixed datasets revealed that, under a certain amount of data, selecting the appropriate categories of sampling views and their corresponding samples can effectively enhance the network's optimization ability for reconstructing images with different sampling views. The network in this paper effectively suppresses artifacts in reconstructed images with different sparse views, improving generalization. We have also created diverse network structures and datasets to deepen the understanding of artifact removal in deep learning networks, offering insights for noise reduction and image enhancement in other imaging methods.

FLANet: A multiscale temporal convolution and spatial-spectral attention network for EEG artifact removal with adversarial training

Objective.Denoising artifacts, such as noise from muscle or cardiac activity, is a crucial and ubiquitous concern in neurophysiological signal processing, particularly for enhancing the signal-to-noise ratio in electroencephalograph (EEG) analysis. Novel methods based on deep learning demonstrate a notably prominent effect compared to traditional denoising approaches. However, those still suffer from certain limitations. Some methods often neglect the multi-domain characteristics of the artifact signal. Even among those that do consider these, there are deficiencies in terms of efficiency, effectiveness and computation cost.Approach.In this study, we propose a multiscale temporal convolution and spatial-spectral attention network with adversarial training for automatically filtering artifacts, named filter artifacts network (FLANet). The multiscale convolution module can extract sufficient temporal information and the spatial-spectral attention network can extract not only non-local similarity but also spectral dependencies. To make data denoising more efficient and accurate, we adopt adversarial training with novel loss functions to generate outputs that are closer to pure signals.Main results.The results show that the method proposed in this paper achieves great performance in artifact removal and valid information preservation on EEG signals contaminated by different types of artifacts. This approach enables a more optimal trade-off between denoising efficacy and computational overhead.Significance.The proposed artifact removal framework facilitates the implementation of an efficient denoising method, contributing to the advancement of neural analysis and neural engineering, and can be expected to be applied to clinical research and to realize novel human-computer interaction systems.

A Method of EEG Signal Feature Extraction Based on Hybrid DWT and EMD

A Method of EEG Signal Feature Extraction Based on Hybrid DWT and EMD

Generating synthetic CT images from unpaired head and neck CBCT images and validating the importance of detailed nasal cavity acquisition through simulations.

Computed tomography (CT) of the head and neck is crucial for diagnosing internal structures. The demand for substituting traditional CT with cone beam CT (CBCT) exists because of its cost-effectiveness and reduced radiation exposure. However, CBCT cannot accurately depict airway shapes owing to image noise. This study proposes a strategy utilizing a cycle-consistent generative adversarial network (cycleGAN) for denoising CBCT images with various loss functions and augmentation strategies, resulting in the generation of denoised synthetic CT (sCT) images. Furthermore, through a rule-based approach, we were able to automatically segment the upper airway in sCT images with high accuracy. Additionally, we conducted an analysis of the impact of finely segmented nasal cavities on airflow using computational fluid dynamics (CFD). We trained the cycleGAN model using various loss functions and compared the quality of the sCT images generated by each model. We improved the artifact removal performance by incorporating CT images with added Gaussian noise augmentation into the training dataset. We developed a rule-based automatic segmentation methodology using threshold and watershed algorithms to compare the accuracy of airway segmentation for noise-reduced sCT and original CBCT. Furthermore, we validated the significance of the nasal cavity by conducting CFD based on automatically segmented shapes obtained from sCT. The generated sCT images exhibited improved quality, with the mean absolute error decreasing from 161.60 to 100.54, peak signal-to-noise ratio increasing from 22.33 to 28.65, and structural similarity index map increasing from 0.617 to 0.865. Furthermore, by comparing the airway segmentation performances of CBCT and sCT using our proposed automatic rule-based algorithm, the Dice score improved from 0.849 to 0.960. Airway segmentation performance is closely associated with the accuracy of fluid dynamics simulations. Detailed airway segmentation is crucial for altering flow dynamics and contributes significantly to diagnostics. Our deep learning methodology enhances the image quality of CBCT to provide anatomical information to medical professionals and enables precise and accurate biomechanical analysis. This allows clinicians to obtain precise quantitative metrics and facilitates accurate assessment.

Abstract WP194: Deep-learning Based Artefact Removal From Relative Non-contrast Computed Tomography Maps To Identify Early Hypodensity Changes After Acute Ischemic Stroke

Abstract WP194: Deep-learning Based Artefact Removal From Relative Non-contrast Computed Tomography Maps To Identify Early Hypodensity Changes After Acute Ischemic Stroke

Blind Source Separation Using Time-Delayed Dynamic Mode Decomposition

Blind Source Separation (BSS) is a significant field of study in signal processing, with many applications in various fields such as audio processing, speech recognition, biomedical signal analysis, image processing and communication systems. Traditional methods, such as Independent Component Analysis (ICA), often rely on statistical independence assumptions, which may limit their performance in systems with significant temporal dynamics. This paper introduces an extension of the dynamic mode decomposition (DMD) approach by using time-delayed coordinates to implement BSS. Time-delay embedding enhances the capability of the method to handle complex, nonstationary signals by incorporating their temporal dependencies. We validate the approach through numerical experiments and applications, including audio signal separation, image separation and EEG artifact removal. The results demonstrate that modification achieves superior performance compared to conventional techniques, particularly in scenarios where sources exhibit dynamic coupling or non-stationary behavior.

Measuring the effects of motion corruption in fetal fMRI.

Irregular and unpredictable fetal movement is the most common cause of artifacts in in utero functional magnetic resonance imaging (fMRI), affecting analysis and limiting our understanding of early functional brain development. The accurate detection of corrupted functional connectivity (FC) resulting from motion artifacts or preprocessing, instead of neural activity, is a prerequisite for reliable and valid analysis of FC and early brain development. Approaches to address this problem in adult data are of limited utility in fetal fMRI. In this study, we evaluate a novel technique for robust computational assessment of motion artifacts, and the quantitative comparison of regression models for artifact removal in fetal FC analysis. It exploits the association between dynamic FC and non-stationarity of fetal movement, to detect residual noise. To validate our motion artifact detection technique in detail, we used a parametric generative model for neural events and fMRI blood oxygenation level-dependent (BOLD) signal. We conducted a systematic evaluation of 11 commonly used regression models in a sample of 70 fetuses with gestational age of 19-39 weeks. Results demonstrate that the proposed method has better accuracy in identifying corrupted FC compared to methods designed for adults. The technique, suggests that censoring, global signal regression and anatomical component-based regression models are the most effective models for compensating motion. The benchmarking technique, and the generative model for realistic fetal fMRI BOLD enables investigators conducting in utero fMRI analysis to effectively quantify the impact of fetal motion and evaluate alternative regression strategies for mitigating this impact. The code is publicly available at: https://github.com/cirmuw/fetalfMRIproc.

The Role of Deep Learning in Medical Image Inpainting: A Systematic Review

Image inpainting is a crucial technique in computer vision, particularly for reconstructing corrupted images. In medical imaging, it addresses issues from instrumental errors, artifacts, or human factors. The development of deep learning techniques has revolutionized image inpainting, allowing for the generation of high-level semantic information to ensure structural and textural consistency in restored images. This paper presents a comprehensive review of 53 studies on deep image inpainting in medical imaging, analyzing its evolution, impact, and limitations. The findings highlight the significance of deep image inpainting in artifact removal and enhancing the performance of multi-task approaches by localizing and inpainting regions of interest. Furthermore, the study identifies magnetic resonance imaging and computed tomography as the predominant modalities and highlights generative adversarial networks and U-Net as preferred architectures. Future research directions include the development of blind inpainting techniques, the exploration of techniques suitable for 3D/4D images, multiple artifacts, and multi-task applications, and the improvement of architectures.

Artifact removal of EEG data using wavelet total variation denoising and independent component analysis

Artifact removal of EEG data using wavelet total variation denoising and independent component analysis

DHCT-GAN: Improving EEG Signal Quality with a Dual-Branch Hybrid CNN-Transformer Network.

Electroencephalogram (EEG) signals are important bioelectrical signals widely used in brain activity studies, cognitive mechanism research, and the diagnosis and treatment of neurological disorders. However, EEG signals are often influenced by various physiological artifacts, which can significantly affect data analysis and diagnosis. Recently, deep learning-based EEG denoising methods have exhibited unique advantages over traditional methods. Most existing methods mainly focus on identifying the characteristics of clean EEG signals to facilitate artifact removal; however, the potential to integrate cross-disciplinary knowledge, such as insights from artifact research, remains an area that requires further exploration. In this study, we developed DHCT-GAN, a new EEG denoising model, using a dual-branch hybrid network architecture. This model independently learns features from both clean EEG signals and artifact signals, then fuses this information through an adaptive gating network to generate denoised EEG signals that accurately preserve EEG signal features while effectively removing artifacts. We evaluated DHCT-GAN's performance through waveform analysis, power spectral density (PSD) analysis, and six performance metrics. The results demonstrate that DHCT-GAN significantly outperforms recent state-of-the-art networks in removing various artifacts. Furthermore, ablation experiments revealed that the hybrid model surpasses single-branch models in artifact removal, underscoring the crucial role of artifact knowledge constraints in improving denoising effectiveness.

Removal of Motion Artifacts From the PPG Signal Using Attentive Generative Adversarial Networks With Dual Discriminator

Removal of Motion Artifacts From the PPG Signal Using Attentive Generative Adversarial Networks With Dual Discriminator

Transformative role of GANs in modern medical imaging: A review

Generative Adversarial Networks (GANs) have emerged as transformative tools in medical imaging, addressing critical challenges such as limited datasets, low image quality, and the need for enhanced diagnostic precision. By leveraging adversarial training, GANs generate highly realistic synthetic images, which are invaluable for data augmentation and improving the robustness of machine learning models. Applications of GANs span diverse areas, including super-resolution imaging to enhance low-quality scans, image-to-image translation for cross-modality data synthesis, and artifact removal to improve diagnostic reliability. GANs also play a pivotal role in simulating pathological scenarios, providing synthetic datasets for training and testing diagnostic algorithms, especially for rare or ethically sensitive conditions. Despite their potential, GANs face technical challenges such as dataset bias, computational demands, and instability during training, which can limit the generalizability of their outputs. Ethical concerns, including the misuse of synthetic data, the indistinguishability between real and synthetic images, and privacy risks, further complicate their application. Regulatory hurdles also pose barriers to clinical adoption, necessitating robust frameworks for validation and integration. Future research directions include the integration of multi-modal data, federated learning for privacy-preserving collaborations, innovations in explainable AI, and real-time applications in telemedicine. Addressing these challenges will be crucial to realizing the full potential of GANs in revolutionizing medical imaging and healthcare.

Adjacent Channel Weight Dependable RLS Adaptive Filter with VMD based Artifact Removal Mechanism in Fetal ECG Separation

Adjacent Channel Weight Dependable RLS Adaptive Filter with VMD based Artifact Removal Mechanism in Fetal ECG Separation

Motion Artifact Removal in Functional Near‐Infrared Spectroscopy Based on Long Short‐Term Memory‐Autoencoder Model

ABSTRACTMotion artifact removal is a critical issue in functional near‐infrared spectroscopy (fNIRS) analysis tasks, with traditional methods relying heavily on expert‐based knowledge and optimal selection of model parameters within brain regions. In this paper, we propose a deep learning denoising model based on long short‐term memory (LSTM)‐autoencoder (viz., LSTM‐AE) to reduce motion artifacts. By training a neural network to reconstruct hemodynamic response coupled with neuronal activity, LSTM‐AE achieves positive denoising results on both our synthesized noisy simulated dataset and the real dataset. The LSTM‐AE processes the raw fNIRS in three phases: (1) Morphological feature extraction of the raw fNIRS is conducted through the encoder module. (2) The LSTM module captures temporal correlations between individual samples to enhance features. (3) The decoder module recovers and reconstructs the morphological feature information of fNIRS from the latent space. Finally, clean reconstructed fNIRS is generated at the output layer. We compare our proposed method with existing calibration algorithms for hemodynamic response estimation using the following metrics: mean square error (MSE), Pearson's correlation (R2), signal‐to‐noise ratio (SNR), and percent deviation ratio (PDR). The proposed LSTM‐AE method outperforms conventional methods, demonstrating an improvement in all these metrics. Additionally, the proposed LSTM‐AE method shows statistically significant differences from other motion artifact algorithms in terms of effectiveness (p < 0.01, significance level α = 0.05). This study demonstrates the potential of deep network architectures to remove motion artifacts in fNIRS data.

Ocular Artifacts Removal in EEG Signal Based on Discrete Wavelet Transform and Savitzky-Golay Filter

Electroencephalography (EEG) is a critical tool in neuroscience and clinical diagnostics, offering valuable insights into brain activity. However, EEG signals are often contaminated by ocular artifacts, which can significantly distort the data, leading to potential misinterpretations. This study introduces a novel method for removing ocular artifacts from EEG signals using a combination of Discrete Wavelet Transform (DWT) and Savitzky-Golay (SG) filter. The proposed method effectively separates the EEG signal into multiple subbands using DWT, followed by the application of the SG filter to the contaminated subbands to remove artifacts while preserving the integrity of the original EEG signal. The performance of the proposed method is evaluated using a publicly available EEG dataset. Two performance metrics (signal-to-noise ratio improvement, and percentage reduction of correlation coefficient) are used to test the DWT-SG method. The results show superior artifact removal capabilities and lower computational complexity compared to traditional methods. The results demonstrate that the DWT-SG approach has an average SNRI and η values of 10.367 dB and 25.26%.

Comparative Neuroexcitation Patterns Using fNIRS in Women With Overactive Bladder

Importance Functional near-infrared spectroscopy (fNIRS) is a noninvasive technique used to quantify prefrontal cortex (PFC) neuroexcitation. The PFC is involved in the decision to void, and dysfunction in the region has been associated with overactive bladder (OAB). This study demonstrates neuroexcitation differences in the brain region associated with the decision to void (prefrontal cortex) using noninvasive fNIRS. Objective The objective of this study was to compare PFC neuroexcitation during natural filling in female participants with and without OAB. Study Design Female participants with OAB were cross-sectionally compared with controls without urinary urgency. The fNIRS signals were continuously recorded during an oral hydration protocol. Simultaneously, recordings of real-time bladder sensation of fullness were completed. A period of “high sensation” was defined as the time from first desire to 100% sensation. Signal analysis included removal of motion artifact, low pass filtering, and interpolated to standardize reporting bladder filling time. Results A total of 25 female participants were enrolled and had complete analyzable data, including 14 with OAB and 11 controls without OAB. Change in O2Hb during the high sensation period was significantly lower in all PFC regions in the OAB group compared with controls (P < 0.001). The majority of OAB participants had a constant or decreasing neuroexcitation pattern, which differenced in comparison to normal controls who displayed an increasing pattern. Conclusions This study demonstrates that fNIRS PFC excitation during a period of high sensation is consistently lower in women with OAB as compared with controls. These data support the hypothesis that the PFC plays an inhibitory role in voiding function and that there may be a lack of inhibitory control in women with OAB.