Motion Artifact Removal Research Articles

Restoration of motion-corrupted EEG signals using attention-guided operational CycleGAN

Electroencephalogram (EEG) signals suffer substantially from motion artifacts even in ambulatory settings. Signal processing techniques for removing motion artifacts from EEG signals have limitations, and the potential of classical or deep machine-learning algorithms for this task remains largely unexplored. We propose Attention-Guided Operational CycleGAN (AGO-CycleGAN), a novel CycleGAN-based framework to remove motion artifacts and enhance the quality of corrupted EEG signals. It incorporates self-generative operational neurons and an attention-guided Feature Pyramid Network with modified bottlenecks as generators and PatchGAN-based discriminators. AGO-CycleGAN was trained and tested on a single-channel EEG dataset from 23 subjects, using a subject-independent Jackknife cross-validation approach. It outperformed other methods and was evaluated through qualitative and quantitative analysis, employing robust metrics in both temporal and frequency domains. The results indicate its effectiveness in restoring EEG signals affected by severe motion artifacts. AGO-CycleGAN achieves state-of-the-art EEG restoration performance in the temporal domain, gaining improvements in signal-to-noise ratio (ΔSNR) and temporal correlation (ηtemp) by 26.497 dB and 87.2%, respectively. It also showed excellent performance in preserving the spectral EEG components (delta, theta, alpha, beta, and gamma), evaluated through band power ratio before and after restoration. Spectral correlation (ηspec) improved by 93.5% after cleaning the motion artifacts. Qualitative evaluations showed excellently reconstructed clean EEG waveforms upon restoration. Spectral restoration visualized through Power Spectral Density (PSD) plots and per-band topographic maps showed a uniform removal of high-power motion artifact components throughout the spectrum. AGO-CycleGAN significantly outperformed existing techniques in EEG artifact removal and can be extended to multi-channel EEG systems.

MRI motion artifact reduction using a conditional diffusion probabilistic model (MAR-CDPM).

High-resolution magnetic resonance imaging (MRI) with excellent soft-tissue contrast is a valuable tool utilized for diagnosis and prognosis. However, MRI sequences with long acquisition time are susceptible to motion artifacts, which can adversely affect the accuracy of post-processingalgorithms. This study proposes a novel retrospective motion correction method named "motion artifact reduction using conditional diffusion probabilistic model" (MAR-CDPM). The MAR-CDPM aimed to remove motion artifacts from multicenter three-dimensional contrast-enhanced T1 magnetization-prepared rapid acquisition gradient echo (3D ceT1 MPRAGE) brain dataset with different brain tumor types. This study employed two publicly accessible MRI datasets: one containing 3D ceT1 MPRAGE and 2D T2-fluid attenuated inversion recovery (FLAIR) images from 230 patients with diverse brain tumors, and the other comprising 3D T1-weighted (T1W) MRI images of 148 healthy volunteers, which included real motion artifacts. The former was used to train and evaluate the model using the in silico data, and the latter was used to evaluate the model performance to remove real motion artifacts. A motion simulation was performed in k-space domain to generate an in silico dataset with minor, moderate, and heavy distortion levels. The diffusion process of the MAR-CDPM was then implemented in k-space to convert structure data into Gaussian noise by gradually increasing motion artifact levels. A conditional network with a Unet backbone was trained to reverse the diffusion process to convert the distorted images to structured data. The MAR-CDPM was trained in two scenarios: one conditioning on the time step of the diffusion process, and the other conditioning on both and T2-FLAIR images. The MAR-CDPM was quantitatively and qualitatively compared with supervised Unet, Unet conditioned on T2-FLAIR, CycleGAN, Pix2pix, and Pix2pix conditioned on T2-FLAIR models. To quantify the spatial distortions and the level of remaining motion artifacts after applying the models, quantitative metrics were reported including normalized mean squared error (NMSE), structural similarity index (SSIM), multiscale structural similarity index (MS-SSIM), peak signal-to-noise ratio (PSNR), visual information fidelity (VIF), and multiscale gradient magnitude similarity deviation (MS-GMSD). Tukey's Honestly Significant Difference multiple comparison test was employed to quantify the difference between the models where p-value was considered statisticallysignificant. Qualitatively, MAR-CDPM outperformed these methods in preserving soft-tissue contrast and different brain regions. It also successfully preserved tumor boundaries for heavy motion artifacts, like the supervised method. Our MAR-CDPM recovered motion-free in silico images with the highest PSNR and VIF for all distortion levels where the differences were statistically significant (p-values ). In addition, our method conditioned on t and T2-FLAIR outperformed (p-values ) other methods to remove motion artifacts from the in silico dataset in terms of NMSE, MS-SSIM, SSIM, and MS-GMSD. Moreover, our method conditioned on only t outperformed generative models (p-values ) and had comparable performances compared with the supervised model (p-values ) to remove real motionartifacts. The MAR-CDPM could successfully remove motion artifacts from 3D ceT1 MPRAGE. It is particularly beneficial for elderly who may experience involuntary movements during high-resolution MRI imaging with long acquisitiontimes.

PortableSingle-Exposure Dual-Energy X-ray Detector for Improved Point-of-Care Diagnostic Imaging.

Dual-energy subtraction (DES) imaging is well known to reduce anatomical noise and enable material classification. The current approaches to DES imaging have trade-offs, such as motion artifacts, low sensitivity because of losses in a mid-filter, and lack of portability. Recently, a portable triple-layer flat-panel detector (FPD) was proposed for use in single-shot DES imaging that can provide improved sensitivity and removal of motion artifacts in a point-of-care setting. The purpose of this study is to evaluate the feasibility of such a detector. Various image quality metrics and clinical images are provided. An FDA-cleared single-exposure DES FPD consisting of three stacked sensors was used for all measurements. This detector generates three images per exposure: A digital radiography (DR) image, i.e., as would be produced with a conventional detector, and two DES images, bone and soft tissue. To evaluate DR image quality, detective quantum efficiency (DQE) and modulation transfer function were measured for multiple radiation quality beams. Digital radiography and DES images obtained from this FPD were evaluated in previously reported fixed and portable clinical studies. Digital radiography and DES images from case studies are presented for qualitative assessment. Modulation transfer function and DQE were measured across multiple radiation quality beams for the DR image. The DES images showed good tissue separation and uniformity with no visible motion or alignment artifacts. The DES images, when read in conjunction with the DR image, resulted in increased reader confidence and revealed abnormalities or details that were sometimes overlooked in the DR image. The proposed panel produces high-quality DR images as indicated by the DQE and modulation transfer function. The DES images have been shown to improve sensitivity in clinical applications and increase reader confidence. This detector can enable DES in portable or otherwise difficult applications, opening new doors for improved patient care.

Automated motion artifact detection in early pediatric diffusion MRI using a convolutional neural network.

Diffusion MRI (dMRI) is a widely used method to investigate the microstructure of the brain. Quality control (QC) of dMRI data is an important processing step that is performed prior to analysis using models such as diffusion tensor imaging (DTI) or neurite orientation dispersion and density imaging (NODDI). When processing dMRI data from infants and young children, where intra-scan motion is common, the identification and removal of motion artifacts is of the utmost importance. Manual QC of dMRI data is (1) time-consuming due to the large number of diffusion directions, (2) expensive, and (3) prone to subjective errors and observer variability. Prior techniques for automated dMRI QC have mostly been limited to adults or school-age children. Here, we propose a deep learning-based motion artifact detection tool for dMRI data acquired from infants and toddlers. The proposed framework uses a simple three-dimensional convolutional neural network (3DCNN) trained and tested on an early pediatric dataset of 2,276 dMRI volumes from 121 exams acquired at 1 month and 24 months of age. An average classification accuracy of 95% was achieved following four-fold cross-validation. A second dataset with different acquisition parameters and ages ranging from 2-36 months (consisting of 2,349 dMRI volumes from 26 exams) was used to test network generalizability, achieving 98% classification accuracy. Finally, to demonstrate the importance of motion artifact volume removal in a dMRI processing pipeline, the dMRI data were fit to the DTI and NODDI models and the parameter maps were compared with and without motion artifact removal.

An 8-Channel Ambulatory EEG Recording IC With In-Channel Fully-Analog Real-Time Motion Artifact Extraction and Removal.

Wereport the design, implementation, and experimental characterization of an 8-channel EEG recording IC (0.13 μm CMOS, 12 mm 2 total area) with a channel architecture that conducts both the extraction and removal of motion artifacts on-chip and in-channel. The proposed dual-path feed-forward method for artifact extraction and removal is implemented in the analog domain, hence is needless of a DSP unit for artifact estimation, and its associated high-DR ADCs and DACs employed by the state of the art for artifact replica generation. Additionally, the presented architecture improves system's scalability as it enables channels' stand-alone operation, and yields the lowest reported channel power consumption among works featuring motion artifact detection/removal. Following an experimental study on electrode-skin interface electrical characteristics for dry electrodes in the absence and presence of motions, the article presents the channel architecture, its detailed signal transfer function analysis, circuit-level implementation, and experimental characterization results. Our measurement results show an amplification voltage gain of 48.3 dB, a bandwidth of 300 Hz, rail-to-rail input DC offset tolerance, and 41.5 dB artifact suppression, while consuming 55 μW per channel. The system's efficacy in EEG motion artifact suppression is validated experimentally, and system- and circuit-level features and performance metrics of the presented design are compared with the state of the art.

Blood pressure estimation and classification using a reference signal-less photoplethysmography signal: a deep learning framework.

The markers that help to predict th function of a cardiovascular system are hemodynamic parameters like blood pressure (BP), stroke volume, heart rate, and cardiac output. Continuous analysis of hemodynamic parameters such as BP can detect abnormalities earlier, preventing cardiovascular diseases (CVDs). However, sometimes due to motion artifacts, it becomes difficult to monitor the BP accurately and classify it. This work presents an optimized deep learning model having the capability to estimate the systolic blood pressure (SBP) and diastolic blood pressure (DBP) and classify the BP stages simultaneously from the same network using only a single channel photoplethysmography (PPG) signal. The proposed model is designed by exploiting the deep learning framework of a convolutional neural network (CNN), exhibiting the inherent ability to extract features automatically. Moreover, the proposed framework utilizes the superlet transform method to transform a 1-D PPG signal into a 2-D super-resolution time-frequency (TF) spectrogram. A superlet transform separates the peaks related to true PPG signal components and motion artifacts components. Thus, the superlet provides a robust realtime approach to accurately estimating and classifying BP using a single PPG sensor signal and does not require additional ECG and PPG sensor signals for reference. Using a super-resolution spectrogram and CNN model makes the method profitable in motion artifact removal, feature selection, and extraction. Hence the proposed framework becomes less complex for deployment on wearable devices having limited battery resources. The performance of the proposed framework is demonstrated on the publicly available larger dataset MIMIC-III. This work obtained a mean absolute error (MAE) of 2.71mmHg and 2.42mmHg for SBP and DBP, respectively. The classification accuracy for the SBP prediction is about 96.79%, whereas it is 98.94% for DBP. From a motion artifact-affected PPG signal, SBP and DBP are estimated. Then the estimated BP is classified into three categories: normotension, prehypertension, and hypertension, and is compared with the state of art methods to show the effectiveness of the proposed optimized framework.

Virtual blebbistatin: A robust and rapid software approach to motion artifact removal in optical mapping of cardiomyocytes

Fluorescent reporters of cardiac electrophysiology provide valuable information on heart cell and tissue function. However, motion artifacts caused by cardiac muscle contraction interfere with accurate measurement of fluorescence signals. Although drugs such as blebbistatin can be applied to stop cardiac tissue from contracting by uncoupling calcium-contraction, their usage prevents the study of excitation-contraction coupling and, as we show, impacts cellular structure. We therefore developed a robust method to remove motion computationally from images of contracting cardiac muscle and to map fluorescent reporters of cardiac electrophysiological activity onto images of undeformed tissue. When validated on cardiomyocytes derived from human induced pluripotent stem cells (iPSCs), in both monolayers and engineered tissues, the method enabled efficient and robust reduction of motion artifact. As with pharmacologic approaches using blebbistatin for motion removal, our algorithm improved the accuracy of optical mapping, as demonstrated by spatial maps of calcium transient decay. However, unlike pharmacologic motion removal, our computational approach allowed direct analysis of calcium-contraction coupling. Results revealed calcium-contraction coupling to be more uniform across cells within engineered tissues than across cells in monolayer culture. The algorithm shows promise as a robust and accurate tool for optical mapping studies of excitation-contraction coupling in heart tissue.

Comparing the efficacy of data-driven denoising methods for a multi-echo fMRI acquisition at 7T

In functional magnetic resonance imaging (fMRI) of the brain the measured signal is corrupted by several (e.g. physiological, motion, and thermal) noise sources and depends on the image acquisition. Imaging at ultrahigh field strength is becoming increasingly popular as it offers increased spatial accuracy. The latter is of particular benefit in brainstem neuroimaging given the small cross-sectional area of most nuclei. However, physiological noise scales with field strength in fMRI acquisitions. Although this problem is in part solved by decreasing voxel size, it is clear that adequate physiological denoising is of utmost importance in brainstem-focused fMRI experiments. Multi-echo sequences have been reported to facilitate highly effective denoising through TE-dependence of Blood Oxygen Level Dependent (BOLD) signals, in a denoising method referred to as multi-echo independent component analysis (ME-ICA). It has not been explored previously how ME-ICA compares to other data-driven denoising approaches at ultrahigh field strength. In the current study, we compared the efficacy of several denoising methods, including anatomical component based correction (aCompCor), Automatic Removal of Motion Artifacts (ICA-AROMA) aggressive and non-aggressive options, ME-ICA, and a combination of ME-ICA and aCompCor. We assessed several data quality metrics, including temporal signal-to-noise ratio (tSNR), delta variation signal (DVARS), spectral density of the global signal, functional connectivity and Shannon spectral entropy. Moreover, we looked at the ability of each method to uncouple the global signal and respiration. In line with previous reports at lower field strengths, we demonstrate that after applying ME-ICA, the data is best post-processed in order to remove spatially diffuse noise with a method such as aCompCor. Our findings indicate that ME-ICA combined with aCompCor and the aggressive option of ICA-AROMA are highly effective denoising approaches for multi-echo data acquired at 7T. ME-ICA combined with aCompCor potentially preserves more signal-of-interest as compared to the aggressive option of ICA-AROMA.

Unsupervised dual-domain disentangled network for removal of rigid motion artifacts in MRI

Motion artifacts in magnetic resonance imaging (MRI) have always been a serious issue because they can affect subsequent diagnosis and treatment. Supervised deep learning methods have been investigated for the removal of motion artifacts; however, they require paired data that are difficult to obtain in clinical settings. Although unsupervised methods are widely proposed to fully use clinical unpaired data, they generally focus on anatomical structures generated by the spatial domain while ignoring phase error (deviations or inaccuracies in phase information that are possibly caused by rigid motion artifacts during image acquisition) provided by the frequency domain. In this study, a 2D unsupervised deep learning method named unsupervised disentangled dual-domain network (UDDN) was proposed to effectively disentangle and remove unwanted rigid motion artifacts from images. In UDDN, a dual-domain encoding module was presented to capture different types of information from the spatial and frequency domains to enrich the information. Moreover, a cross-domain attention fusion module was proposed to effectively fuse information from different domains, reduce information redundancy, and improve the performance of motion artifact removal. UDDN was validated on a publicly available dataset and a clinical dataset. Qualitative and quantitative experimental results showed that our method could effectively remove motion artifacts and reconstruct image details. Moreover, the performance of UDDN surpasses that of several state-of-the-art unsupervised methods and is comparable with that of the supervised method. Therefore, our method has great potential for clinical application in MRI, such as real-time removal of rigid motion artifacts.

Motion-robust anterior–posterior imaging ballistocardiography for non-contact heart rate measurements

Imaging ballistocardiography (iBCG) is a novel technique that utilizes video-based technology to measure heart rate (HR). This innovative method is based on the detection of subtle mechanical head movements that are caused by heartbeats and does not require direct physical contact with the body. However, the iBCG signals can be easily contaminated by rigid and nonrigid motion artifacts. In this paper, we propose a novel method for iBCG motion artifact removal (MAR). First, anterior–posterior (Z-axis) signals are reconstructed as the raw iBCG signals from two facial regions of interest (ROIs) according to the law of perspective. Next, the adaptive filtering technique is utilized to remove rigid motion artifacts from raw iBCG signals with respect to the motion reference of the X-axis traces. The rigid-motion-free iBCG signals in each ROI are further dimensionally compressed via principal component analysis (PCA). Then, the principle components (PCs) from the two regions of interest (ROIs) are subjected to canonical correlation analysis (CCA) to remove residual non-rigid motion artifacts that have low spatial correlations. Finally, the target HR value is identified by selecting the canonical variates (CVs) with the highest power spectrum amplitude. Experimental results on two publicly available databases and a in-house real-world database demonstrate that the proposed method achieves the best performance compared to existing iBCG methods during most cases, especially in the presence of motion artifacts. The study provides a feasible scheme for practical applications of iBCG HR measurements.

Abstract P1096: Computational Motion Artifact Removal Acts As Virtual Blebbistatin In Ipsc-derived Cardiomyocytes And Micro-tissues

Introduction: Drugs like blebbistatin that paralyze tissues are critical for accurate optocardiography but directly affect sarcomeres, making it challenging to study structure-function relationships. To overcome this, we applied Direct Deformation Estimation (DDE), a robust strain estimation tool, to enable computational motion removal from videos of beating monolayers and engineered heart tissues formed from human Induced Pluripotent Stem Cell derived cardiomyocytes (hiPSC-CM). Methods: hiPSC-CM and miniaturized engineered heart muscles were stained with the far-red voltage sensitive dye, BeRST-1. Videos of overall motion (bright-field), Ca 2+ (endogenous GCamP6f reporter) and voltage were captured at 100 Hz. Temporal median filtering and Contrast-Limited Adaptive Histogram Equalization were applied as pre-processing steps to improve convergence. The inverse of conformal mappings estimated from DDE were used to “unwarp” videos to artificially reduce motion. Removal of motion was assessed in bright-field videos by performing optical flow analysis. Improvements in optical mapping accuracy were estimated by calculating the spatial distribution of APD 80 (voltage) and time to 75% decay from peak (τ 75 ; Ca 2+ ). Results: Virtual blebbistatin removed >90% of motion from monolayers and engineered tissues without affecting sarcomere architecture (sarcomeric α-Actinin staining), in contrast to chemical blebbistatin. Virtual blebbistatin further reduced spatial dispersion in both APD 80 and τ 75, leading to overall distributions that were less skewed by artificially low repolarization times. Interestingly, when directly assessing Ca 2+ -contraction coupling in plots of motion-corrected Ca 2+ vs. contraction magnitude, we observed that engineered tissues had more uniform and consistent coupling compared to monolayers. Conclusions: Superior uniformity in calcium-contraction coupling of engineered tissues as opposed to monolayers is consistent with observations that engineered tissues are more likely to recapitulate genotype-phenotype relationships and drug responsiveness. Virtual blebbistatin is a promising tool for non-invasive analysis of Ca 2+ -contraction coupling and robust optocardiography.

Enhanced Contactless Heart Rate Monitoring Using Camera with Motion Artifact Removal During Physical Activities.

Contactless monitoring of heart rate (HR) can improve passive and continuous tracking of cardiovascular activities and overall people's health. Remote photoplethysmography (rPPG) using a camera eliminates the need for a wearable device. rPPG-based HR has shown promising results to be accurate and comparable to conventional methods such as contact PPG. Most experiments use stationary subjects while motion is known to affect the accuracy of remote PPG. In this paper, a novel methodology is introduced to enhance the accuracy and reliability of HR monitoring based on rPPG in the presence of physical activities like Yoga. This method quickly and accurately tracks HR and analyzes head motion to exclude unreliable data within short windows of rPPG signals. The method was tested with smartphone video data collected from 60 subjects when they are doing activities with varying levels of movement. Results show that our method without motion removal improves the accuracy of the HR readings by 0.7 bpm, reaching 3.57 bpm on average for a 30-sec-window. The accuracy is further improved by another 1.3 bpm after removing the motion artifacts, and reaches 2.29 bpm.Clinical relevance- The enhancement of HR readings from shorter rPPG signal with motion tolerance during physical activities can ultimately help with a more reliable HR tracking of people in uncontrolled settings like home which is a critical step towards remote health-care or wellness tracking.

Precision Heart Rate Estimation Using a PPG Sensor Patch Equipped with New Algorithms of Pre-Quality Checking and Hankel Decomposition.

A new method for accurately estimating heart rates based on a single photoplethysmography (PPG) signal and accelerations is proposed in this study, considering motion artifacts due to subjects' hand motions and walking. The method comprises two sub-algorithms: pre-quality checking and motion artifact removal (MAR) via Hankel decomposition. PPGs and accelerations were collected using a wearable device equipped with a PPG sensor patch and a 3-axis accelerometer. The motion artifacts caused by hand movements and walking were effectively mitigated by the two aforementioned sub-algorithms. The first sub-algorithm utilized a new quality-assessment criterion to identify highly noise-contaminated PPG signals and exclude them from subsequent processing. The second sub-algorithm employed the Hankel matrix and singular value decomposition (SVD) to effectively identify, decompose, and remove motion artifacts. Experimental data collected during hand-moving and walking were considered for evaluation. The performance of the proposed algorithms was assessed using the datasets from the IEEE Signal Processing Cup 2015. The obtained results demonstrated an average error of merely 0.7345 ± 8.1129 beats per minute (bpm) and a mean absolute error of 1.86 bpm for walking, making it the second most accurate method to date that employs a single PPG and a 3-axis accelerometer. The proposed method also achieved the best accuracy of 3.78 bpm in mean absolute errors among all previously reported studies for hand-moving scenarios.

Wearable Integrated Online Fusion Learning Filter for Heart PPG Sensing Tracking

Heart rate is an important physiological indicator of the human body. It can evaluate the activity of the heart and the degree of fatigue. It can be further used to assess emotions by monitoring heart rate changes and voice recording or breathing. Single-lead or multi-lead equipment is often used to monitor ECG in medical treatment. However, it brings inconvenience to daily life to record the heart rate from a free-living natural environment. Due to the subject’s voluntary or involuntary movement, it is difficult to collect ideal photoplethysmography (PPG) signal by using wearable device as it is continually interfered by the motion artifacts (MA). These MAs seriously affect the calculation and online monitoring of the heart rate. This paper proposes a wearable device with real-time online fusion learning for heart PPG tracking. In particular, it proposes a Recursive Least Squares algorithm to fuse three-axis acceleration signals to remove motion artifacts from PPG signals. In order to further determine the heart rate frequency range and select the appropriate spectrum peak, a decision tree spectrum interval estimation method is proposed to provide prior information for PPG signal spectrum tracking, so as to optimize the spectrum peak estimation. The performance of the proposed device, which is an integrated internet of things with wearable platform, has been shown to be robust to natural and unpredictable situations. Experimental results have confirmed that the proposed method can adaptively track the PPG signal with high accuracy.

Removal of Motion Artifacts in Capacitive Electrocardiogram Acquisition: A Review.

Capacitive electrocardiogram (cECG) systems are increasingly used for the monitoring of cardiac activity. They can operate within the presence of a small layer of air, hair or cloth and do not require a qualified technician. They can be integrated into wearables, clothing or objects of daily life, such as beds or chairs. While they offer many advantages over conventional electrocardiogram systems (ECG) that rely on wet electrodes, they are more prone to be affected by motion artifacts (MAs). These effects, which are due to the relative movement of the electrode in relation to the skin, are several orders of magnitude higher than ECG signal amplitudes, they occur in frequencies that might overlap with the ECG signal, and they may saturate the electronics in the most severe cases. In this paper, we provide a detailed description of MA mechanisms that translate into capacitance variations due to electrode-skin geometric changes or into triboelectric effects due to electrostatic charge redistribution. A state-of-the-art overview of the different approaches based on materials and construction, analog circuits and digital signal processing is provided as well as the trade-offs to be made using these techniques, to mitigate MAs efficiently.

An Improved Method of Heart Rate Extraction Algorithm Based on Photoplethysmography for Sports Bracelet

Heart rate measurement employing photoplethysmography (PPG) is a prevalent technique for wearable devices. However, the acquired PPG signal is often contaminated with motion artifacts, which need to be accurately removed. In cases where the PPG and accelerometer (ACC) spectra overlap at the actual heart rate, traditional discrete Fourier transform (DFT) algorithms fail to compute the heart rate accurately. This study proposed an enhanced heart rate extraction algorithm based on PPG to address the issue of PPG and ACC spectral overlap. The spectral overlap is assessed according to the morphological characteristics of both the PPG and ACC spectra. Upon detecting an overlap, the singular spectrum analysis (SSA) algorithm is employed to calculate the heart rate at the given time. The SSA algorithm effectively resolves the issue of spectral overlap by removing motion artifacts through the elimination of ACC-related time series in the PPG signal. Experimental results reveal that the accuracy of the proposed algorithm surpasses that of the traditional DFT method by 19.01%. The proposed method makes up for the deficiency posed by artifact and heart rate signal overlap in conventional algorithms and significantly improves heart rate extraction accuracy.

Adaptive Algorithm for Motion Artifacts Removal in Wearable Biomedical Sensors During Physical Exercise

<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Objective:</i> Motion artifacts (MA) are significant sources of noise in the wearable devices that are used to collect biological information from the human body. Photoplethysmography (PPG) is an example of the sensors embedded in many of these devices. PPG signals are highly influenced by MA, especially when the motion involves the organ that the PPG sensor is attached to. The aim of this paper is to build an adaptive algorithm and multiresolution analysis technique to denoise the raw PPG signals, suppress the MAs and accurately estimate the HR as an example of MA suppression in the wearable devices. The challenge here is to find the right selection considering high accuracy and low-computational complexity. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Methods:</i> Discrete wavelet transform recursive inverse (DWT-RI) adaptive filter algorithm in addition to multiresolution analysis is implemented to suppress MAs and estimate the HR using the simultaneously recorded accelerations in the three dimensions as reference signals for the adaptive algorithm. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Results:</i> The proposed algorithm has a low computational cost and results in an absolute average error of 1.17 beats per minute (BPM) when tested on 12 subjects from a well-known database for this purpose. The performance of the proposed algorithm is compared to the other existing methods in literature used for noise removal and motion artifact suppression. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Conclusion:</i> DWT-RI adaptive algorithm can successfully suppress motion artifacts in PPG signals with a low computational complexity and outperforms several alternatives in terms of the average absolute error.

An Automatic Motion-Based Artifact Reduction Algorithm for fNIRS in Concurrent Functional Magnetic Resonance Imaging Studies (AMARA–fMRI)

Multimodal functional near-infrared spectroscopy–functional magnetic resonance imaging (fNIRS–fMRI) studies have been highly beneficial for both the fNIRS and fMRI field as, for example, they shed light on the underlying mechanism of each method. However, several noise sources exist in both methods. Motion artifact removal is an important preprocessing step in fNIRS analysis. Several manual motion–artifact removal methods have been developed which require time and are highly dependent on expertise. Only a few automatic methods have been proposed. AMARA (acceleration-based movement artifact reduction algorithm) is one of the most promising automatic methods and was originally tested in an fNIRS sleep study with long acquisition times (~8 h). However, it relies on accelerometry data, which is problematic when performing concurrent fNIRS–fMIRI experiments. Most accelerometers are not MR compatible, and in any case, existing datasets do not have this data. Here, we propose a new way to retrospectively determine acceleration data for motion correction methods, such as AMARA in multimodal fNIRS–fMRI studies. We do so by considering the individual slice stack acquisition times of simultaneous multislice (SMS) acquisition and reconstructing high-resolution motion traces from each slice stack time. We validated our method on 10 participants during a memory task (2- and 3-back) with 6 fNIRS channels over the prefrontal cortex (limited field of view with fMRI). We found that this motion correction significantly improved the detection of activation in deoxyhemoglobin and outperformed up-sampled motion traces. However, we found no improvement in oxyhemoglobin. Furthermore, our data show a high overlap with fMRI activation when considering activation in channels according to both deoxyhemoglobin and oxyhemoglobin.

Hybrid deep autoencoder network based adaptive cross guided bilateral filter for motion artifacts correction and denoising from MRI

ABSTRACT Removal of motion artifacts from medical images is essential, because the respiration by patient causes degradation in artifact removal. Therefore, getting an MRI without any artifacts and noise is challenging. Previous techniques failed to preserve the image quality during denoising, thereby affecting the classification accuracy. To overcome such challenges, two modules are considered in this work: classification and denoising. The classification process is successfully performed by Hybrid Deep autoencoder-convolutional neural network (DAE-CNN). It classifies the original images into motion artifacts, available and normal images. Then, the available artifacts are removed using cross guided bilateral filter (CGBF). The optimal parameters required to improve the CGBF performance are selected using the hybrid optimization algorithm. The filter’s performance relies on the optimal spatial and range kernels selection. Finally, the classification and denoising-based results are evaluated using the BRATS 2015 dataset and achieved 95.84% accuracy and PSNR – 46.4, which is better than existing methods.

Dynamic 3D imaging of cerebral blood flow in awake mice using self-supervised-learning-enhanced optical coherence Doppler tomography

Cerebral blood flow (CBF) is widely used to assess brain function. However, most preclinical CBF studies have been performed under anesthesia, which confounds findings. High spatiotemporal-resolution CBF imaging of awake animals is challenging due to motion artifacts and background noise, particularly for Doppler-based flow imaging. Here, we report ultrahigh-resolution optical coherence Doppler tomography (µODT) for 3D imaging of CBF velocity (CBFv) dynamics in awake mice by developing self-supervised deep-learning for effective image denoising and motion-artifact removal. We compare cortical CBFv in awake vs. anesthetized mice and their dynamic responses in arteriolar, venular and capillary networks to acute cocaine (1 mg/kg, i.v.), a highly addictive drug associated with neurovascular toxicity. Compared with awake, isoflurane (2-2.5%) induces vasodilation and increases CBFv within 2-4 min, whereas dexmedetomidine (0.025 mg/kg, i.p.) does not change vessel diameters nor flow. Acute cocaine decreases CBFv to the same extent in dexmedetomidine and awake states, whereas decreases are larger under isoflurane, suggesting that isoflurane-induced vasodilation might have facilitated detection of cocaine-induced vasoconstriction. Awake mice after chronic cocaine show severe vasoconstriction, CBFv decreases and vascular adaptations with extended diving arteriolar/venular vessels that prioritize blood supply to deeper cortical capillaries. The 3D imaging platform we present provides a powerful tool to study dynamic changes in vessel diameters and morphology alongside CBFv networks in the brain of awake animals that can advance our understanding of the effects of drugs and disease conditions (ischemia, tumors, wound healing).