Motion Artifact Removal Research Articles

Removal of Motion Artifact in Top View of Optical Coherence Tomography Angiography Based on Compensated Eigenimage Filtering Algorithm

Removal of Motion Artifact in Top View of Optical Coherence Tomography Angiography Based on Compensated Eigenimage Filtering Algorithm

Wavelet Domain Optimized Savitzky–Golay Filter for the Removal of Motion Artifacts From EEG Recordings

Motion artifact is observed in electroencephalogram (EEG) signals during the acquisition. The elimination of this type of artifact using various signal processing approaches is considered a preprocessing task for different neural information processing applications. In this article, the wavelet domain optimized Savitzky–Golay (WOSG) filtering approach was proposed for the removal of motion artifacts from EEG signals. The multiscale analysis of the EEG signals using discrete wavelet transform (DWT) produces subband signals at different scales. Motion artifact is a low-frequency artifact that appears in the approximation subband signal. The optimized SG filter was applied to the motion artifact intermixed approximation subband signal, and the cleaned approximation subband signal was evaluated based on the subtraction of the optimized SG filter output from the motion artifact intermixed subband signal. The filtered EEG signal was computed based on the addition of cleaned approximation subband signal with other subband signals of contaminated EEG. The proposed WOSG filtering approach was evaluated using EEG recordings from various publicly available databases. Measures, such as the mean absolute error in power spectral density (MAE-PSD) of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\delta $ </tex-math></inline-formula> -band between contaminated and cleaned EEG signal, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Delta $ </tex-math></inline-formula> SNR, percentage change in correlation coefficients ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\eta $ </tex-math></inline-formula> ), and mutual information (MI), were used to quantify the performance of the proposed filtering approach. The results revealed that the proposed WOSG filtering approach had superior denoising performance with the average <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Delta $ </tex-math></inline-formula> SNR, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\eta $ </tex-math></inline-formula> , and MAE-PSD values of 30.59 dB, 68.76%, and 0.0263 dB/Hz in comparison to the multiresolution total variation (MTV) ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\Delta $ </tex-math></inline-formula> SNR as 29.12 dB, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\eta $ </tex-math></inline-formula> as 68.56%, and MAE-PSD as 0.0365 dB/Hz) and other existing methods. The approach had the average MI values of 4.152 and 4.103 and the average MAE-PSD values of 0.276 and 0.256 dB/Hz for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$\delta $ </tex-math></inline-formula> -bands of EEG signals recorded during standing and walking conditions.

Human Presence Sensing and Gesture Recognition for Smart Home Applications With Moving and Stationary Clutter Suppression Using a 60-GHz Digital Beamforming FMCW Radar

With the advancement of radio frequency (RF) assisted smart home technology, it is critical for the RF sensors deployed indoors to isolate the target of interest from unwanted clutter sources. This paper presents a novel method for suppressing both moving and stationary clutters in an indoor environment to localize stationary human subjects with a millimeter-wave frequency-modulated continuous-wave (FMCW) radar. The method derives its roots from the intrinsic high-pass filter (HPF) characteristic of the exponential moving average (EMA) algorithm, a preferred approach for background stationary clutter suppression. In this work, emphasis was laid on expanding the capability to detect and suppress unwanted moving clutter sources in the indoor environment along with stationary clutters, which has not been widely explored before. The proposed method removes motion artifacts so that the characteristic respiratory signal can be identified for human-aware localization. The paper provides experimental validation of the proposed method, wherein a 60-GHz FMCW radar with digital beamforming (DBF) capability was used to identify the 2-D location of a sitting human subject, with a moving window curtain in the background acting as a strong moving clutter source along with other stationary clutters. In addition, a lateral hand gesture recognition technique is presented, wherein the EMA algorithm was used to enhance the signature of the hand motion. The instantaneous position of the hand at the beginning and end of the gesture was determined to classify the gesture as a left-to-right or right-to-left hand swipe.

Smart automated heart health monitoring using photoplethysmography signal classification.

This paper proposes a smart, automated heart health-monitoring (SAHM) device using a single photoplethysmography (PPG) sensor that can monitor cardiac health. The SAHM uses an Orthogonal Matching Pursuit (OMP)-based classifier along with low-rank motion artifact removal as a pre-processing stage. Major contributions of the proposed SAHM device over existing state-of-the-art technologies include these factors: (i)the detection algorithm works with robust features extracted from a single PPG sensor; (ii) the motion compensation algorithm for the PPG signal can make the device wearable; and (iii) the real-time analysis of PPG input and sharing through the Internet. The proposed low-cost, compact and user-friendly PPG device can also be prototyped easily. The SAHM system was tested on three different datasets, and detailed performance analysis was carried out to show and prove the efficiency of the proposed algorithm.

A Real-Time Movement Artifact Removal Method for Ambulatory Brain-Computer Interfaces.

Recently, practical brain-computer interfaces (BCIs) have been widely investigated for detecting human intentions in real world. However, performance differences still exist between the laboratory and the real world environments. One of the main reasons for such differences comes from the user's unstable physical states (e.g., human movements are not strictly controlled), which produce unexpected signal artifacts. Hence, to minimize the performance degradation of electroencephalography (EEG)-based BCIs, we present a novel artifact removal method named constrained independent component analysis with online learning (cIOL). The cIOL can find and reject the noise-like components related to human body movements (i.e., movement artifacts) in the EEG signals. To obtain movement information, isolated electrodes are used to block electrical signals from the brain using high-resistance materials. We estimate artifacts with movement information using constrained independent component analysis from EEG signals and then extract artifact-free signals using online learning in each sample. In addition, the cIOL is evaluated by signal processing under 16 different experimental conditions (two types of EEG devices × two BCI paradigms × four different walking speeds). The experimental results show that the cIOL has the highest accuracy in both scalp- and ear-EEG, and has the highest signal-to-noise ratio in scalp-EEG among the state-of-the-art methods, except for the case of steady-state visual evoked potential at 2.0 m/s with superposition problem.

Retrospective respiratory motion correction in cardiac cine MRI reconstruction using adversarial autoencoder and unsupervised learning.

The aim of this study was to develop a deep neural network for respiratory motion compensation in free-breathing cine MRI and evaluate its performance. An adversarial autoencoder network was trained using unpaired training data from healthy volunteers and patients who underwent clinically indicated cardiac MRI examinations. A U-net structure was used for the encoder and decoder parts of the network and the code space was regularized by an adversarial objective. The autoencoder learns the identity map for the free-breathing motion-corrupted images and preserves the structural content of the images, while the discriminator, which interacts with the output of the encoder, forces the encoder to remove motion artifacts. The network was first evaluated based on data that were artificially corrupted with simulated rigid motion with regard to motion-correction accuracy and the presence of any artificially created structures. Subsequently, to demonstrate the feasibility of the proposed approach in vivo, our network was trained on respiratory motion-corrupted images in an unpaired manner and was tested on volunteer and patient data. In the simulation study, mean structural similarity index scores for the synthesized motion-corrupted images and motion-corrected images were 0.76 and 0.93 (out of 1), respectively. The proposed method increased the Tenengrad focus measure of the motion-corrupted images by 12% in the simulation study and by 7% in the in vivo study. The average overall subjective image quality scores for the motion-corrupted images, motion-corrected images and breath-held images were 2.5, 3.5 and 4.1 (out of 5.0), respectively. Nonparametric-paired comparisons showed that there was significant difference between the image quality scores of the motion-corrupted and breath-held images (P < .05); however, after correction there was no significant difference between the image quality scores of the motion-corrected and breath-held images. This feasibility study demonstrates the potential of an adversarial autoencoder network for correcting respiratory motion-related image artifacts without requiring paired data.

Schrödinger filtering: a precise EEG despiking technique for EEG-fMRI gradient artifact

In EEG data acquired in the presence of fMRI, gradient-related spike artifacts contaminate the signal following the common preprocessing step of average artifact subtraction. Spike artifacts compromise EEG data quality since they overlap with the EEG signal in frequency, thereby confounding frequency-based inferences on activity. As well, spike artifacts can inflate or deflate correlations among time series, thereby confounding inferences on functional connectivity.We present Schrödinger filtering, which uses the Schrödinger equation to decompose the spike-containing input. The basis functions of the decomposition are localized and pulse-shaped, and selectively capture the various input peaks, with the spike components clustered at the beginning of the spectrum. Schrödinger filtering automatically subtracts the spike components from the data.On real and simulated data, we show that Schrödinger filtering (1) simultaneously accomplishes high spike removal and high signal preservation without affecting evoked activity, and (2) reduces spurious pairwise correlations in spontaneous activity. In these regards, Schrödinger filtering was significantly better than three other despiking techniques: median filtering, amplitude thresholding, and wavelet denoising.These results encourage the use of Schrödinger filtering in future EEG-fMRI pipelines, as well as in other spike-related applications (e.g., fMRI motion artifact removal or action potential extraction).

Car Driver's Sympathetic Reaction Detection Through Electrodermal Activity and Electrocardiogram Measurements.

in this paper we propose a system to detect a subject's sympathetic reaction, which is related to unexpected or challenging events during a car drive. we use the Electrocardiogram (ECG) signal and the Skin Potential Response (SPR) signal, which has several advantages with respect to other Electrodermal (EDA) signals. We record one SPR signal for each hand, and use an algorithm that, selecting the smoother signal, is able to remove motion artifacts. We extract statistical features from the ECG and SPR signals in order to classify signal segments and identify the presence or absence of emotional events via a Supervised Learning Algorithm. The experiments were carried out in a company which specializes in driving simulator equipment, using a motorized platform and a driving simulator. Different subjects were tested with this setup, with different challenging events happening on predetermined locations on the track. we obtain an Accuracy as high as 79.10% for signal blocks and as high as 91.27% for events. results demonstrate the good performance of the presented system in detecting sympathetic reactions, and the effectiveness of the motion artifact removal procedure. our work demonstrates the possibility to classify the emotional state of the driver, using the ECG and EDA signals and a slightly invasive setup. In particular, the proposed use of SPR and of the motion artifact removal procedure are crucial for the effectiveness of the system.

Preliminary study on motion artifacts removal of coronary CT angiography using generative adversarial network

Preliminary study on motion artifacts removal of coronary CT angiography using generative adversarial network

Comparative assessment of drivers' stress induced by autonomous and manual driving with heart rate variability parameters and machine learning analysis of electrodermal activity

Abstract Background Nowadays research on Autonomous Driving Systems (ADS) and attention towards novel technology allowing real-time assessment of car drivers' psycho-physiological status is growing, to quantify driver's stress during semi-autonomous or autonomous driving assistance and to investigate human reaction to different types of ADS. We present a system for automatic stress detection with combined machine learning analysis of Skin Potential Response (SPR) and electrocardiographic (ECG) recordings to compare the driver's stress reaction during both manual and autonomous driving sessions carried out in a dynamic professional drive simulator (PDS). Methods All data were acquired after informed consent from 14 healthy volunteers (HVs) in the Vi-grade (Udine) PDS. Two SPR signals (one from each hand) and three chest ECG leads were recorded. A Motion Artifact (MA) removal algorithm was used to remove motion artifacts from SPR signals. A cleaned, single SPR signal, obtained as the RMS value by combining the two original signals, was then sent together with the time-variation of heart rate (HR) to a Machine Learning (ML) classification algorithm, i.e., a Support Vector Machine (SVM), based on some specific features of this signal. The output of the SVM provides a series of labels, that indicate the presence or lack of stress episodes during the driving experiment. Stress occurrence was also independently quantified with heart rate variability (HRV) analysis in the time (TD) and frequency (FD) domains and with non-linear (NL) methods. Results All participants completed the driving protocol consisting of two subsequent sessions, one with conventional manual (MD) and the other with autonomous (AD) driving settings, along a highway where some unexpected events occurred, inducing different level stress response. Figure 1 shows an example of time variant changes of the RMS SPR signal and of the HR of one tested individual during both experimental settings. A simultaneous increase of both SPR and HR signal is apparent during the stress episodes correctly identified by the SVM (gray shadows). Discriminant analysis of FD (VLF, LF and HF) and NL (SD1, SD2, Entropy and Recurrence Plot) HRV parameters, independently assessed by two researchers blind to SVM results, differentiated between stress induced by MD and AD (accuracy: 88,4% cross-correlated) in good agreement with automatic SVM assessment. In general stress level was lower during the AD, being all HRV parameters not significantly modified from baseline rest. SPR amplitude eventually increased also during AD, but SVM efficiently differentiated between AD and MD stress anyhow. Conclusions The proposed method for automatic assessment of stress reactions of car drivers with SVM of SPR and HR signals is reliable, in both MD and AD scenarios. The results seem to evidence that MD is in general more demanding than AD inducing higher activation of sympathetic nervous system, especially in critical situations. Figure 1. Time variance of SPR and HR. Funding Acknowledgement Type of funding source: None

Wearable Belt With Built-In Textile Electrodes for Cardio—Respiratory Monitoring

Unobtrusive and continuous monitoring of vital signs is becoming more and more important both for patient monitoring in the home environment and for sports activity tracking. Even though many gadgets and clinical systems exist, the need for simple, low-cost and easily applicable solutions still remains, especially in view of a more widespread use within everyone’s reach. The paper presents a fully wearable and wireless sensorized belt, suitable to simultaneously acquire respiratory and cardiac signals employing a single acquisition channel. The adopted method relies on a 50-kHz current injected in the subject thorax through a couple of textile electrodes and on envelope detection of the trans-thoracic voltage acquired from a couple of different embedded electrodes. The resulting signal contains both the baseband electrocardiogram (ECG) signal and the trans-thoracic impedance signal, which encodes respiratory acts. The two signals can be easily separated through suitable filtering and the cardio–respiratory rates extracted. The proposed solution yields performances comparable to those of a spirometer and a two-lead ECG. The whole system, with a realization cost below 100 €, a wireless interface, and several hours (or even days) of autonomy, is a suitable candidate for everyday use, especially if complemented by motion artifact removal techniques, currently under implementation.

Motion and Muscle Artifact Removal Validation Using an Electrical Head Phantom, Robotic Motion Platform, and Dual Layer Mobile EEG.

Motion and muscle artifacts can undermine signal quality in electroencephalography (EEG) recordings during locomotion. We evaluated approaches for recovering ground-truth artificial brain signals from noisy EEG recordings. We built an electrical head phantom that broadcast four brain and four muscle sources. Head movements were generated by a robotic motion platform. We recorded 128-channel dual layer EEG and 8-channel neck electromyography (EMG) from the head phantom during motion. We evaluated ground-truth electrocortical source signal recovery from artifact contaminated data using Independent Component Analysis (ICA) to determine: (1) the number of isolated noise sensor recordings needed to capture and remove motion artifacts, (2) the ability of Artifact Subspace Reconstruction to remove motion and muscle artifacts at contrasting artifact detection thresholds, (3) the number of neck EMG sensor recordings needed to capture and remove muscle artifacts, and (4) the ability of Canonical Correlation Analysis to remove muscle artifacts. We also evaluated source signal recovery by combining the best practices identified in aims 1-4. By including isolated noise and EMG recordings in the ICA decomposition, we more effectively recovered ground-truth artificial brain signals. A reduced subset of 32-noise and 6-EMG channels showed equivalent performance compared to including the complete arrays. Artifact Subspace Reconstruction improved source separation, but this was contingent on muscle activity amplitude. Canonical Correlation Analysis also improved source separation. Merging noise and EMG recordings into the ICA decomposition, with Artifact Subspace Reconstruction and Canonical Correlation Analysis preprocessing, improved source signal recovery. This study expands on previous head phantom experiments by including neck muscle source activity and evaluating artificial electrocortical spectral power fluctuations synchronized with gait events.

T23. ANTIPSYCHOTIC EXPOSURE AND STRIATAL FUNCTIONAL CONNECTIVITY IN PSYCHOSIS RELAPSE: A HYPOTHESIS GENERATING STUDY

BackgroundMost individuals with schizophrenia experience relapse over the course of the illness, yet unfortunately the mechanisms of this phenomenon are poorly understood. This research is often confounded by non-adherence with antipsychotic drugs. We propose to study relapse in individuals treated with long acting injectable antipsychotics (LAIs), for whom treatment adherence is confirmed. Since striatal resting state functional connectivity (RSFC) has been shown to reflect pathophysiological aspects of antipsychotic treatment response, we aim to study striatal RSFC in relapse in individuals treated with LAIs to identify potential mechanisms. In particular, we will compare striatal RSFC between individuals who relapse while treated with LAIs, individuals who are not on LAIs and are non-adherent with antipsychotics at the time of relapse, and healthy controls, to generate a hypothesis about the role of striatal functioning in psychosis relapse.MethodsSubjects with a psychotic disorder treated with LAI antipsychotics and history of clinical response to that trial confirmed by collateral, presenting with acute psychotic symptoms at the time of the scan (defined as ≥4 in BPRS in at least one of the psychotic items) (n=16) were compared with subjects also with a psychotic disorder presenting with acute psychotic symptoms who were non-adherent with antipsychotic drugs demonstrated by negative plasma level (n=16), and healthy controls (n=18). Participants were scanned using fMRI and data was pre-processed using the HCP pipeline with the ICA-FIX procedure, removing motion artifacts and nuisance variables. Connectivity maps were generated for 6 bilateral (12 total) striatal regions of interest as in Di Martino et al. 2007, which were compared between groups (cluster threshold p< .05, voxel threshold p<.001 uncorrected). In addition, we calculated striatal connectivity indices (SCI) as in Sarpal et al. 2016, as this metric reflecting RSFC between the striatum and 91 other regions of interest has been shown to have high precision in predicting response to antipsychotics in patients with first episode psychosis.ResultsWe found no significant differences in sex or age between any of the 2 patient groups or the healthy controls, nor of psychopathology between the patient groups. For patients treated with LAIs upon relapse, striatal RSFC was significantly lower in an area in posterior cingulate, whereas it was higher in an area in the middle temporal gyrus, inferior temporal gyrus, and precentral gyrus, compared with healthy controls. When the LAI-treated individuals’ striatal RSFC was compared with that of individuals who were non-adherent with antipsychotic drugs at the time of relapse, it was significantly higher in the posterior parietal cortex, whereas it was lower in the pulvinar (thalamus) and primary and associative cortex. The SCI values for individuals who relapsed despite assured antipsychotic exposure were significantly lower than for non-LAI individuals who had relapsed due to non-adherence (p=0.049), and than healthy controls (p=0.01).DiscussionDespite a relatively small sample, these results indicate differences in striatal functional connectivity depending on antipsychotic exposure at the time of relapse. The finding of significantly lower SCI values for LAI treated individuals at the time of relapse compared with non-adherent individuals with relapse and healthy controls suggests the hypothesis that relapse occurring despite assured antipsychotic exposure may result from aberrant striatal functional connectivity which is insufficiently engaged by antipsychotic drugs.

S152. DIAGNOSTIC CLASSIFICATION OF SCHIZOPHRENIA USING 3D CONVOLUTIONAL NEURAL NETWORK WITH RESTING-STATE FUNCTIONAL MRI

BackgroundSeveral machine-learning (ML) algorithms have been deployed in the diagnostic classification of schizophrenia. Compared to other ML methods, the 3D convolutional neural network (CNN) has an advantage of learning complex and subtle patterns in data and preserving spatial information, which is a more suitable tool for brain imaging data. Although resting-state functional MRI (rsfMRI) data has been used in previous ML studies relating to the diagnostic classification of schizophrenia, a limited number of studies have been conducted using resting-state functional connectivity resulted from group independent component analysis (ICA) and dual regression. The objective of this study was to investigate whether a successful diagnostic classification of schizophrenia vs. healthy controls could be achieved by the 3D CNN using resting-state networks in which areas with a significant group difference in activity existed.MethodsT1 and rsfMRI data were collected in 46 patients with recent-onset schizophrenia and 22 healthy controls. In the pre-processing steps of rsfMRI, the ICA-based automatic removal of motion artifacts was applied to subject-level ICA results and the resulting rsfMRI data were temporally concatenated for group ICA and dual regression. The executive control and auditory networks had areas with significantly higher activity in the control group compared with the patient group. The independent components (ICs) respective to the executive control and auditory networks were used as input for the 3D CNN model which was developed to discriminate the schizophrenia patients from the healthy controls.ResultsThe 3D CNN model using the executive control and auditory networks as inputs showed classification accuracies of 65~70%, and error rates of 30~35% approximately.DiscussionOur findings suggest that the 3D CNN model using rsfMRI data can be useful for learning patterns implicated in schizophrenia and identifying discriminative patterns of schizophrenia in brain imaging data.

T135. ABERRANT EXECUTIVE CONTROL AND AUDITORY NETWORKS IN RECENT-ONSET SCHIZOPHRENIA - A GROUP ICA DUAL REGRESSION ANALYSIS

BackgroundA great number of studies using resting-state functional MRI (rsfMRI) have been conducted for revealing altered functional connectivity in schizophrenia. Although the default mode network has been predominantly investigated, other resting-state networks (RSNs) can be networks of interest for unveiling the neurobiological basis of schizophrenia. Our study investigated changes in functional connectivity in the nine RSNs in recent-onset schizophrenia.MethodsWe performed a rsfMRI in 46 patients with recent-onset schizophrenia and 22 healthy controls. In the preprocessing steps, independent component analysis (ICA)-based automatic removal of motion artifacts was applied to eliminate motion-related components from an individual-level ICA. Group ICA and dual regression were performed for voxel-wise comparisons between the groups with the non-parametric permutation test using threshold-free cluster enhancement and a corrected-p < 0.05 for multiple comparisons. We used the Positive and Negative Syndrome Scale scores for the correlation analysis of symptom severity with functional connectivity in the patient group.ResultsThe control group had areas with a significant group difference in activity compared to that of the patient group in which it existed in the left supplementary motor cortex and supramarginal gyrus (the executive control network) and the right postcentral gyrus (the auditory network). There were no significant correlations of symptom severity with the functional connectivity of these regions.DiscussionThe left supplementary motor cortex, supramarginal gyrus, and right postcentral gyrus having areas with a significant group difference may have a role in the pathophysiology of schizophrenia, given their language and auditory information processing functions.

Wireless Sensors System for Stress Detection by Means of ECG and EDA Acquisition.

This paper describes the design of a two channels electrodermal activity (EDA) sensor and two channels electrocardiogram (ECG) sensor. The EDA sensors acquire data on the hands and transmit them to the ECG sensor with wireless WiFi communication for increased wearability. The sensors system acquires two EDA channels to improve the removal of motion artifacts that take place if EDA is measured on individuals who need to move their hands in their activities. The ECG channels are acquired on the chest and the ECG sensor is responsible for aligning the two ECG traces with the received packets from EDA sensors; the ECG sensor sends via WiFi the aligned packets to a laptop for real time plot and data storage. The metrological characterization showed high-level performances in terms of linearity and jitter; the delays introduced by the wireless transmission from EDA to ECG sensor have been proved to be negligible for the present application.

Application of Biomedical Signal Acquisition Equipment in Human Sport Heart Rate Monitoring

Aiming at exploring biomedical signal acquisition equipment used in human motion heart rate monitoring, the research on the related hardware design and signal processing method was carried out. A biomedical signal acquisition device based on photoplethysmography (PPG) is designed, and the equipment was applied to acquire PPG signals and acceleration sensor signals under different motion states. The analysis of the experimental data showed that, the fusion method of the acceleration sensing information in the motion artifact removal method is perfected. The effectiveness of the baseline drift removal algorithm, motion artifact removal algorithm and dynamic heart rate monitoring algorithm was verified by reconstructing the signal quality evaluation index. To sum up, taking MINDRAY VS-800 as a reference device, it is compared with the adaptive filtering technology in terms of signal quality, BPM detection results and algorithm complexity, and better results are finally obtained.

Photoplethysmography Motion Artifacts Removal Based on Signal-Noise Interaction Modeling Utilizing Envelope Filtering and Time-Delay Neural Network

Physiological features extraction from Motion Artifacts (MA) corrupted Photoplethysmography (PPG) signals are of great difficulty due to the non-linear interaction between clean PPG and noise. To accurately extract features such as heart rate, blood pressure, and Oxygen Saturation in Blood, a robust PPG de-noising and waveform recovering method is required. However, traditional adaptive filtering or signal decomposition methods fail to achieve this goal. In this paper, a Signal-Noise Interaction modeling based algorithm for motion artifacts removal (SniMA) under strenuous physical exercise utilizing Envelope Filtering (EF) and Time-Delay Neural Network (TDNN) is proposed. Envelope Filtering normalizes raw data and eliminates imbalance training problem for neural networks, while TDNN is a hidden-state included method aiming at modeling PPG signal-noise interaction. An accelerometer as well as a gyroscope functions as the noise reference. Results comparing 8 performance indexes extracted from 4 types of waveform related features (heart rate, waveform correlation, pulse width, and pulse area) on an open access dataset we built show SniMA’s effectiveness for PPG MA removal. The proposed algorithm provides a significant improvement in PPG waveform recovery and PPG feature estimation accuracy. This is the first time that a TDNN has been introduced for PPG de-noising. This study also indicates the potential of other hidden-state involved signal-noise interaction modeling methods for PPG de-noising.

A Novel Adaptive Recursive Least Squares Filter to Remove the Motion Artifact in Seismocardiography.

This paper presents a novel adaptive recursive least squares filter (ARLSF) for motion artifact removal in the field of seismocardiography (SCG). This algorithm was tested with a consumer-grade accelerometer. This accelerometer was placed on the chest wall of 16 subjects whose ages ranged from 24 to 35 years. We recorded the SCG signal and the standard electrocardiogram (ECG) lead I signal by placing one electrode on the right arm (RA) and another on the left arm (LA) of the subjects. These subjects were asked to perform standing and walking movements on a treadmill. ARLSF was developed in MATLAB to process the collected SCG and ECG signals simultaneously. The SCG peaks and heart rate signals were extracted from the output of ARLSF. The results indicate a heartbeat detection accuracy of up to 98%. The heart rates estimated from SCG and ECG are similar under both standing and walking conditions. This observation shows that the proposed ARLSF could be an effective method to remove motion artifact from recorded SCG signals.

Self-Navigated Three-Dimensional Ultrashort Echo Time Technique for Motion-Corrected Skull MRI.

Ultrashort echo time (UTE) MRI is capable of detecting signals from protons with very short T2 relaxation times, and thus has potential for skull-selective imaging as a radiation-free alternative to computed tomography. However, relatively long scan times make the technique vulnerable to artifacts from involuntary subject motion. Here, we developed a self-navigated, three-dimensional (3D) UTE pulse sequence, which builds on dual-RF, dual-echo UTE imaging, and a retrospective motion correction scheme for motion-resistant skull MRI. Full echo signals in the second readout serve as a self-navigator that yields a time-course of center of mass, allowing for adaptive determination of motion states. Furthermore, golden-means based k-space trajectory was employed to achieve a quasi-uniform distribution of sampling views on a spherical k-space surface for any subset of the entire data collected, thereby allowing reconstruction of low-resolution images pertaining to each motion state for subsequent estimation of rigid-motion parameters. Finally, the extracted trajectory of the head was used to make the whole k-space datasets motion-consistent, leading to motion-corrected, high-resolution images. Additionally, we posit that hardware-related k-space trajectory errors, if uncorrected, result in obscured bone contrast. Thus, a calibration scan was performed once to measure k-space encoding locations, subsequently used during image reconstruction of actual imaging data. In vivo studies were performed to evaluate the effectiveness of the proposed correction schemes in combination with approaches to accelerated bone-selective imaging. Results illustrating effective removal of motion artifacts and clear depiction of skull bone voxels suggest that the proposed method is robust to intermittent head motions during scanning.