Showing papers in "IEEE Transactions on Biomedical Engineering in 2016"

Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks

Abstract: Goal: This paper presents a fast and accurate patient-specific electrocardiogram (ECG) classification and monitoring system. Methods: An adaptive implementation of 1-D convolutional neural networks (CNNs) is inherently used to fuse the two major blocks of the ECG classification into a single learning body: feature extraction and classification. Therefore, for each patient, an individual and simple CNN will be trained by using relatively small common and patient-specific training data, and thus, such patient-specific feature extraction ability can further improve the classification performance. Since this also negates the necessity to extract hand-crafted manual features, once a dedicated CNN is trained for a particular patient, it can solely be used to classify possibly long ECG data stream in a fast and accurate manner or alternatively, such a solution can conveniently be used for real-time ECG monitoring and early alert system on a light-weight wearable device. Results: The results over the MIT-BIH arrhythmia benchmark database demonstrate that the proposed solution achieves a superior classification performance than most of the state-of-the-art methods for the detection of ventricular ectopic beats and supraventricular ectopic beats. Conclusion: Besides the speed and computational efficiency achieved, once a dedicated CNN is trained for an individual patient, it can solely be used to classify his/her long ECG records such as Holter registers in a fast and accurate manner. Significance: Due to its simple and parameter invariant nature, the proposed system is highly generic, and, thus, applicable to any ECG dataset.

A Dataset for Breast Cancer Histopathological Image Classification

Abstract: Today, medical image analysis papers require solid experiments to prove the usefulness of proposed methods. However, experiments are often performed on data selected by the researchers, which may come from different institutions, scanners, and populations. Different evaluation measures may be used, making it difficult to compare the methods. In this paper, we introduce a dataset of 7909 breast cancer histopathology images acquired on 82 patients, which is now publicly available from http://web.inf.ufpr.br/vri/breast-cancer-database . The dataset includes both benign and malignant images. The task associated with this dataset is the automated classification of these images in two classes, which would be a valuable computer-aided diagnosis tool for the clinician. In order to assess the difficulty of this task, we show some preliminary results obtained with state-of-the-art image classification systems. The accuracy ranges from 80% to 85%, showing room for improvement is left. By providing this dataset and a standardized evaluation protocol to the scientific community, we hope to gather researchers in both the medical and the machine learning field to advance toward this clinical application.

Full-Body Musculoskeletal Model for Muscle-Driven Simulation of Human Gait

Abstract: Objective: Musculoskeletal models provide a non-invasive means to study human movement and predict the effects of interventions on gait. Our goal was to create an open-source 3-D musculoskeletal model with high-fidelity representations of the lower limb musculature of healthy young individuals that can be used to generate accurate simulations of gait. Methods: Our model includes bony geometry for the full body, 37 degrees of freedom to define joint kinematics, Hill-type models of 80 muscle-tendon units actuating the lower limbs, and 17 ideal torque actuators driving the upper body. The model's musculotendon parameters are derived from previous anatomical measurements of 21 cadaver specimens and magnetic resonance images of 24 young healthy subjects. We tested the model by evaluating its computational time and accuracy of simulations of healthy walking and running. Results: Generating muscle-driven simulations of normal walking and running took approximately 10 minutes on a typical desktop computer. The differences between our muscle-generated and inverse dynamics joint moments were within 3% (RMSE) of the peak inverse dynamics joint moments in both walking and running, and our simulated muscle activity showed qualitative agreement with salient features from experimental electromyography data. Conclusion: These results suggest that our model is suitable for generating muscle-driven simulations of healthy gait. We encourage other researchers to further validate and apply the model to study other motions of the lower extremity. Significance: The model is implemented in the open-source software platform OpenSim. The model and data used to create and test the simulations are freely available at https://simtk.org/home/full_body/ , allowing others to reproduce these results and create their own simulations.

Photoplethysmography Revisited: From Contact to Noncontact, From Point to Imaging

Abstract: Photoplethysmography (PPG) is a noninvasive optical technique for detecting microvascular blood volume changes in tissues. Its ease of use, low cost and convenience make it an attractive area of research in the biomedical and clinical communities. Nevertheless, its single spot monitoring and the need to apply a PPG sensor directly to the skin limit its practicality in situations such as perfusion mapping and healing assessments or when free movement is required. The introduction of fast digital cameras into clinical imaging monitoring and diagnosis systems, the desire to reduce the physical restrictions, and the possible new insights that might come from perfusion imaging and mapping inspired the evolution of the conventional PPG technology to imaging PPG (IPPG). IPPG is a noncontact method that can detect heart-generated pulse waves by means of peripheral blood perfusion measurements. Since its inception, IPPG has attracted significant public interest and provided opportunities to improve personal healthcare. This study presents an overview of the wide range of IPPG systems currently being introduced along with examples of their application in various physiological assessments. We believe that the widespread acceptance of IPPG is happening, and it will dramatically accelerate the promotion of this healthcare model in the near future.

Logistic Regression-HSMM-Based Heart Sound Segmentation

Abstract: The identification of the exact positions of the first and second heart sounds within a phonocardiogram (PCG), or heart sound segmentation, is an essential step in the automatic analysis of heart sound recordings, allowing for the classification of pathological events. While threshold-based segmentation methods have shown modest success, probabilistic models, such as hidden Markov models, have recently been shown to surpass the capabilities of previous methods. Segmentation performance is further improved when a priori information about the expected duration of the states is incorporated into the model, such as in a hidden semi-Markov model (HSMM). This paper addresses the problem of the accurate segmentation of the first and second heart sound within noisy real-world PCG recordings using an HSMM, extended with the use of logistic regression for emission probability estimation. In addition, we implement a modified Viterbi algorithm for decoding the most likely sequence of states, and evaluated this method on a large dataset of 10 172 s of PCG recorded from 112 patients (including 12 181 first and 11 627 second heart sounds). The proposed method achieved an average $F_{1}$ score of 95.63 $\,\pm \,$ 0.85%, while the current state of the art achieved 86.28 $\pm \,$ 1.55% when evaluated on unseen test recordings. The greater discrimination between states afforded using logistic regression as opposed to the previous Gaussian distribution-based emission probability estimation as well as the use of an extended Viterbi algorithm allows this method to significantly outperform the current state-of-the-art method based on a two-sided paired t-test.

cvxEDA: A Convex Optimization Approach to Electrodermal Activity Processing

Abstract: Goal: This paper reports on a novel algorithm for the analysis of electrodermal activity (EDA) using methods of convex optimization EDA can be considered as one of the most common observation channels of sympathetic nervous system activity, and manifests itself as a change in electrical properties of the skin, such as skin conductance (SC) Methods: The proposed model describes SC as the sum of three terms: the phasic component, the tonic component, and an additive white Gaussian noise term incorporating model prediction errors as well as measurement errors and artifacts This model is physiologically inspired and fully explains EDA through a rigorous methodology based on Bayesian statistics, mathematical convex optimization, and sparsity Results: The algorithm was evaluated in three different experimental sessions to test its robustness to noise, its ability to separate and identify stimulus inputs, and its capability of properly describing the activity of the autonomic nervous system in response to strong affective stimulation Significance: Results are very encouraging, showing good performance of the proposed method and suggesting promising future applicability, eg, in the field of affective computing

Scalable High-Performance Image Registration Framework by Unsupervised Deep Feature Representations Learning

Abstract: Feature selection is a critical step in deformable image registration. In particular, selecting the most discriminative features that accurately and concisely describe complex morphological patterns in image patches improves correspondence detection, which in turn improves image registration accuracy. Furthermore, since more and more imaging modalities are being invented to better identify morphological changes in medical imaging data, the development of deformable image registration method that scales well to new image modalities or new image applications with little to no human intervention would have a significant impact on the medical image analysis community. To address these concerns, a learning-based image registration framework is proposed that uses deep learning to discover compact and highly discriminative features upon observed imaging data. Specifically, the proposed feature selection method uses a convolutional stacked autoencoder to identify intrinsic deep feature representations in image patches. Since deep learning is an unsupervised learning method, no ground truth label knowledge is required. This makes the proposed feature selection method more flexible to new imaging modalities since feature representations can be directly learned from the observed imaging data in a very short amount of time. Using the LONI and ADNI imaging datasets, image registration performance was compared to two existing state-of-the-art deformable image registration methods that use handcrafted features. To demonstrate the scalability of the proposed image registration framework, image registration experiments were conducted on 7.0-T brain MR images. In all experiments, the results showed that the new image registration framework consistently demonstrated more accurate registration results when compared to state of the art.

A Novel Algorithm for Remote Photoplethysmography: Spatial Subspace Rotation

Abstract: In this paper, we propose a conceptually novel algorithm, namely “Spatial Subspace Rotation” (2SR), that improves the robustness of remote photoplethysmography. Based on the assumption of 1) spatially redundant pixel-sensors of a camera, and 2) a well-defined skin mask, our core idea is to estimate a spatial subspace of skin-pixels and measure its temporal rotation for pulse extraction, which does not require skin-tone or pulse-related priors in contrast to existing algorithms. The proposed algorithm is thoroughly assessed on a benchmark dataset containing 54 videos, which includes challenges of various skin-tones, body-motions in complex illuminance conditions, and pulse-rate recovery after exercise. The experimental results show that given a well-defined skin mask, 2SR outperforms the popular ICA-based approach and two state-of-the-art algorithms (CHROM and PBV). When comparing the pulse frequency spectrum, 2SR improves on average the SNR of ICA by 2.22 dB, CHROM by 1.56 dB, and PBV by 1.95 dB. When comparing the instant pulse-rate, 2SR improves on average the Pearson correlation and precision of ICA by 47% and 65%, CHROM by 22% and 23%, and PBV by 21% and 39%. ANOVA confirms the significant improvement of 2SR in peak-to-peak accuracy. The proposed 2SR algorithm is very simple to use and extend, i.e., the implementation only requires a few lines MATLAB code.

EEG Source Imaging Enhances the Decoding of Complex Right-Hand Motor Imagery Tasks

Abstract: Goal: Sensorimotor-based brain–computer interfaces (BCIs) have achieved successful control of real and virtual devices in up to three dimensions; however, the traditional sensor-based paradigm limits the intuitive use of these systems. Many control signals for state-of-the-art BCIs involve imagining the movement of body parts that have little to do with the output command, revealing a cognitive disconnection between the user's intent and the action of the end effector. Therefore, there is a need to develop techniques that can identify with high spatial resolution the self-modulated neural activity reflective of the actions of a helpful output device. Methods: We extend previous EEG source imaging (ESI) work to decoding natural hand/wrist manipulations by applying a novel technique to classifying four complex motor imaginations of the right hand: flexion, extension, supination, and pronation. Results: We report an increase of up to 18.6% for individual task classification and 12.7% for overall classification using the proposed ESI approach over the traditional sensor-based method. Conclusion: ESI is able to enhance BCI performance of decoding complex right-hand motor imagery tasks. Significance: This study may lead to the development of BCI systems with naturalistic and intuitive motor imaginations, thus facilitating broad use of noninvasive BCIs.

Continuous Cuffless Blood Pressure Estimation Using Pulse Transit Time and Photoplethysmogram Intensity Ratio

Abstract: Pulse transit time (PTT) has attracted much interest for cuffless blood pressure (BP) measurement. However, its limited accuracy is one of the main problems preventing its widespread acceptance. Arterial BP oscillates mainly at high frequency (HF) because of respiratory activity, and at low frequency (LF) because of vasomotor tone. Prior studies suggested that PTT can track BP variation in HF range, but was inadequate to follow the LF variation, which is probably the main reason for its unsatisfactory accuracy. This paper presents a new indicator, the photoplethysmogram intensity ratio (PIR), which can be affected by changes in the arterial diameter, and, thus, trace the LF variation of BP. Spectral analysis of BP, PTT, PIR, and respiratory signal confirmed that PTT was related to BP in HF at the respiratory frequency, while PIR was associated with BP in LF range. We, therefore, develop a novel BP estimation algorithm by using both PTT and PIR. The proposed algorithm was validated on 27 healthy subjects with continuous Finapres BP as reference. The results showed that the mean ± standard deviation (SD) for the estimated systolic, diastolic, and mean BP with the proposed method against reference were $-0.37 \pm 5.21$ , $-0.08 \pm 4.06$ , $-0.18 \pm 4.13$ mmHg, and mean absolute difference (MAD) were 4.09, 3.18, 3.18 mmHg, respectively. Furthermore, the proposed method outperformed the two most cited PTT algorithms for about 2 mmHg in SD and MAD. These results demonstrated that the proposed BP model using PIR and PTT can estimate continuous BP with improved accuracy.

Fast Multiclass Dictionaries Learning With Geometrical Directions in MRI Reconstruction

Abstract: Objective: Improve the reconstructed image with fast and multiclass dictionaries learning when magnetic resonance imaging is accelerated by undersampling the k-space data. Methods: A fast orthogonal dictionary learning method is introduced into magnetic resonance image reconstruction to provide adaptive sparse representation of images. To enhance the sparsity, image is divided into classified patches according to the same geometrical direction and dictionary is trained within each class. A new sparse reconstruction model with the multiclass dictionaries is proposed and solved using a fast alternating direction method of multipliers. Results: Experiments on phantom and brain imaging data with acceleration factor up to 10 and various undersampling patterns are conducted. The proposed method is compared with state-of-the-art magnetic resonance image reconstruction methods. Conclusion: Artifacts are better suppressed and image edges are better preserved than the compared methods. Besides, the computation of the proposed approach is much faster than the typical K-SVD dictionary learning method in magnetic resonance image reconstruction. Significance: The proposed method can be exploited in undersampled magnetic resonance imaging to reduce data acquisition time and reconstruct images with better image quality.

Close-Packed Silicon Microelectrodes for Scalable Spatially Oversampled Neural Recording

Abstract: Objective: Neural recording electrodes are important tools for understanding neural codes and brain dynamics. Neural electrodes that are closely packed, such as in tetrodes, enable spatial oversampling of neural activity, which facilitates data analysis. Here we present the design and implementation of close-packed silicon microelectrodes to enable spatially oversampled recording of neural activity in a scalable fashion. Methods: Our probes are fabricated in a hybrid lithography process, resulting in a dense array of recording sites connected to submicron dimension wiring. Results: We demonstrate an implementation of a probe comprising 1000 electrode pads, each 9 × 9 μm, at a pitch of 11 μm. We introduce design automation and packaging methods that allow us to readily create a large variety of different designs. Significance: We perform neural recordings with such probes in the live mammalian brain that illustrate the spatial oversampling potential of closely packed electrode sites.

An Early Clinical Study of Time-Domain Microwave Radar for Breast Health Monitoring

Abstract: This study reports on monthly scans of healthy patient volunteers with the clinical prototype of a microwave imaging system. The system uses time-domain measurements, and incorporates a multistatic radar approach to imaging. It operates in the 2–4 GHz range and contains 16 wideband sensors embedded in a hemispherical dielectric radome. The system has been previously tested on tissue phantoms in controlled experiments. With this system prototype, we scanned 13 patients (26 breasts) over an eight-month period, collecting a total of 342 breast scans. The goal of the study described in this paper was to investigate how the system measurements are impacted by multiple factors that are unavoidable in monthly monitoring of human subjects. These factors include both biological variability (e.g., tissue variations due to hormonal changes or weight gain) and measurement variability (e.g., inconsistencies in patient positioning, system noise). For each patient breast, we process the results of the monthly scans to assess the variability in both the raw measured signals and in the generated images. The significance of this study is that it quantifies how much variability should be anticipated when conducting microwave breast imaging of a healthy patient over a longer period. This is an important step toward establishing the feasibility of the microwave radar imaging system for frequent monitoring of breast health.

Subspace Regularized Sparse Multitask Learning for Multiclass Neurodegenerative Disease Identification

Abstract: The high feature-dimension and low sample-size problem is one of the major challenges in the study of computer-aided Alzheimer's disease (AD) diagnosis. To circumvent this problem, feature selection and subspace learning have been playing core roles in the literature. Generally, feature selection methods are preferable in clinical applications due to their ease for interpretation, but subspace learning methods can usually achieve more promising results. In this paper, we combine two different methodological approaches to discriminative feature selection in a unified framework. Specifically, we utilize two subspace learning methods, namely, linear discriminant analysis and locality preserving projection, which have proven their effectiveness in a variety of fields, to select class-discriminative and noise-resistant features. Unlike previous methods in neuroimaging studies that mostly focused on a binary classification, the proposed feature selection method is further applicable for multiclass classification in AD diagnosis. Extensive experiments on the Alzheimer's disease neuroimaging initiative dataset showed the effectiveness of the proposed method over other state-of-the-art methods.

An Obstructive Sleep Apnea Detection Approach Using a Discriminative Hidden Markov Model From ECG Signals

Abstract: Obstructive sleep apnea (OSA) syndrome is a common sleep disorder suffered by an increasing number of people worldwide. As an alternative to polysomnography (PSG) for OSA diagnosis, the automatic OSA detection methods used in the current practice mainly concentrate on feature extraction and classifier selection based on collected physiological signals. However, one common limitation in these methods is that the temporal dependence of signals are usually ignored, which may result in critical information loss for OSA diagnosis. In this study, we propose a novel OSA detection approach based on ECG signals by considering temporal dependence within segmented signals. A discriminative hidden Markov model (HMM) and corresponding parameter estimation algorithms are provided. In addition, subject-specific transition probabilities within the model are employed to characterize the subject-to-subject differences of potential OSA patients. To validate our approach, 70 recordings obtained from the Physionet Apnea-ECG database were used. Accuracies of 97.1% for per-recording classification and 86.2% for per-segment OSA detection with satisfactory sensitivity and specificity were achieved. Compared with other existing methods that simply ignore the temporal dependence of signals, the proposed HMM-based detection approach delivers more satisfactory detection performance and could be extended to other disease diagnosis applications.

Cutaneous Feedback of Fingertip Deformation and Vibration for Palpation in Robotic Surgery

Abstract: Despite its expected clinical benefits, current teleoperated surgical robots do not provide the surgeon with haptic feedback largely because grounded forces can destabilize the system's closed-loop controller. This paper presents an alternative approach that enables the surgeon to feel fingertip contact deformations and vibrations while guaranteeing the teleoperator's stability. We implemented our cutaneous feedback solution on an Intuitive Surgical da Vinci Standard robot by mounting a SynTouch BioTac tactile sensor to the distal end of a surgical instrument and a custom cutaneous display to the corresponding master controller. As the user probes the remote environment, the contact deformations, dc pressure, and ac pressure (vibrations) sensed by the BioTac are directly mapped to input commands for the cutaneous device's motors using a model-free algorithm based on look-up tables. The cutaneous display continually moves, tilts, and vibrates a flat plate at the operator's fingertip to optimally reproduce the tactile sensations experienced by the BioTac. We tested the proposed approach by having eighteen subjects use the augmented da Vinci robot to palpate a heart model with no haptic feedback, only deformation feedback, and deformation plus vibration feedback. Fingertip deformation feedback significantly improved palpation performance by reducing the task completion time, the pressure exerted on the heart model, and the subject's absolute error in detecting the orientation of the embedded plastic stick. Vibration feedback significantly improved palpation performance only for the seven subjects who dragged the BioTac across the model, rather than pressing straight into it.

Fabric-Based Wearable Dry Electrodes for Body Surface Biopotential Recording

Abstract: A flexible and conformable dry electrode design on nonwoven fabrics is examined as a sensing platform for biopotential measurements. Due to limitations of commercial wet electrodes (e.g., shelf life, skin irritation), dry electrodes are investigated as the potential candidates for long-term monitoring of ECG signals. Multilayered dry electrodes are fabricated by screen printing of Ag/AgCl conductive inks on flexible nonwoven fabrics. This study focuses on the investigation of skin–electrode interface, form factor design, electrode body placement of printed dry electrodes for a wearable sensing platform. ECG signals obtained with dry and wet electrodes are comparatively studied as a function of body posture and movement. Experimental results show that skin-electrode impedance is influenced by printed electrode area, skin–electrode interface material, and applied pressure. The printed electrode yields comparable ECG signals to wet electrodes, and the QRS peak amplitude of ECG signal is dependent on printed electrode area and electrode on body spacing. Overall, fabric-based printed dry electrodes present an inexpensive health monitoring platform solution for mobile wearable electronics applications by fulfilling user comfort and wearability.

Fully Textile, PEDOT:PSS Based Electrodes for Wearable ECG Monitoring Systems

Abstract: Goal: To evaluate a novel kind of textile electrodes based on woven fabrics treated with PEDOT:PSS, through an easy fabrication process, testing these electrodes for biopotential recordings. Methods: Fabrication is based on raw fabric soaking in PEDOT:PSS using a second dopant, squeezing and annealing. The electrodes have been tested on human volunteers, in terms of both skin contact impedance and quality of the ECG signals recorded at rest and during physical activity (power spectral density, baseline wandering, QRS detectability, and broadband noise). Results: The electrodes are able to operate in both wet and dry conditions. Dry electrodes are more prone to noise artifacts, especially during physical exercise and mainly due to the unstable contact between the electrode and the skin. Wet (saline) electrodes present a stable and reproducible behavior, which is comparable or better than that of traditional disposable gelled Ag/AgCl electrodes. Conclusion: The achieved results reveal the capability of this kind of electrodes to work without the electrolyte, providing a valuable interface with the skin, due to mixed electronic and ionic conductivity of PEDOT:PSS. These electrodes can be effectively used for acquiring ECG signals. Significance: Textile electrodes based on PEDOT:PSS represent an important milestone in wearable monitoring, as they present an easy and reproducible fabrication process, very good performance in wet and dry (at rest) conditions and a superior level of comfort with respect to textile electrodes proposed so far. This paves the way to their integration into smart garments.

MAPS: A Quantitative Radiomics Approach for Prostate Cancer Detection

Abstract: This paper presents a quantitative radiomics feature model for performing prostate cancer detection using multiparametric MRI (mpMRI). It incorporates a novel tumor candidate identification algorithm to efficiently and thoroughly identify the regions of concern and constructs a comprehensive radiomics feature model to detect tumorous regions. In contrast to conventional automated classification schemes, this radiomics-based feature model aims to ground its decisions in a way that can be interpreted and understood by the diagnostician. This is done by grouping features into high-level feature categories which are already used by radiologists to diagnose prostate cancer: Morphology, Asymmetry, Physiology, and Size (MAPS), using biomarkers inspired by the PI-RADS guidelines for performing structured reporting on prostate MRI. Clinical mpMRI data were collected from 13 men with histology-confirmed prostate cancer and labeled by an experienced radiologist. These annotated data were used to train classifiers using the proposed radiomics-driven feature model in order to evaluate the classification performance. The preliminary experimental results indicated that the proposed model outperformed each of its constituent feature groups as well as a comparable conventional mpMRI feature model. A further validation of the proposed algorithm will be conducted using a larger dataset as future work.

Chronic In Vivo Evaluation of PEDOT/CNT for Stable Neural Recordings

Abstract: Objective: Subcellular-sized chronically implanted recording electrodes have demonstrated significant improvement in single unit (SU) yield over larger recording probes. Additional work expands on this initial success by combining the subcellular fiber-like lattice structures with the design space versatility of silicon microfabrication to further improve the signal-to-noise ratio, density of electrodes, and stability of recorded units over months to years. However, ultrasmall microelectrodes present very high impedance, which must be lowered for SU recordings. While poly(3,4-ethylenedioxythiophene) (PEDOT) doped with polystyrene sulfonate (PSS) coating have demonstrated great success in acute to early-chronic studies for lowering the electrode impedance, concern exists over long-term stability. Here, we demonstrate a new blend of PEDOT doped with carboxyl functionalized multiwalled carbon nanotubes (CNTs), which shows dramatic improvement over the traditional PEDOT/PSS formula. Methods: Lattice style subcellular electrode arrays were fabricated using previously established method. PEDOT was polymerized with carboxylic acid functionalized carbon nanotubes onto high-impedance (8.0 ± 0.1 MΩ: M ± S.E.) 250-μm2 gold recording sites. Results: PEDOT/CNT-coated subcellular electrodes demonstrated significant improvement in chronic spike recording stability over four months compared to PEDOT/PSS recording sites. Conclusion: These results demonstrate great promise for subcellular-sized recording and stimulation electrodes and long-term stability. Significance: This project uses leading-edge biomaterials to develop chronic neural probes that are small (subcellular) with excellent electrical properties for stable long-term recordings. High-density ultrasmall electrodes combined with advanced electrode surface modification are likely to make significant contributions to the development of long-term (permanent), high quality, and selective neural interfaces.

Evaluation of Six Registration Methods for the Human Abdomen on Clinically Acquired CT

Abstract: Objective: This work evaluates current 3-D image registration tools on clinically acquired abdominal computed tomography (CT) scans. Methods: Thirteen abdominal organs were manually labeled on a set of 100 CT images, and the 100 labeled images (i.e., atlases) were pairwise registered based on intensity information with six registration tools (FSL, ANTS-CC, ANTS-QUICK-MI, IRTK, NIFTYREG, and DEEDS). The Dice similarity coefficient (DSC), mean surface distance, and Hausdorff distance were calculated on the registered organs individually. Permutation tests and indifference-zone ranking were performed to examine the statistical and practical significance, respectively. Results: The results suggest that DEEDS yielded the best registration performance. However, due to the overall low DSC values, and substantial portion of low-performing outliers, great care must be taken when image registration is used for local interpretation of abdominal CT. Conclusion: There is substantial room for improvement in image registration for abdominal CT. Significance: All data and source code are available so that innovations in registration can be directly compared with the current generation of tools without excessive duplication of effort.

A Robust Heart Rate Monitoring Scheme Using Photoplethysmographic Signals Corrupted by Intense Motion Artifacts

Abstract: Goal: Although photoplethysmographic (PPG) signals can monitor heart rate (HR) quite conveniently in hospital environments, trying to incorporate them during fitness programs poses a great challenge, since in these cases, the signals are heavily corrupted by motion artifacts. Methods: In this paper, we present a novel signal processing framework which utilizes two channel PPG signals and estimates HR in two stages. The first stage eliminates any chances of a runaway error by resorting to an absolute criterion condition based on ensemble empirical mode decomposition. This stage enables the algorithm to depend very little on the previously estimated HR values and to discard the need of an initial resting phase. The second stage, on the other hand, increases the algorithm's robustness against offtrack errors by using recursive least squares filters complemented with an additional novel technique, namely time-domain extraction. Results: Using this framework, an average absolute error of 1.02 beat per minute (BPM) and standard deviation of 1.79 BPM are recorded for 12 subjects performing a run with peak velocities reaching as high as 15 km/h. Conclusion: The performance of this algorithm is found to be better than the other recently reported algorithms in this field such as TROIKA and JOSS. Significance: This method is expected to greatly facilitate the presently available wearable gadgets in HR computation during various physical activities.

Separable Common Spatio-Spectral Patterns for Motor Imagery BCI Systems

Abstract: Objective : Feature extraction is one of the most important steps in any brain–computer interface (BCI) system. In particular, spatio-spectral feature extraction for motor-imagery BCIs (MI-BCI) has been the focus of several works in the past decade. This paper proposes a novel method, called separable common spatio-spectral patterns (SCSSP), for extraction of discriminant spatio-spectral EEG features in MI-BCIs. Methods: Assuming a binary classification problem, SCSSP uses a heteroscedastic matrix-variate Gaussian model for the multiband EEG rhythms, and seeks the spatio-spectral features whose variance is maximized for one brain task and minimized for the other task. Therefore, SCSSP can be considered as a spatio-spectral generalization of the conventional common spatial patterns (CSP) algorithm. Results: The experimental results on two-class and multiclass motor-imagery data from publicly available BCI Competition datasets demonstrate that the proposed computationally efficient method competes closely with filter-bank CSP (FBCSP), and can even outperform the FBCSP if enough training data are available. Furthermore, SCSSP provides us with a simple measure for ranking the discriminant power of extracted spatio-spectral features, which is not possible in FBCSP. Conclusion: The matrix-variate Gaussian assumption allows the SCSSP method to jointly process the EEG data in both spatial and spectral domains. As a result, compared to the similar solutions in the literature such as FBCSP, the proposed SCSSP method requires significantly lower computations. Significance: The proposed computationally efficient spatio-spectral feature extractor is particularly suitable for applications in which the computational power is limited, such as emerging wearable mobile BCI systems.

Neural Data-Driven Musculoskeletal Modeling for Personalized Neurorehabilitation Technologies

Abstract: Objectives: The development of neurorehabilitation technologies requires the profound understanding of the mechanisms underlying an individual's motor ability and impairment. A major factor limiting this understanding is the difficulty of bridging between events taking place at the neurophysiologic level (i.e., motor neuron firings) with those emerging at the musculoskeletal level (i.e. joint actuation), in vivo in the intact moving human. This review presents emerging model-based methodologies for filling this gap that are promising for developing clinically viable technologies. Methods: We provide a design overview of musculoskeletal modeling formulations driven by recordings of neuromuscular activity with a critical comparison to alternative model-free approaches in the context of neurorehabilitation technologies. We present advanced electromyography-based techniques for interfacing with the human nervous system and model-based techniques for translating the extracted neural information into estimates of motor function. Results: We introduce representative application areas where modeling is relevant for accessing neuromuscular variables that could not be measured experimentally. We then show how these variables are used for designing personalized rehabilitation interventions, biologically inspired limbs, and human–machine interfaces. Conclusion: The ability of using electrophysiological recordings to inform biomechanical models enables accessing a broader range of neuromechanical variables than analyzing electrophysiological data or movement data individually. This enables understanding the neuromechanical interplay underlying in vivo movement function, pathology, and robot-assisted motor recovery. Significance: Filling the gap between our understandings of movement neural and mechanical functions is central for addressing one of the major challenges in neurorehabilitation: personalizing current technologies and interventions to an individual's anatomy and impairment.

Epileptic Seizure Prediction Based on Multivariate Statistical Process Control of Heart Rate Variability Features

Abstract: Objective: The present study proposes a new epileptic seizure prediction method through integrating heart rate variability (HRV) analysis and an anomaly monitoring technique. Methods: Because excessive neuronal activities in the preictal period of epilepsy affect the autonomic nervous systems and autonomic nervous function affects HRV, it is assumed that a seizure can be predicted through monitoring HRV. In the proposed method, eight HRV features are monitored for predicting seizures by using multivariate statistical process control, which is a well-known anomaly monitoring method. Results: We applied the proposed method to the clinical data collected from 14 patients. In the collected data, 8 patients had a total of 11 awakening preictal episodes and the total length of interictal episodes was about 57 h. The application results of the proposed method demonstrated that seizures in ten out of eleven awakening preictal episodes could be predicted prior to the seizure onset, that is, its sensitivity was 91%, and its false positive rate was about 0.7 times per hour. Conclusion: This study proposed a new HRV-based epileptic seizure prediction method, and the possibility of realizing an HRV-based epileptic seizure prediction system was shown. Significance: The proposed method can be used in daily life, because the heart rate can be measured easily by using a wearable sensor.

Real-Time Classification of Hand Motions Using Ultrasound Imaging of Forearm Muscles

Abstract: Surface electromyography (sEMG) has been the predominant method for sensing electrical activity for a number of applications involving muscle–computer interfaces, including myoelectric control of prostheses and rehabilitation robots. Ultrasound imaging for sensing mechanical deformation of functional muscle compartments can overcome several limitations of sEMG, including the inability to differentiate between deep contiguous muscle compartments, low signal-to-noise ratio, and lack of a robust graded signal. The objective of this study was to evaluate the feasibility of real-time graded control using a computationally efficient method to differentiate between complex hand motions based on ultrasound imaging of forearm muscles. Dynamic ultrasound images of the forearm muscles were obtained from six able-bodied volunteers and analyzed to map muscle activity based on the deformation of the contracting muscles during different hand motions. Each participant performed 15 different hand motions, including digit flexion, different grips (i.e., power grasp and pinch grip), and grips in combination with wrist pronation. During the training phase, we generated a database of activity patterns corresponding to different hand motions for each participant. During the testing phase, novel activity patterns were classified using a nearest neighbor classification algorithm based on that database. The average classification accuracy was 91%. Real-time image-based control of a virtual hand showed an average classification accuracy of 92%. Our results demonstrate the feasibility of using ultrasound imaging as a robust muscle–computer interface. Potential clinical applications include control of multiarticulated prosthetic hands, stroke rehabilitation, and fundamental investigations of motor control and biomechanics.

Magnesium deficiency and oxidative stress: an update.

Abstract: Magnesium deficiency (MgD) has been shown to impact numerous biological processes at the cellular and molecular levels. In the present review, we discuss the relationship between MgD and oxidative stress (OS). MgD is accompanied by increased levels of OS markers such as lipid, protein and DNA oxidative modification products. Additionally, a relationship was detected between MgD and a weakened antioxidant defence. Different mechanisms associated with MgD are involved in the development and maintenance of OS. These mechanisms include systemic reactions such as inflammation and endothelial dysfunction, as well as changes at the cellular level, such as mitochondrial dysfunction and excessive fatty acid production.

Inherent Structure-Based Multiview Learning With Multitemplate Feature Representation for Alzheimer's Disease Diagnosis

Abstract: Multitemplate-based brain morphometric pattern analysis using magnetic resonance imaging has been recently proposed for automatic diagnosis of Alzheimer's disease (AD) and its prodromal stage (i.e., mild cognitive impairment or MCI). In such methods, multiview morphological patterns generated from multiple templates are used as feature representation for brain images. However, existing multitemplate-based methods often simply assume that each class is represented by a specific type of data distribution (i.e., a single cluster), while in reality, the underlying data distribution is actually not preknown. In this paper, we propose an inherent structure-based multiview leaning method using multiple templates for AD/MCI classification. Specifically, we first extract multiview feature representations for subjects using multiple selected templates and then cluster subjects within a specific class into several subclasses (i.e., clusters) in each view space. Then, we encode those subclasses with unique codes by considering both their original class information and their own distribution information, followed by a multitask feature selection model. Finally, we learn an ensemble of view-specific support vector machine classifiers based on their, respectively, selected features in each view and fuse their results to draw the final decision. Experimental results on the Alzheimer's Disease Neuroimaging Initiative database demonstrate that our method achieves promising results for AD/MCI classification, compared to the state-of-the-art multitemplate-based methods.

Unsupervised Trajectory Segmentation for Surgical Gesture Recognition in Robotic Training

Abstract: Dexterity and procedural knowledge are two critical skills that surgeons need to master to perform accurate and safe surgical interventions. However, current training systems do not allow us to provide an in-depth analysis of surgical gestures to precisely assess these skills. Our objective is to develop a method for the automatic and quantitative assessment of surgical gestures. To reach this goal, we propose a new unsupervised algorithm that can automatically segment kinematic data from robotic training sessions. Without relying on any prior information or model, this algorithm detects critical points in the kinematic data that define relevant spatio-temporal segments. Based on the association of these segments, we obtain an accurate recognition of the gestures involved in the surgical training task. We, then, perform an advanced analysis and assess our algorithm using datasets recorded during real expert training sessions. After comparing our approach with the manual annotations of the surgical gestures, we observe 97.4% accuracy for the learning purpose and an average matching score of 81.9% for the fully automated gesture recognition process. Our results show that trainees workflow can be followed and surgical gestures may be automatically evaluated according to an expert database. This approach tends toward improving training efficiency by minimizing the learning curve.

User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach

Abstract: Goal : To investigate the accuracy of template matching for classifying sports activities using the acceleration signal recorded with a wearable sensor. Methods : A population of 29 normal weight and 19 overweight subjects was recruited to perform eight common sports activities, while body movement was measured using a triaxial accelerometer placed at the wrist. User- and axis-independent acceleration signal templates were automatically extracted to represent each activity category and recognize activity types. Five different similarity measures between example signals and templates were compared: Euclidean distance, dynamic time warping (DTW), derivative DTW, correlation and an innovative index, and combining distance and correlation metrics ( Rce ). Template-based activity recognition was compared to statistical-learning classifiers, such as Naive Bayes, decision tree, logistic regression (LR), and artificial neural network (ANN) trained using time- and frequency-domain signal features. Each algorithm was tested on data from a holdout group of 15 normal weight and 19 overweight subjects. Results : The Rce index outperformed other template-matching metrics by achieving recognition rate above 80% for the majority of the activities. Template matching showed robust classification accuracy when tested on unseen data and in case of limited training examples. LR and ANN achieved the highest overall recognition accuracy $\sim$ 85% but showed to be more vulnerable to misclassification error than template matching on overweight subjects’ data. Conclusion : Template matching can be used to classify sports activities using the wrist acceleration signal. Significance : Automatically extracted template prototypes from the acceleration signal may be used to enhance accuracy and generalization properties of statistical-learning classifiers.