Showing papers in "IEEE Transactions on Biomedical Engineering in 2015"

Wound dressings – a review

Abstract: Wound healing is a dynamic and complex process which requires suitable environment to promote healing process. With the advancement in technology, more than 3000 products have been developed to treat different types of wounds by targeting various aspects of healing process. The present review traces the history of dressings from its earliest inception to the current status and also discusses the advantage and limitations of the dressing materials.

Toward Ubiquitous Blood Pressure Monitoring via Pulse Transit Time: Theory and Practice.

Abstract: Ubiquitous blood pressure (BP) monitoring is needed to improve hypertension detection and control and is becoming feasible due to recent technological advances such as in wearable sensing. Pulse transit time (PTT) represents a well-known potential approach for ubiquitous BP monitoring. The goal of this review is to facilitate the achievement of reliable ubiquitous BP monitoring via PTT. We explain the conventional BP measurement methods and their limitations; present models to summarize the theory of the PTT-BP relationship; outline the approach while pinpointing the key challenges; overview the previous work toward putting the theory to practice; make suggestions for best practice and future research; and discuss realistic expectations for the approach.

TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise

Abstract: Heart rate monitoring using wrist-type photoplethysmographic signals during subjects’ intensive exercise is a difficult problem, since the signals are contaminated by extremely strong motion artifacts caused by subjects’ hand movements. So far few works have studied this problem. In this study, a general framework, termed TROIKA, is proposed, which consists of signal decomposiTion for denoising, sparse signal RecOnstructIon for high-resolution spectrum estimation, and spectral peaK trAcking with verification. The TROIKA framework has high estimation accuracy and is robust to strong motion artifacts. Many variants can be straightforwardly derived from this framework. Experimental results on datasets recorded from 12 subjects during fast running at the peak speed of 15 km/h showed that the average absolute error of heart rate estimation was 2.34 beat per minute, and the Pearson correlation between the estimates and the ground truth of heart rate was 0.992. This framework is of great values to wearable devices such as smartwatches which use PPG signals to monitor heart rate for fitness.

Real-Time Neuroimaging and Cognitive Monitoring Using Wearable Dry EEG

Abstract: Goal: We present and evaluate a wearable high-density dry-electrode EEG system and an open-source software framework for online neuroimaging and state classification. Methods: The system integrates a 64-channel dry EEG form factor with wireless data streaming for online analysis. A real-time software framework is applied, including adaptive artifact rejection, cortical source localization, multivariate effective connectivity inference, data visualization, and cognitive state classification from connectivity features using a constrained logistic regression approach (ProxConn). We evaluate the system identification methods on simulated 64-channel EEG data. Then, we evaluate system performance, using ProxConn and a benchmark ERP method, in classifying response errors in nine subjects using the dry EEG system. Results: Simulations yielded high accuracy (AUC = 0.97 ± 0.021) for real-time cortical connectivity estimation. Response error classification using cortical effective connectivity [short-time direct-directed transfer function (sdDTF)] was significantly above chance with similar performance (AUC) for cLORETA $(0.74 \pm 0.09)$ and LCMV $(0.72 \pm 0.08)$ source localization. Cortical ERP-based classification was equivalent to ProxConn for cLORETA $(0.74 \pm 0.16)$ but significantly better for LCMV $(0.82 \pm 0.12)$ . Conclusion: We demonstrated the feasibility for real-time cortical connectivity analysis and cognitive state classification from high-density wearable dry EEG. Significance: This paper is the first validated application of these methods to 64-channel dry EEG. This study addresses a need for robust real-time measurement and interpretation of complex brain activity in the dynamic environment of the wearable setting. Such advances can have broad impact in research, medicine, and brain–computer interfaces. The pipelines are made freely available in the open-source SIFT and BCILAB toolboxes.

Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease

Abstract: The accurate diagnosis of Alzheimer's disease (AD) is essential for patient care and will be increasingly important as disease modifying agents become available, early in the course of the disease. Although studies have applied machine learning methods for the computer-aided diagnosis of AD, a bottleneck in the diagnostic performance was shown in previous methods, due to the lacking of efficient strategies for representing neuroimaging biomarkers. In this study, we designed a novel diagnostic framework with deep learning architecture to aid the diagnosis of AD. This framework uses a zero-masking strategy for data fusion to extract complementary information from multiple data modalities. Compared to the previous state-of-the-art workflows, our method is capable of fusing multimodal neuroimaging features in one setting and has the potential to require less labeled data. A performance gain was achieved in both binary classification and multiclass classification of AD. The advantages and limitations of the proposed framework are discussed.

Adhesive RFID Sensor Patch for Monitoring of Sweat Electrolytes

Abstract: Wearable digital health devices are dominantly found in rigid form factors such as bracelets and pucks. An adhesive radio-frequency identification (RFID) sensor bandage (patch) is reported, which can be made completely intimate with human skin, a distinct advantage for chronological monitoring of biomarkers in sweat. In this demonstration, a commercial RFID chip is adapted with minimum components to allow potentiometric sensing of solutes in sweat, and surface temperature, as read by an Android smartphone app with 96% accuracy at 50 mM Na + (in vitro tests). All circuitry is solder-reflow integrated on a standard Cu/polyimide flexible-electronic layer including an antenna, but while also allowing electroplating for simple integration of exotic metals for sensing electrodes. Optional paper microfluidics wick sweat from a sweat porous adhesive allowing flow to the sensor, or the sensor can be directly contacted to the skin. The wearability of the patch has been demonstrated for up to seven days, and includes a protective textile which provides a feel and appearance similar to a standard Band-Aid. Applications include hydration monitoring, but the basic capability is extendable to other mM ionic solutes in sweat (Cl - , K + , Mg 2+ , NH 4 + , and Zn 2+ ). The design and fabrication of the patch are provided in full detail, as the basic components could be useful in the design of other wearable sensors.

Photoplethysmography-Based Heart Rate Monitoring in Physical Activities via Joint Sparse Spectrum Reconstruction

Abstract: Goal: A new method for heart rate monitoring using photoplethysmography (PPG) during physical activities is proposed. Methods : It jointly estimates the spectra of PPG signals and simultaneous acceleration signals, utilizing the multiple measurement vector model in sparse signal recovery. Due to a common sparsity constraint on spectral coefficients, the method can easily identify and remove the spectral peaks of motion artifact (MA) in the PPG spectra. Thus, it does not need any extra signal processing modular to remove MA as in some other algorithms. Furthermore, seeking spectral peaks associated with heart rate is simplified. Results : Experimental results on 12 PPG datasets sampled at 25 Hz and recorded during subjects’ fast running showed that it had high performance. The average absolute estimation error was 1.28 beat/min and the standard deviation was 2.61 beat/min. Conclusion and Significance : These results show that the method has great potential to be used for PPG-based heart rate monitoring in wearable devices for fitness tracking and health monitoring.

An overview of targeted cancer therapy.

Abstract: Cancer is a multifactorial disease and is one of the leading causes of death worldwide. The contributing factors include specific genetic background, chronic exposure to various environmental stresses and improper diet. All these risk factors lead to the accumulation of molecular changes or mutations in some important proteins in cells which contributes to the initiation of carcinogenesis. Chemotherapy is an effective treatment against cancer but undesirable chemotherapy reactions and the development of resistance to drugs which results in multi-drug resistance (MDR) are the major obstacles in cancer chemotherapy. Strategies which are in practice with limited success include alternative formulations e.g., liposomes, resistance modulation e.g., PSC833, antidotes/toxicity modifiers e.g., ICRF-187 and gene therapy. Targeted therapy is gaining importance due to its specificity towards cancer cells while sparing toxicity to off-target cells. The scope of this review involves the various strategies involved in targeted therapy like-monoclonal antibodies, prodrug, small molecule inhibitors and nano-particulate antibody conjugates.

Epileptic Seizure Classification of EEG Time-Series Using Rational Discrete Short-Time Fourier Transform

Abstract: A system for epileptic seizure detection in electroencephalography (EEG) is described in this paper. One of the challenges is to distinguish rhythmic discharges from nonstationary patterns occurring during seizures. The proposed approach is based on an adaptive and localized time–frequency representation of EEG signals by means of rational functions. The corresponding rational discrete short-time Fourier transform (DSTFT) is a novel feature extraction technique for epileptic EEG data. A multilayer perceptron classifier is fed by the coefficients of the rational DSTFT in order to separate seizure epochs from seizure-free epochs. The effectiveness of the proposed method is compared with several state-of-art feature extraction algorithms used in offline epileptic seizure detection. The results of the comparative evaluations show that the proposed method outperforms competing techniques in terms of classification accuracy. In addition, it provides a compact representation of EEG time-series.

From Wearable Sensors to Smart Implants-–Toward Pervasive and Personalized Healthcare

Abstract: Objective: This paper discusses the evolution of pervasive healthcare from its inception for activity recognition using wearable sensors to the future of sensing implant deployment and data processing. Methods: We provide an overview of some of the past milestones and recent developments, categorized into different generations of pervasive sensing applications for health monitoring. This is followed by a review on recent technological advances that have allowed unobtrusive continuous sensing combined with diverse technologies to reshape the clinical workflow for both acute and chronic disease management. We discuss the opportunities of pervasive health monitoring through data linkages with other health informatics systems including the mining of health records, clinical trial databases, multiomics data integration, and social media. Conclusion: Technical advances have supported the evolution of the pervasive health paradigm toward preventative, predictive, personalized, and participatory medicine. Significance: The sensing technologies discussed in this paper and their future evolution will play a key role in realizing the goal of sustainable healthcare systems.

Exploiting Spatial Redundancy of Image Sensor for Motion Robust rPPG

Abstract: Remote photoplethysmography (rPPG) techniques can measure cardiac activity by detecting pulse-induced color variations on human skin using an RGB camera. State-of-the-art rPPG methods are sensitive to subject body motions (e.g., motion-induced color distortions). This study proposes a novel framework to improve the motion robustness of rPPG. The basic idea of this paper originates from the observation that a camera can simultaneously sample multiple skin regions in parallel, and each of them can be treated as an independent sensor for pulse measurement. The spatial redundancy of an image sensor can thus be exploited to distinguish the pulse signal from motion-induced noise. To this end, the pixel-based rPPG sensors are constructed to estimate a robust pulse signal using motion-compensated pixel-to-pixel pulse extraction, spatial pruning, and temporal filtering. The evaluation of this strategy is not based on a full clinical trial, but on 36 challenging benchmark videos consisting of subjects that differ in gender, skin types, and performed motion categories. Experimental results show that the proposed method improves the SNR of the state-of-the-art rPPG technique from 3.34 to 6.76 dB, and the agreement ( $\pm 1.96\sigma$ ) with instantaneous reference pulse rate from 55% to 80% correct. ANOVA with post hoc comparison shows that the improvement on motion robustness is significant. The rPPG method developed in this study has a performance that is very close to that of the contact-based sensor under realistic situations, while its computational efficiency allows real-time processing on an off-the-shelf computer.

On the Opportunities and Challenges in Microwave Medical Sensing and Imaging

Abstract: Widely used medical imaging systems in clinics currently rely on X-rays, magnetic resonance imaging, ultrasound, computed tomography, and positron emission tomography. The aforementioned technologies provide clinical data with a variety of resolution, implementation cost, and use complexity, where some of them rely on ionizing radiation. Microwave sensing and imaging (MSI) is an alternative method based on nonionizing electromagnetic (EM) signals operating over the frequency range covering hundreds of megahertz to tens of gigahertz. The advantages of using EM signals are low health risk, low cost implementation, low operational cost, ease of use, and user friendliness. Advancements made in microelectronics, material science, and embedded systems make it possible for miniaturization and integration into portable, handheld, mobile devices with networking capability. MSI has been used for tumor detection, blood clot/stroke detection, heart imaging, bone imaging, cancer detection, and localization of in-body RF sources. The fundamental notion of MSI is that it exploits the tissue-dependent dielectric contrast to reconstruct signals and images using radar-based or tomographic imaging techniques. This paper presents a comprehensive overview of the active MSI for various medical applications, for which the motivation, challenges, possible solutions, and future directions are discussed.

A Review of Basic to Clinical Studies of Irreversible Electroporation Therapy

Abstract: The use of irreversible electroporation (IRE) for cancer treatment has increased sharply over the past decade. As a nonthermal therapy, IRE offers several potential benefits over other focal therapies, which include 1) short treatment delivery time, 2) reduced collateral thermal injury, and 3) the ability to treat tumors adjacent to major blood vessels. These advantages have stimulated widespread interest in basic through clinical studies of IRE. For instance, many in vitro and in vivo studies now identify treatment planning protocols (IRE threshold, pulse parameters, etc.), electrode delivery (electrode design, placement, intraoperative imaging methods, etc.), injury evaluation (methods and timing), and treatment efficacy in different cancer models. Therefore, this study reviews the in vitro, translational, and clinical studies of IRE cancer therapy based on major experimental studies particularly within the past decade. Further, this study provides organized data and facts to assist further research, optimization, and clinical applications of IRE.

Accurate Segmentation of Cervical Cytoplasm and Nuclei Based on Multiscale Convolutional Network and Graph Partitioning

Abstract: In this paper, a multiscale convolutional network (MSCN) and graph-partitioning-based method is proposed for accurate segmentation of cervical cytoplasm and nuclei. Specifically, deep learning via the MSCN is explored to extract scale invariant features, and then, segment regions centered at each pixel. The coarse segmentation is refined by an automated graph partitioning method based on the pretrained feature. The texture, shape, and contextual information of the target objects are learned to localize the appearance of distinctive boundary, which is also explored to generate markers to split the touching nuclei. For further refinement of the segmentation, a coarse-to-fine nucleus segmentation framework is developed. The computational complexity of the segmentation is reduced by using superpixel instead of raw pixels. Extensive experimental results demonstrate that the proposed cervical nucleus cell segmentation delivers promising results and outperforms existing methods.

A Novel Algorithm for the Automatic Detection of Sleep Apnea From Single-Lead ECG

Abstract: Goal: This paper presents a methodology for the automatic detection of sleep apnea from single-lead ECG. Methods: It uses two novel features derived from the ECG, and two well-known features in heart rate variability analysis, namely the standard deviation and the serial correlation coefficients of the RR interval time series. The first novel feature uses the principal components of the QRS complexes, and it describes changes in their morphology caused by an increased sympathetic activity during apnea. The second novel feature extracts the information shared between respiration and heart rate using orthogonal subspace projections. Respiratory information is derived from the ECG by means of three state-of-the-art algorithms, which are implemented and compared here. All features are used as input to a least-squares support vector machines classifier, using an RBF kernel. In total, 80 ECG recordings were included in the study. Results: Accuracies of about 85% are achieved on a minute-by-minute basis, for two independent datasets including both hypopneas and apneas together. Separation between apnea and normal recordings is achieved with 100% accuracy. In addition to apnea classification, the proposed methodology determines the contamination level of each ECG minute. Conclusion: The performances achieved are comparable with those reported in the literature for fully automated algorithms. Significance: These results indicate that the use of only ECG sensors can achieve good accuracies in the detection of sleep apnea. Moreover, the contamination level of each ECG segment can be used to automatically detect artefacts, and to highlight segments that require further visual inspection.

Iterative Vessel Segmentation of Fundus Images

Abstract: This paper presents a novel unsupervised iterative blood vessel segmentation algorithm using fundus images. First, a vessel enhanced image is generated by tophat reconstruction of the negative green plane image. An initial estimate of the segmented vasculature is extracted by global thresholding the vessel enhanced image. Next, new vessel pixels are identified iteratively by adaptive thresholding of the residual image generated by masking out the existing segmented vessel estimate from the vessel enhanced image. The new vessel pixels are, then, region grown into the existing vessel, thereby resulting in an iterative enhancement of the segmented vessel structure. As the iterations progress, the number of false edge pixels identified as new vessel pixels increases compared to the number of actual vessel pixels. A key contribution of this paper is a novel stopping criterion that terminates the iterative process leading to higher vessel segmentation accuracy. This iterative algorithm is robust to the rate of new vessel pixel addition since it achieves 93.2–95.35% vessel segmentation accuracy with 0.9577–0.9638 area under ROC curve (AUC) on abnormal retinal images from the STARE dataset. The proposed algorithm is computationally efficient and consistent in vessel segmentation performance for retinal images with variations due to pathology, uneven illumination, pigmentation, and fields of view since it achieves a vessel segmentation accuracy of about 95% in an average time of 2.45, 3.95, and 8 s on images from three public datasets DRIVE, STARE, and CHASE_DB1, respectively. Additionally, the proposed algorithm has more than 90% segmentation accuracy for segmenting peripapillary blood vessels in the images from the DRIVE and CHASE_DB1 datasets.

Inertial Sensor-Based Stride Parameter Calculation From Gait Sequences in Geriatric Patients

Abstract: A detailed and quantitative gait analysis can provide evidence of various gait impairments in elderly people. To provide an objective decision-making basis for gait analysis, simple applicable tests analyzing a high number of strides are required. A mobile gait analysis system, which is mounted on shoes, can fulfill these requirements. This paper presents a method for computing clinically relevant temporal and spatial gait parameters. Therefore, an accelerometer and a gyroscope were positioned laterally below each ankle joint. Temporal gait events were detected by searching for characteristic features in the signals. To calculate stride length , the gravity compensated accelerometer signal was double integrated, and sensor drift was modeled using a piece-wise defined linear function. The presented method was validated using GAITRite-based gait parameters from 101 patients (average age 82.1 years). Subjects performed a normal walking test with and without a wheeled walker. The parameters stride length and stride time showed a correlation of 0.93 and 0.95 between both systems. The absolute error of stride length was 6.26 cm on normal walking test. The developed system as well as the GAITRite showed an increased stride length, when using a four-wheeled walker as walking aid. However, the walking aid interfered with the automated analysis of the GAITRite system, but not with the inertial sensor-based approach. In summary, an algorithm for the calculation of clinically relevant gait parameters derived from inertial sensors is applicable in the diagnostic workup and also during long-term monitoring approaches in the elderly population.

Multiscale Energy and Eigenspace Approach to Detection and Localization of Myocardial Infarction

Abstract: In this paper, a novel technique on a multiscale energy and eigenspace (MEES) approach is proposed for the detection and localization of myocardial infarction (MI) from multilead electrocardiogram (ECG). Wavelet decomposition of multilead ECG signals grossly segments the clinical components at different subbands. In MI, pathological characteristics such as hypercute T-wave, inversion of T-wave, changes in ST elevation, or pathological Q-wave are seen in ECG signals. This pathological information alters the covariance structures of multiscale multivariate matrices at different scales and the corresponding eigenvalues. The clinically relevant components can be captured by eigenvalues. In this study, multiscale wavelet energies and eigenvalues of multiscale covariance matrices are used as diagnostic features. Support vector machines (SVMs) with both linear and radial basis function (RBF) kernel and K-nearest neighbor are used as classifiers. Datasets, which include healthy control, and various types of MI, such as anterior, anteriolateral, anterioseptal, inferior, inferiolateral, and inferioposterio-lateral, from the PTB diagnostic ECG database are used for evaluation. The results show that the proposed technique can successfully detect the MI pathologies. The MEES approach also helps localize different types of MIs. For MI detection, the accuracy, the sensitivity, and the specificity values are 96%, 93%, and 99% respectively. The localization accuracy is 99.58%, using a multiclass SVM classifier with RBF kernel.

A Dynamically Optimized SSVEP Brain–Computer Interface (BCI) Speller

Abstract: The aim of this study was to design a dynamically optimized steady-state visually evoked potential (SSVEP) brain-computer interface (BCI) system with enhanced performance relative to previous SSVEP BCIs in terms of the number of items selectable on the interface, accuracy, and speed. In this approach, the row/column (RC) paradigm was employed in a SSVEP speller to increase the number of items. The target is detected by subsequently determining the row and column coordinates. To improve spelling accuracy, we added a posterior processing after the canonical correlation analysis (CCA) approach to reduce the interfrequency variation between different subjects and named the new signal processing method CCA-RV, and designed a real-time biofeedback mechanism to increase attention on the visual stimuli. To achieve reasonable online spelling speed, both fixed and dynamic approaches for setting the optimal stimulus duration were implemented and compared. Experimental results for 11 subjects suggest that the CCA-RV method and the real-time biofeedback effectively increased accuracy compared with CCA and the absence of real-time feedback, respectively. In addition, both optimization approaches for setting stimulus duration achieved reasonable online spelling performance. However, the dynamic optimization approach yielded a higher practical information transfer rate (PITR) than the fixed optimization approach. The average online PITR achieved by the proposed adaptive SSVEP speller, including the time required for breaks between selections and error correction, was 41.08 bit/min. These results indicate that our BCI speller is promising for use in SSVEP-based BCI applications.

Doppler Radar Fall Activity Detection Using the Wavelet Transform

Abstract: We propose in this paper the use of Wavelet transform (WT) to detect human falls using a ceiling mounted Doppler range control radar. The radar senses any motions from falls as well as nonfalls due to the Doppler effect. The WT is very effective in distinguishing the falls from other activities, making it a promising technique for radar fall detection in nonobtrusive inhome elder care applications. The proposed radar fall detector consists of two stages. The prescreen stage uses the coefficients of wavelet decomposition at a given scale to identify the time locations in which fall activities may have occurred. The classification stage extracts the time-frequency content from the wavelet coefficients at many scales to form a feature vector for fall versus nonfall classification. The selection of different wavelet functions is examined to achieve better performance. Experimental results using the data from the laboratory and real inhome environments validate the promising and robust performance of the proposed detector.

Flexible 16 Antenna Array for Microwave Breast Cancer Detection

Abstract: Radar-based microwave imaging has been widely studied for breast cancer detection in recent times. Sensing dielectric property differences of tissues has been studied over a wide frequency band for this application. We design single- and dual-polarization antennas for wireless ultrawideband breast cancer detection systems using an inhomogeneous multilayer model of the human breast. Antennas made from flexible materials are more easily adapted to wearable applications. Miniaturized flexible monopole and spiral antennas on a 50-μm Kapton polyimide are designed, using a high-frequency structure simulator, to be in contact with biological breast tissues. The proposed antennas are designed to operate in a frequency range of 2–4 GHz (with reflection coefficient (S11) below –10 dB). Measurements show that the flexible antennas have good impedance matching when in different positions with different curvature around the breast. Our miniaturized flexible antennas are 20 mm × 20 mm. Furthermore, two flexible conformal 4 × 4 ultrawideband antenna arrays (single and dual polarization), in a format similar to that of a bra, were developed for a radar-based breast cancer detection system. By using a reflector for the arrays, the penetration of the propagated electromagnetic waves from the antennas into the breast can be improved by factors of 3.3 and 2.6, respectively.

An Ingestible Sensor for Measuring Medication Adherence

Abstract: In this paper, we describe the design and performance of the first integrated-circuit microsensor developed for daily ingestion by patients. The ingestible sensor is a device that allows patients, families, and physicians to measure medication ingestion and adherence patterns in real time, relate pharmaceutical compliance to important physiologic metrics, and take appropriate action in response to a patient's adherence pattern and specific health metrics. The design and theory of operation of the device are presented, along with key in-vitro and in-vivo performance results. The chemical, toxicological, mechanical, and electrical safety tests performed to establish the device's safety profile are described in detail. Finally, aggregate results from multiple clinical trials involving 412 patients and 5656 days of system usage are presented to demonstrate the device's reliability and performance as part of an overall digital health feedback system.

Relationship between Neural Activation and Electric Field Distribution during Deep Brain Stimulation

Abstract: Models and simulations are commonly used to study deep brain stimulation (DBS). Simulated stimulation fields are often defined and visualized by electric field isolevels or volumes of tissue activated (VTA). The aim of the present study was to evaluate the relationship between stimulation field strength as defined by the electric potential V, the electric field E, and the divergence of the electric field $ abla ^2 V$ , and neural activation. Axon cable models were developed and coupled to finite-element DBS models in three-dimensional (3-D). Field thresholds ( $V_{T}$ , $E_{T}$ , and $ abla ^2 V_T $ ) were derived at the location of activation for various stimulation amplitudes (1 to 5 V), pulse widths (30 to 120 μs), and axon diameters (2.0 to 7.5 μm). Results showed that thresholds for $V_{T}$ and $ abla ^2 V_T $ were highly dependent on the stimulation amplitude while $E_{T}$ were approximately independent of the amplitude for large axons. The activation field strength thresholds presented in this study may be used in future studies to approximate the VTA during model-based investigations of DBS without the need of computational axon models.

A Novel EOG/EEG Hybrid Human–Machine Interface Adopting Eye Movements and ERPs: Application to Robot Control

Abstract: This study presents a novel human-machine interface (HMI) based on both electrooculography (EOG) and electroencephalography (EEG). This hybrid interface works in two modes: an EOG mode recognizes eye movements such as blinks, and an EEG mode detects event related potentials (ERPs) like P300. While both eye movements and ERPs have been separately used for implementing assistive interfaces, which help patients with motor disabilities in performing daily tasks, the proposed hybrid interface integrates them together. In this way, both the eye movements and ERPs complement each other. Therefore, it can provide a better efficiency and a wider scope of application. In this study, we design a threshold algorithm that can recognize four kinds of eye movements including blink, wink, gaze, and frown. In addition, an oddball paradigm with stimuli of inverted faces is used to evoke multiple ERP components including P300, N170, and VPP. To verify the effectiveness of the proposed system, two different online experiments are carried out. One is to control a multifunctional humanoid robot, and the other is to control four mobile robots. In both experiments, the subjects can complete tasks effectively by using the proposed interface, whereas the best completion time is relatively short and very close to the one operated by hand.

Automatic Feature Learning to Grade Nuclear Cataracts Based on Deep Learning

Abstract: Goal : Cataracts are a clouding of the lens and the leading cause of blindness worldwide. Assessing the presence and severity of cataracts is essential for diagnosis and progression monitoring, as well as to facilitate clinical research and management of the disease. Methods: Existing automatic methods for cataract grading utilize a predefined set of image features that may provide an incomplete, redundant, or even noisy representation. In this study, we propose a system to automatically learn features for grading the severity of nuclear cataracts from slit-lamp images. Local filters are first acquired through clustering of image patches from lenses within the same grading class. The learned filters are fed into a convolutional neural network, followed by a set of recursive neural networks, to further extract higher order features. With these features, support vector regression is applied to determine the cataract grade. Results: The proposed system is validated on a large population-based dataset of $\text{5378}$ images, where it outperforms the state of the art by yielding with respect to clinical grading a mean absolute error ( $\varepsilon$ ) of $0.304$ , a $70.7\%$ exact integral agreement ratio ( $R_0$ ), an $88.4\%$ decimal grading error $\le 0.5$ ( $R_{e0.5}$ ), and a $99.0\%$ decimal grading error $\le 1.0$ ( $R_{e1.0}$ ). Significance: The proposed method is useful for assisting and improving clinical management of the disease in the context of large-population screening and has the potential to be applied to other eye diseases.

Machine Learning and Decision Support in Critical Care

Abstract: Clinical data management systems typically provide caregiver teams with useful information, derived from large, sometimes highly heterogeneous, data sources that are often changing dynamically. Over the last decade there has been a significant surge in interest in using these data sources, from simply reusing the standard clinical databases for event prediction or decision support, to including dynamic and patient-specific information into clinical monitoring and prediction problems. However, in most cases, commercial clinical databases have been designed to document clinical activity for reporting, liability, and billing reasons, rather than for developing new algorithms. With increasing excitement surrounding “secondary use of medical records” and “Big Data” analytics, it is important to understand the limitations of current databases and what needs to change in order to enter an era of “precision medicine.” This review article covers many of the issues involved in the collection and preprocessing of critical care data. The three challenges in critical care are considered: compartmentalization, corruption, and complexity. A range of applications addressing these issues are covered, including the modernization of static acuity scoring; online patient tracking; personalized prediction and risk assessment; artifact detection; state estimation; and incorporation of multimodal data sources such as genomic and free text data.

A Novel Kalman Filter for Human Motion Tracking With an Inertial-Based Dynamic Inclinometer

Abstract: Goal: Design and development of a linear Kalman filter to create an inertial-based inclinometer targeted to dynamic conditions of motion. Methods: The estimation of the body attitude (i.e., the inclination with respect to the vertical) was treated as a source separation problem to discriminate the gravity and the body acceleration from the specific force measured by a triaxial accelerometer. The sensor fusion between triaxial gyroscope and triaxial accelerometer data was performed using a linear Kalman filter. Wrist-worn inertial measurement unit data from ten participants were acquired while performing two dynamic tasks: 60-s sequence of seven manual activities and 90 s of walking at natural speed. Stereophotogrammetric data were used as a reference. A statistical analysis was performed to assess the significance of the accuracy improvement over state-of-the-art approaches. Results: The proposed method achieved, on an average, a root mean square attitude error of 3.6° and 1.8° in manual activities and locomotion tasks (respectively). The statistical analysis showed that, when compared to few competing methods, the proposed method improved the attitude estimation accuracy. Conclusion: A novel Kalman filter for inertial-based attitude estimation was presented in this study. A significant accuracy improvement was achieved over state-of-the-art approaches, due to a filter design that better matched the basic optimality assumptions of Kalman filtering. Significance: Human motion tracking is the main application field of the proposed method. Accurately discriminating the two components present in the triaxial accelerometer signal is well suited for studying both the rotational and the linear body kinematics.

Holistic Atlases of Functional Networks and Interactions Reveal Reciprocal Organizational Architecture of Cortical Function

Abstract: For decades, it has been largely unknown to what extent multiple functional networks spatially overlap/interact with each other and jointly realize the total cortical function. Here, by developing novel sparse representation of whole-brain fMRI signals and by using the recently publicly released large-scale Human Connectome Project high-quality fMRI data, we show that a number of reproducible and robust functional networks, including both task-evoked and resting state networks, are simultaneously distributed in distant neuroanatomic areas and substantially spatially overlapping with each other, thus forming an initial collection of holistic atlases of functional networks and interactions (HAFNIs). More interestingly, the HAFNIs revealed two distinct patterns of highly overlapped regions and highly specialized regions and exhibited that these two patterns of areas are reciprocally localized, revealing a novel organizational principle of cortical function.

Domain Transfer Learning for MCI Conversion Prediction

Abstract: Machine learning methods have successfully been used to predict the conversion of mild cognitive impairment (MCI) to Alzheimer's disease (AD), by classifying MCI converters (MCI-C) from MCI nonconverters (MCI-NC). However, most existing methods construct classifiers using data from one particular target domain (e.g., MCI), and ignore data in other related domains (e.g., AD and normal control (NC)) that may provide valuable information to improve MCI conversion prediction performance. To address is limitation, we develop a novel domain transfer learning method for MCI conversion prediction, which can use data from both the target domain (i.e., MCI) and auxiliary domains (i.e., AD and NC). Specifically, the proposed method consists of three key components: 1) a domain transfer feature selection component that selects the most informative feature-subset from both target domain and auxiliary domains from different imaging modalities; 2) a domain transfer sample selection component that selects the most informative sample-subset from the same target and auxiliary domains from different data modalities; and 3) a domain transfer support vector machine classification component that fuses the selected features and samples to separate MCI-C and MCI-NC patients. We evaluate our method on 202 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that have MRI, FDG-PET, and CSF data. The experimental results show the proposed method can classify MCI-C patients from MCI-NC patients with an accuracy of 79.4%, with the aid of additional domain knowledge learned from AD and NC.

Human Joint Angle Estimation with Inertial Sensors and Validation with A Robot Arm

Abstract: Traditionally, human movement has been captured primarily by motion capture systems. These systems are costly, require fixed cameras in a controlled environment, and suffer from occlusion. Recently, the availability of low-cost wearable inertial sensors containing accelerometers, gyroscopes, and magnetometers have provided an alternative means to overcome the limitations of motion capture systems. Wearable inertial sensors can be used anywhere, cannot be occluded, and are low cost. Several groups have described algorithms for tracking human joint angles. We previously described a novel approach based on a kinematic arm model and the Unscented Kalman Filter (UKF). Our proposed method used a minimal sensor configuration with one sensor on each segment. This paper reports significant improvements in both the algorithm and the assessment. The new model incorporates gyroscope and accelerometer random drift models, imposes physical constraints on the range of motion for each joint, and uses zero-velocity updates to mitigate the effect of sensor drift. A high-precision industrial robot arm precisely quantifies the performance of the tracker during slow, normal, and fast movements over continuous 15-min recording durations. The agreement between the estimated angles from our algorithm and the high-precision robot arm reference was excellent. On average, the tracker attained an RMS angle error of about $3^\circ$ for all six angles. The UKF performed slightly better than the more common Extended Kalman Filter