Instantaneous measure of EEG channel importance for improved patient-adaptive neonatal seizure detection

A measure of bipolar channel importance is proposed for EEG-based detection of neonatal seizures. The channel weights are computed based on the integrated synchrony of classifier probabilistic outputs for the channels which share a common electrode. These estimated time-varying weights are introduced within a Bayesian probabilistic framework to provide a channel specific and, thus, adaptive seizure classification scheme. Validation results on a clinical dataset of neonatal seizures confirm the utility of the proposed channel weighting for the two patient-independent seizure detectors recently developed by this research group: one based on support vector machines (SVMs) and the other on Gaussian mixture models (GMMs). By exploiting the channel weighting, the receiver operating characteristic (ROC) area can be significantly increased for the most difficult patients, with the average ROC area across 17 patients increased by 22% (relative) for the SVM and by 15% (relative) for the GMM-based detector, respectively. It is shown that the system developed here outperforms the recent published studies in this area.     

心电检测技术及应用

心电图（electrocardiogram,ECG）作为心血管疾病诊断中的一种重要的方法,能为心脏疾病的正确分析、诊断、治疗和监护提供客观指标。ECG是一种重要的心电信号检测技术,它反映心脏兴奋的产生、传导和恢复过程中的生物电变化。心电检测技术是一种安全、无创、准确的检测方法,其广泛应用于临床监测中。本文综述了ECG基础理论、心电检测技术及其在血液透析中的应用,并对心电信号检测技术的发展趋势作了展望。     

Analog seizure detection and performance evaluation

Epilepsy is the most prevalent neurological disorder affecting both adults and children. Over two-and-one-half million individuals in the United States have epilepsy and 25% of them do not respond to drugs. A significant focus of current research efforts is the development of a fully implantable device for real-time seizure detection and automated warning and blockage of seizures. The purpose of this paper is to describe and demonstrate the feasibility of incorporating a novel tool, the percentile tracking filter into a successful, validated seizure detection algorithm to create an analog seizure detection device. We demonstrate, in a small-scale study, that the performance of this analog implementation is statistically similar to a digital implementation of a previously described and successfully validated seizure digital algorithm. This analog implementation can be realized into an application specific integrated circuit that is suitable for a fully implantable device for seizure monitoring, warning and treatment, which is likely to consume very little power, a feature of practical value.     

Automated algorithm for generalized tonic-clonic epileptic seizure onset detection based on sEMG zero-crossing rate

Patients are not able to call for help during a generalized tonic-clonic epileptic seizure. Our objective was to develop a robust generic algorithm for automatic detection of tonic-clonic seizures, based on surface electromyography (sEMG) signals suitable for a portable device. Twenty-two seizures were analyzed from 11 consecutive patients. Our method is based on a high-pass filtering with a cutoff at 150 Hz, and monitoring a count of zero crossings with a hysteresis of ±50 μV . Based on data from one sEMG electrode (on the deltoid muscle), we achieved a sensitivity of 100% with a mean detection latency of 13.7 s, while the rate of false detection was limited to 1 false alarm per 24 h. The overall performance of the presented generic algorithm is adequate for clinical implementation.     

Model-based seizure detection for intracranial EEG recordings

This paper presents a novel model-based patient-specific method for automatic detection of seizures in the intracranial EEG recordings. The proposed method overcomes the complexities in the practical implementation of the patient-specific approach of seizure detection. The method builds a seizure model (set of basis functions) for a priori known seizure (the template seizure pattern), and uses the statistically optimal null filters as a building block for the detection of similar seizures. The process of modeling the template seizure is fully automatic. Overall, the detection method involves the segmentation of the template seizure pattern, rejection of the redundant and noisy segments, extraction of features from the segments to generate a set of models, selection of the best seizure model, and training of the classifier. The trained classifier is used to detect similar seizures in the remaining data. The resulting seizure detection method was evaluated on a total of 304 h of single-channel depth EEG recordings from 14 patients. The system performance is further compared to the Qu-Gotman patient-specific system using the same data. A significant improvement in the proposed system, in terms of specificity, is observed over the compared method.     

Epileptic seizure detection using genetically programmed artificial features

Patient-specific epilepsy seizure detectors were designed based on the genetic programming artificial features algorithm, a general-purpose, methodic algorithm comprised by a genetic programming module and a k-nearest neighbor classifier to create synthetic features. Artificial features are an extension to conventional features, characterized by being computer-coded and may not have a known physical meaning. In this paper, artificial features are constructed from the reconstructed state-space trajectories of the intracranial EEG signals intended to reveal patterns indicative of epileptic seizure onset. The algorithm was evaluated in seven patients and validation experiments were carried out using 730.6 hr of EEG recordings. The results with the artificial features compare favorably with previous benchmark work that used a handcrafted feature. Among other results, 88 out of 92 seizures were detected yielding a low false negative rate of 4.35%.     

Mixed-band wavelet-chaos-neural network methodology for epilepsy and epileptic seizure detection

A novel wavelet-chaos-neural network methodology is presented for classification of electroencephalograms (EEGs) into healthy, ictal, and interictal EEGs. Wavelet analysis is used to decompose the EEG into delta, theta, alpha, beta, and gamma sub-bands. Three parameters are employed for EEG representation: standard deviation (quantifying the signal variance), correlation dimension, and largest Lyapunov exponent (quantifying the non-linear chaotic dynamics of the signal). The classification accuracies of the following techniques are compared: (1) unsupervised k-means clustering; (2) linear and quadratic discriminant analysis; (3) radial basis function neural network; (4) Levenberg-Marquardt backpropagation neural network (LMBPNN). To reduce the computing time and output analysis, the research was performed in two phases: band-specific analysis and mixed-band analysis. In phase two, over 500 different combinations of mixed-band feature spaces consisting of promising parameters from phase one of the research were investigated. It is concluded that all three key components of the wavelet-chaos-neural network methodology are important for improving the EEG classification accuracy. Judicious combinations of parameters and classifiers are needed to accurately discriminate between the three types of EEGs. It was discovered that a particular mixed-band feature space consisting of nine parameters and LMBPNN result in the highest classification accuracy, a high value of 96.7%.     

A hybrid feature extraction and machine learning approaches for epileptic seizure detection

Multidimensional Systems and Signal Processing - Epileptic seizure detection from the brain EEG signals is an essential step for speeding up the diagnosis that assists researchers and medical...     

High-Frequency Electrocardiogram Analyzer

We have developed a microprocessor-based analyzer for processing the high-frequency electrocardiogram. It has a signal band-width of 500 Hz, five times that of the standard clinical ECG. The device is programmed to isolate QRS complexes, to compute their first derivatives, and to dilate the time base so that the high frequency ECG's and their derivatives can be recorded on a restricted-bandwidth hard copy device such as a strip chart recorder or ECG machine. Also, the analyzer interfaces directly to a laboratory computer system for additional signal processing.     

Low-complexity image processing for real-time detection of neonatal clonic seizures

In this paper, we consider a novel low-complexity real-time image-processing-based approach to the detection of neonatal clonic seizures. Our approach is based on the extraction, from a video of a newborn, of an average luminance signal representative of the body movements. Since clonic seizures are characterized by periodic movements of parts of the body (e.g., the limbs), by evaluating the periodicity of the extracted average luminance signal it is possible to detect the presence of a clonic seizure. The periodicity is investigated, through a hybrid autocorrelation-Yin estimation technique, on a per-window basis, where a time window is defined as a sequence of consecutive video frames. While processing is first carried out on a single window basis, we extend our approach to interlaced windows. The performance of the proposed detection algorithm is investigated, in terms of sensitivity and specificity, through receiver operating characteristic curves, considering video recordings of newborns affected by neonatal seizures.     

Data-mining based fault detection

This paper presents a fault-detection method based on the phase space reconstruction and data mining approaches for the complex electronic system. The approach for the phase space reconstruction of chaotic time series is a combination algorithm of multiple autocorrelation and Г-test, by which the quasi-optimal embedding dimension and time delay can be obtained. The data mining algorithm, which calculates the radius of gyration of unit-mass point around the centre of mass in the phase space, can distinguish the fault parameter from the chaotic time series output by the tested system. The experimental results depict that this fault detection method can correctly detect the fault phenomena of electronic system.     

Electrocardiogram Recording with Pasteless Electrodes

Experimentation regarding various aspects of a technique for recording electrocardiographic potentials from unprepared skin, without the use of conventional paste, is described. Because of the relatively high skin-to-electrode impedances encountered without electrolytic paste, high input impedance amplifiers must be utilized for acquisition of the signal. In order to minimize susceptibility to external electrostatic and electromagnetic interference, an inherent problem with high input impedance amplifiers, buffer amplifiers were incorporated directly within the electrode housing. Of the different metals tested, stainless steel proved to be the most stable skin contact material for pasteless operation. The integrated electrode-buffer amplifiers described comply with specifications of the American Heart Association and should prove useful as a direct replacement for conventional paste-type electrodes in existing clinical EKG equipment as well as for long-term applications such as space missions and intensive-care-unit patient monitoring, where frequent attention to the electrodes is inconvenient.     

3D saliency detection based on background detection

Unlike 2D saliency detection, 3D saliency detection can consider the effects of depth and binocular parallax. In this paper, we propose a 3D saliency detection approach based on background detection via depth information. With the aid of the synergism between a color image and the corresponding depth map, our approach can detect the distant background and surfaces with gradual changes in depth. We then use the detected background to predict the potential characteristics of the background regions that are occluded by foreground objects through polynomial fitting; this step imitates the human imagination/envisioning process. Finally, a saliency map is obtained based on the contrast between the foreground objects and the potential background. We compare our approach with 14 state-of-the-art saliency detection methods on three publicly available databases. The proposed model demonstrates good performance and succeeds in detecting and removing backgrounds and surfaces of gradually varying depth on all tested databases.     

Latent Components in the Electrocardiogram

A new decomposition technique useful for representing a set of observed electrocardiograms is presented. This decomposition is different from past techniques in the constraints placed on the component waveforms in that they must be positive and start, stop, and overlap in a prescribed manner. The number of component waveforms is dependent on the maximum error tolerated in the reconstruction of the observed waveforms from the component representation.     

Detection of pseudosinusoidal epileptic seizure segments in the neonatal EEG by cascading a rule-based algorithm with a neural network

This paper presents an approach to detect epileptic seizure segments in the neonatal electroencephalogram (EEG) by characterizing the spectral features of the EEG waveform using a rule-based algorithm cascaded with a neural network. A rule-based algorithm screens out short segments of pseudosinusoidal EEG patterns as epileptic based on features in the power spectrum. The output of the rule-based algorithm is used to train and compare the performance of conventional feedforward neural networks and quantum neural networks. The results indicate that the trained neural networks, cascaded with the rule-based algorithm, improved the performance of the rule-based algorithm acting by itself. The evaluation of the proposed cascaded scheme for the detection of pseudosinusoidal seizure segments reveals its potential as a building block of the automated seizure detection system under development.     

简易心电图仪的设计

为方便人们实时了解心律的变化,根据心电信号特征设计了便携式心电图仪.它采用新型低功耗的16位单片机MSP430F2274作为整个系统的控制核心,利用低噪声、低功耗、共模抑制能力强的仪表放大器INA2331将心电信号放大后通过MAX291CPA进行滤波,最后在液晶上显示心电波形.该心电图仪能实现人机对话和信号的存储与回放,设计简洁,携带方便,经过调试,运行良好,能够达到观察心电信号的目的.     

Gaussian process modeling of EEG for the detection of neonatal seizures

Gaussian process (GP) probabilistic models have attractive advantages over parametric and neural network modeling approaches. They have a small number of tuneable parameters, can be trained on relatively small training sets, and provide a measure of prediction certainty. In this paper, these properties are exploited to develop two methods of highlighting the presence of neonatal seizures from electroencephalograph (EEG) signals. In the first method, the certainty of the GP model prediction is used to indicate the presence of seizures. In the second approach, the hyperparameters of the GP model are used. Tests are carried out with a feature set of ten EEG measures developed from various signal processing techniques. Features are evaluated using a neural network classifier on 51 h of real neonatal EEG. The GP measures, in particular, the prediction certainty approach, produce a high level of performance compared to other modeling methods and methods currently in clinical use for EEG analysis, indicating that they are an important and useful tool for the real-time detection of neonatal seizures.     

Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection.

A novel principal component analysis (PCA)-enhanced cosine radial basis function neural network classifier is presented. The two-stage classifier is integrated with the mixed-band wavelet-chaos methodology, developed earlier by the authors, for accurate and robust classification of electroencephalogram (EEGs) into healthy, ictal, and interictal EEGs. A nine-parameter mixed-band feature space discovered in previous research for effective EEG representation is used as input to the two-stage classifier. In the first stage, PCA is employed for feature enhancement. The rearrangement of the input space along the principal components of the data improves the classification accuracy of the cosine radial basis function neural network (RBFNN) employed in the second stage significantly. The classification accuracy and robustness of the classifier are validated by extensive parametric and sensitivity analysis. The new wavelet-chaos-neural network methodology yields high EEG classification accuracy (96.6%) and is quite robust to changes in training data with a low standard deviation of 1.4%. For epilepsy diagnosis, when only normal and interictal EEGs are considered, the classification accuracy of the proposed model is 99.3%. This statistic is especially remarkable because even the most highly trained neurologists do not appear to be able to detect interictal EEGs more than 80% of the times.     

Automated epileptic seizure waveform detection method based on the feature of the mean slope of wavelet coefficient counts using a hidden Markov model and EEG signals

Long‐term electroencephalography (EEG) monitoring is time‐consuming, and requires experts to interpret EEG signals to detect seizures in patients. In this paper, we propose a novel automated method called adaptive slope of wavelet coefficient counts over various thresholds (ASCOT) to classify patient episodes as seizure waveforms. ASCOT involves extracting the feature matrix by calculating the mean slope of wavelet coefficient counts over various thresholds in each frequency subband. We validated our method using our own database and a public database to avoid overtuning. The experimental results show that the proposed method achieved a reliable and promising accuracy in both our own database (98.93%) and the public database (99.78%). Finally, we evaluated the performance of the method considering various window sizes. In conclusion, the proposed method achieved a reliable seizure detection performance with a short‐term window size. Therefore, our method can be utilized to interpret long‐term EEG results and detect momentary seizure waveforms in diagnostic systems.     

Image forgery detection algorithm based on U-shaped detection network

Aiming at the defects of traditional image tampering detection algorithm relying on single image attribute,low applicability and current high time-complexity detection algorithm based on deep learning,an U-shaped detection network image forgery detection algorithm was proposed.Firstly,the multi-stage feature information in the image by using the continuous convolution layers and the max-pooling layers was extracted by U-shaped detection network,and then the obtained feature information to the resolution of the input image through the upsampling operation was restored.At the same time,in order to ensure higher detection accuracy while extracting high-level semantic information of the image,the output features of each stage in U-shaped detection network would be merged with the corresponding output features through the upsampling layer.Further the hidden feature information between tampered and un-tampered regions in the image upon the characteristics of the general network was explored by U-shaped detection network,which could be realized quickly by using its end-to-end network structure and extracting the attributes of strong correlation information among image contexts that could ensure high-precision detection results.Finally,the conditional random field was used to optimize the output of the U-shaped detection network to obtain a more exact detection results.The experimental results show that the proposed algorithm outperforms those traditional forgery detection algorithms based on single image attribute and the current deep learning-based detection algorithm,and has good robustness.