Correlation dimension based lossless compression of EEG signals

Transmission of long duration EEG signals without loss of information is essential for telemedicine based applications. In this work, a lossless compression scheme for EEG signals based on neural network predictors using the concept of correlation dimension (CD) is proposed. EEG signals which are considered as irregular time series of chaotic processes can be characterized by the non-linear dynamic parameter CD which is a measure of the correlation among the EEG samples. The EEG samples are first divided into segments of 1 s duration and for each segment, the value of CD is calculated. Blocks of EEG samples are then constructed such that each block contains segments with closer CD values. By arranging the EEG samples in this fashion, the accuracy of the predictor is improved as it makes use of highly correlated samples. As a result, the magnitude of the prediction error decreases leading to less number of bits for transmission. Experiments are conducted using EEG signals recorded under different physiological conditions. Different neural network predictors as well as classical predictors are considered. Experimental results show that the proposed CD based preprocessing scheme improves the compression performance of the predictors significantly.     

Enhancing biomedical text summarization using semantic relation extraction

Automatic text summarization for a biomedical concept can help researchers to get the key points of a certain topic from large amount of biomedical literature efficiently. In this paper, we present a method for generating text summary for a given biomedical concept, e.g., H1N1 disease, from multiple documents based on semantic relation extraction. Our approach includes three stages: 1) We extract semantic relations in each sentence using the semantic knowledge representation tool SemRep. 2) We develop a relation-level retrieval method to select the relations most relevant to each query concept and visualize them in a graphic representation. 3) For relations in the relevant set, we extract informative sentences that can interpret them from the document collection to generate text summary using an information retrieval based method. Our major focus in this work is to investigate the contribution of semantic relation extraction to the task of biomedical text summarization. The experimental results on summarization for a set of diseases show that the introduction of semantic knowledge improves the performance and our results are better than the MEAD system, a well-known tool for text summarization.     

复杂度脑电地形图研究

脑电地形图是近年脑电分析的热点之一。通过对各种复杂度算法的分析得出,近似熵由于所需要的时间序列长度较短,大大减少了脑电非平稳性所带来的困难,且无需粗粒化,在对生物医学信号的复杂度分析中有其一定的优点,采用近似熵对多道脑电信号的复杂度运算结果,通过空间插值,构建复杂性动态脑地形图,以便于观察大脑各部ＥＥＧ信号复杂度在同一时刻的相对强弱关系和这种关系随时间的变化。并通过对一些脑疾病患者脑电数据的分析,     

脑电图复杂度分析中的粗粒化问题 I.过分粗粒化和三种复杂度的比较

在对生物医学信号时间序列进行复杂度分析时,往往需要首先对原始信号进行粗粒化预处理。这种预处理有可能会造成丢失原始信号中所蕴含的信息,甚至在某些情况下根本改变原信号的动力学性质。本文提出了克服这一问题的一些途径,通过对若干种复杂度定义的比较研究,建议采用近似熵和我们所定义的Ｃ０复杂度作为复杂性度量。并以脑电的复杂性分析为例作了说明。     

Integrating image data into biomedical text categorization

Categorization of biomedical articles is a central task for supporting various curation efforts. It can also form the basis for effective biomedical text mining. Automatic text classification in the biomedical domain is thus an active research area. Contests organized by the KDD Cup (2002) and the TREC Genomics track (since 2003) defined several annotation tasks that involved document classification, and provided training and test data sets. So far, these efforts focused on analyzing only the text content of documents. However, as was noted in the KDD'02 text mining contest-where figure-captions proved to be an invaluable feature for identifying documents of interest-images often provide curators with critical information. We examine the possibility of using information derived directly from image data, and of integrating it with text-based classification, for biomedical document categorization. We present a method for obtaining features from images and for using them-both alone and in combination with text-to perform the triage task introduced in the TREC Genomics track 2004. The task was to determine which documents are relevant to a given annotation task performed by the Mouse Genome Database curators. We show preliminary results, demonstrating that the method has a strong potential to enhance and complement traditional text-based categorization methods.     

The use of a multi-channel kalman filter algorithm in structural analysis of the epileptic EEG

An extension of the Kalman filter algorithm to the multi-channel case is presented and its application as a segmenting procedure in the analysis of the epileptic EEG is discussed. An analytical example of structural analysis, using the segments extracted by the proposed filter, is presented for a particular set of 4-channel EEG recordings. This analysis is shown to be especially fruitful if the autoregressive coefficients - a by product of the filtering procedure - are used to estimate the information flow between the channels by the calculation of partial as well as directed coherences for the representative segments.     

Hash subgraph pairwise kernel for protein-protein interaction extraction

Extracting protein-protein interaction (PPI) from biomedical literature is an important task in biomedical text mining (BioTM). In this paper, we propose a hash subgraph pairwise (HSP) kernel-based approach for this task. The key to the novel kernel is to use the hierarchical hash labels to express the structural information of subgraphs in a linear time. We apply the graph kernel to compute dependency graphs representing the sentence structure for protein-protein interaction extraction task, which can efficiently make use of full graph structural information, and particularly capture the contiguous topological and label information ignored before. We evaluate the proposed approach on five publicly available PPI corpora. The experimental results show that our approach significantly outperforms all-path kernel approach on all five corpora and achieves state-of-the-art performance.     

Detecting determinism in short time series, with an application to the analysis of a stationary EEG recording

We have developed a new method for detecting determinism in a short time series and used this method to examine whether a stationary EEG is deterministic or stochastic. The method is based on the observation that the trajectory of a time series generated from a differentiable dynamical system behaves smoothly in an embedded phase space. The angles between two successive directional vectors in the trajectory reconstructed from a time series at a minimum embedding dimension were calculated as a function of time. We measured the irregularity of the angle variations obtained from the time series using second-order difference plots and central tendency measures, and compared these values with those from surrogate data. The ability of the proposed method to distinguish between chaotic and stochastic dynamics is demonstrated through a number of simulated time series, including data from Lorenz, R?ssler, and Van der Pol attractors, high-dimensional equations, and 1/f noise. We then applied this method to the analysis of stationary segments of EEG recordings consisting of 750 data points (6-s segments) from five normal subjects. The stationary EEG segments were not found to exhibit deterministic components. This method can be used to analyze determinism in short time series, such as those from physiological recordings, that can be modeled using differentiable dynamical processes.     

Selecting EEG components using time series analysis in brain death diagnosis

In diagnosis of brain death for human organ transplant, EEG (electroencephalogram) must be flat to conclude the patient’s brain death but it has been reported that the flat EEG test is sometimes difficult due to artifacts such as the contamination from the power supply and ECG (electrocardiogram, the signal from the heartbeat). ICA (independent component analysis) is an effective signal processing method that can separate such artifacts from the EEG signals. Applying ICA to EEG channels, we obtain several separated components among which some correspond to the brain activities while others contain artifacts. This paper aims at automatic selection of the separated components based on time series analysis. In the flat EEG test in brain death diagnosis, such automatic component selection is helpful.     

Local discriminative spatial patterns for movement-related potentials-based EEG classification

A novel discriminant method, termed local discriminative spatial patterns (LDSP), is proposed for movement-related potentials (MRPs)-based single-trial electroencephalogram (EEG) classification. Different from conventional discriminative spatial patterns (DSP), LDSP explicitly considers local structure of EEG trials in the construction of scatter matrices in the Fisher-like criterion. The underlying manifold structure of two-dimensional spatio-temporal EEG signals contains more discriminative information. LDSP is an extension to DSP in the sense that DSP can be formulated as a special case of LDSP. By constructing an adjacency matrix, LDSP is calculated as a generalized eigenvalue problem, and so is computationally straightforward. Experiments on MRPs-based single-trial EEG classification show the effectiveness of the proposed LDSP method.     

A modified Zeeman model for producing HRV signals and its application to ECG signal generation

Developing a mathematical model for the artificial generation of electrocardiogram (ECG) signals is a subject that has been widely investigated. One of the challenges is to generate ECG signals with a wide range of waveforms, power spectra and variations in heart rate variability (HRV)--all of which are important indexes of human heart functions. In this paper we present a comprehensive model for generating such artificial ECG signals. We incorporate into our model the effects of respiratory sinus arrhythmia, Mayer waves and the important very low-frequency component in the power spectrum of HRV. We use a new modified Zeeman model for generating the time series for HRV, and a single cycle of ECG is produced by using a simple neural network. The importance of the work is the model's ability to produce artificial ECG signals that resemble experimental recordings under various physiological conditions. As such the model provides a useful tool to simulate and analyse the main characteristics of ECG, such as its power spectrum and HRV under different conditions. Potential applications of this model include using the generated ECG as a flexible signal source to assess the effectiveness of a diagnostic ECG signal-processing device.     

Categorizing biomedicine images using novel image features and sparse coding representation

Background

Images embedded in biomedical publications carry rich information that often concisely summarize key hypotheses adopted, methods employed, or results obtained in a published study. Therefore, they offer valuable clues for understanding main content in a biomedical publication. Prior studies have pointed out the potential of mining images embedded in biomedical publications for automatically understanding and retrieving such images' associated source documents. Within the broad area of biomedical image processing, categorizing biomedical images is a fundamental step for building many advanced image analysis, retrieval, and mining applications. Similar to any automatic categorization effort, discriminative image features can provide the most crucial aid in the process.

Method

We observe that many images embedded in biomedical publications carry versatile annotation text. Based on the locations of and the spatial relationships between these text elements in an image, we thus propose some novel image features for image categorization purpose, which quantitatively characterize the spatial positions and distributions of text elements inside a biomedical image. We further adopt a sparse coding representation (SCR) based technique to categorize images embedded in biomedical publications by leveraging our newly proposed image features.

Results

we randomly selected 990 images of the JPG format for use in our experiments where 310 images were used as training samples and the rest were used as the testing cases. We first segmented 310 sample images following the our proposed procedure. This step produced a total of 1035 sub-images. We then manually labeled all these sub-images according to the two-level hierarchical image taxonomy proposed by [1]. Among our annotation results, 316 are microscopy images, 126 are gel electrophoresis images, 135 are line charts, 156 are bar charts, 52 are spot charts, 25 are tables, 70 are flow charts, and the remaining 155 images are of the type "others". A serial of experimental results are obtained. Firstly, each image categorizing results is presented, and next image categorizing performance indexes such as precision, recall, F-score, are all listed. Different features which include conventional image features and our proposed novel features indicate different categorizing performance, and the results are demonstrated. Thirdly, we conduct an accuracy comparison between support vector machine classification method and our proposed sparse representation classification method. At last, our proposed approach is compared with three peer classification method and experimental results verify our impressively improved performance.

Conclusions

Compared with conventional image features that do not exploit characteristics regarding text positions and distributions inside images embedded in biomedical publications, our proposed image features coupled with the SR based representation model exhibit superior performance for classifying biomedical images as demonstrated in our comparative benchmark study.

     

Dynamics extraction in multivariate biomedical time series

A nonlinear analysis of the underlying dynamics of a biomedical time series is proposed by means of a multi-dimensional testing of nonlinear Markovian hypotheses in the observed time series. The observed dynamics of the original N-dimensional biomedical time series is tested against a hierarchy of null hypotheses corresponding to N-dimensional nonlinear Markov processes of increasing order, whose conditional probability densities are estimated using neural networks. For each of the N time series, a measure based on higher order cumulants quantifies the independence between the past of the N-dimensional time series, and its value r steps ahead. This cumulant-based measure is used as a discriminating statistic for testing the null hypotheses. Experiments performed on artificial and real world examples, including autoregressive models, noisy chaos, and nonchaotic nonlinear processes, show the effectiveness of the proposed approach in modeling multivariate systems, predicting multidimensional time series, and characterizing the structure of biological systems. Electroencephalogram (EEG) time series and heart rate variability trends are tested as biomedical signal examples. Received: 2 July 1997 / Accepted in revised form: 26 March 1998     

脑电图复杂度分析中的粗粒化问题II.量化对复杂度计算的影响

在对生物医学信号时间序列进行复杂度分析时,粗粒化预处理有可能会造成丢失原始信号中所蕴含的信息,甚至在某些情况下根本改变原信号的动力学性质。用计算机计算时的量化过程也是一种粗粒化,民有这类问题。通过对近似熵和我们所定义的Ｃ０复杂度这两种复杂度在不同量化精度下对一些典型时间序列复杂度分析的比较研究,发现一秀说来量化精度对复杂度分析的影响不是很大,仅当时原始信号进行二值比等极端情况下,才会显著改变原信号     

Des sources neuronales aux signaux EEG : modèle et interprétation des activités épileptiques

This work deals with the interpretation of electrophysiological patients recorded in epileptic patients candidate to surgery. This issue is addressed through a physiologically relevant model for the generation of scalp and intracerebral electroencephalographic (EEG) signals. The proposed model is based on a spatiotemporal representation of the sources of brain activity, which combines a distributed dipole source model and a model of coupled neuronal populations. Signals recorded by sensors (scalp and intracerebral) are then computed by solving the forward problem in the head volume conductor. In this paper, the EEG generation model is used to study the influence of some source-related parameters (spatial extent, position, synchronization) on simulated signals, during epileptic transient activity (interictal spikes). Results show that the model allows for studying, on the one hand, the relationship between the spatiotemporal organization of neuronal sources and the properties of the observed signals and, on the other hand, the relationship between surface and depth EEG signals.     

Exploring Age-Related Changes in Dynamical Non-Stationarity in Electroencephalographic Signals during Early Adolescence

Dynamics of brain signals such as electroencephalogram (EEG) can be characterized as a sequence of quasi-stable patterns. Such patterns in the brain signals can be associated with coordinated neural oscillations, which can be modeled by non-linear systems. Further, these patterns can be quantified through dynamical non-stationarity based on detection of qualitative changes in the state of the systems underlying the observed brain signals. This study explored age-related changes in dynamical non-stationarity of the brain signals recorded at rest, longitudinally with 128-channel EEG during early adolescence (10 to 13 years of age, 56 participants). Dynamical non-stationarity was analyzed based on segmentation of the time series with subsequent grouping of the segments into clusters with similar dynamics. Age-related changes in dynamical non-stationarity were described in terms of the number of stationary states and the duration of the stationary segments. We found that the EEG signal became more non-stationary with age. Specifically, the number of states increased whereas the mean duration of the stationary segment decreased with age. These two effects had global and parieto-occipital distribution, respectively, with the later effect being most dominant in the alpha (around 10 Hz) frequency band.     

Conductive polymer combined silk fiber bundle for bioelectrical signal recording

Electrode materials for recording biomedical signals, such as electrocardiography (ECG), electroencephalography (EEG) and evoked potentials data, are expected to be soft, hydrophilic and electroconductive to minimize the stress imposed on living tissue, especially during long-term monitoring. We have developed and characterized string-shaped electrodes made from conductive polymer with silk fiber bundles (thread), which offer a new biocompatible stress free interface with living tissue in both wet and dry conditions.An electroconductive polyelectrolyte, poly(3,4-ethylenedioxythiophene)-poly(styrenesulfonate) (PEDOT-PSS) was electrochemically combined with silk thread made from natural Bombyx mori. The polymer composite 280 μm thread exhibited a conductivity of 0.00117 S/cm (which corresponds to a DC resistance of 2.62 Mohm/cm). The addition of glycerol to the PEDOT-PSS silk thread improved the conductivity to 0.102 S/cm (20.6 kohm/cm). The wettability of PEDOT-PSS was controlled with glycerol, which improved its durability in water and washing cycles. The glycerol treated PEDOT-PSS silk thread showed a tensile strength of 1000 cN in both wet and dry states. Without using any electrolytes, pastes or solutions, the thread directly collects electrical signals from living tissue and transmits them through metal cables. ECG, EEG, and sensory evoked potential (SEP) signals were recorded from experimental animals by using this thread placed on the skin. PEDOT-PSS silk glycerol composite thread offers a new class of biocompatible electrodes in the field of biomedical and health promotion that does not induce stress in the subjects.     

Statistical modeling of biomedical corpora: mining the Caenorhabditis Genetic Center Bibliography for genes related to life span

Background  

The statistical modeling of biomedical corpora could yield integrated, coarse-to-fine views of biological phenomena that complement discoveries made from analysis of molecular sequence and profiling data. Here, the potential of such modeling is demonstrated by examining the 5,225 free-text items in the Caenorhabditis Genetic Center (CGC) Bibliography using techniques from statistical information retrieval. Items in the CGC biomedical text corpus were modeled using the Latent Dirichlet Allocation (LDA) model. LDA is a hierarchical Bayesian model which represents a document as a random mixture over latent topics; each topic is characterized by a distribution over words.     

1D-CADCapsNet: One dimensional deep capsule networks for coronary artery disease detection using ECG signals

PurposeCardiovascular disease (CVD) is a leading cause of death globally. Electrocardiogram (ECG), which records the electrical activity of the heart, has been used for the diagnosis of CVD. The automated and robust detection of CVD from ECG signals plays a significant role for early and accurate clinical diagnosis. The purpose of this study is to provide automated detection of coronary artery disease (CAD) from ECG signals using capsule networks (CapsNet).MethodsDeep learning-based approaches have become increasingly popular in computer aided diagnosis systems. Capsule networks are one of the new promising approaches in the field of deep learning. In this study, we used 1D version of CapsNet for the automated detection of coronary artery disease (CAD) on two second (95,300) and five second-long (38,120) ECG segments. These segments are obtained from 40 normal and 7 CAD subjects. In the experimental studies, 5-fold cross validation technique is employed to evaluate performance of the model.ResultsThe proposed model, which is named as 1D-CADCapsNet, yielded a promising 5-fold diagnosis accuracy of 99.44% and 98.62% for two- and five-second ECG signal groups, respectively. We have obtained the highest performance results using 2 s ECG segment than the state-of-art studies reported in the literature.Conclusions1D-CADCapsNet model automatically learns the pertinent representations from raw ECG data without using any hand-crafted technique and can be used as a fast and accurate diagnostic tool to help cardiologists.     

基于大脑皮层信息传输的脑电信息图示方法

提出一种基于大脑皮层信息传输的脑电地形图示方法—脑电信息图（Ｂｒａｉｎ ＩｎｆｏｒｍａｔｉｏｎＭａｐｐｉｎｇ － ＢＩＭ） 。其原理是从不同导联电极上采集脑电信号经相空间重建构成头皮电位信息传输矩阵, 将各导联信息传输时间序列的信息传输量和复杂度数据绘制成头皮拓扑分布图, 以直观地反映脑电信息传输分布模式在不同时相中的变化进程。该方法不仅是从新的角度观察大脑功能变化, 而且可克服传统的脑电频谱分段地形图不能表达长程脑电模式变化的不足。对局限性癫痫病患者的试用表明,脑电信息图能较好地反映癫痫发作前后的信息传输动向和复杂度（Ｋｃ 、Ｃ１ 、Ｃ２） 的变化趋势。结果提示,脑电信息图（ＢＩＭ） 有可能成为一种新的观察大脑功能活动的图示诊断方法,值得进一步深入研究。