Barbara T. Mika

Supervised and Unsupervised Learning Systems as a Part of Hybrid Structures Applied in EGG Signals Classifiers

This paper aims at investigating an unsupervised learnt neural networks in classifier applications and comparing them to supervised perceptron type nets. The proposed solutions focus on combing the time-frequency preliminary analysis by means of wavelet transform with application of self organizing maps. Using wavelet transform as a feature extraction tool allowed to reveal important parameters included both in time and frequency domain of non-stationary electrogastrographic signals, which were classified in elaborated systems. Proposed structures were tested using the set of clinically characterized EGG signals of 62 patients, as cases with different level rhythm disturbances from bradygastria up to tachygastria together with some artifacts of non-stationary character such as muscle thrill etc. Additionally similar control group of healthy patients was analyzed. The results of the proposed methodology are illustrated in the measure of sensitivity and specificity, where the best classifier based on Kohonen maps with preliminary wavelet processing reached the performance above 90%

Assessment of slow wave propagation in multichannel electrogastrography by using noise-assisted multivariate empirical mode decomposition and cross-covariance analysis

Electrogastrography (EGG) is a noninvasive technique for recording the myoelectrical activity of the stomach. An electrogastrographic signal recorded by using a four-channel system with electrodes placed on the surface of the skin is a mixture of a low-frequency gastric pacesetter potential known as a slow wave, electrical activity from other organs, and random noise. The aim of this work was to investigate the possibility of detecting the propagation of the gastric slow wave from multichannel EGG data. Noise-assisted multivariate empirical mode decomposition (NA-MEMD) and cross-covariance analysis (CCA) are proposed as new detection tools. NA-MEMD was applied to attenuate the noise and extract the EGG signal from four channels, while CCA was performed to assess the time shift between the EGG signal channels. Validation of the method was performed using synthetic EGG signals and the methodology was tested on four young, healthy adults. After validation, the proposed method was applied for two kinds of human EGG data: 10-min (short) EGG data from the preprandial phase and 90-120-min (long) EGG data from the preprandial phase as well as the postprandial phase. The results obtained for both synthetic and human EGG data confirm that the proposed method could be a useful tool for assessing the propagation of slow waves. The time shift calculation from the preprandial phase of the EGG examination yielded more consistent results than the postprandial phase. The mean value of the slow wave time lag between neighbouring channels for synthetic data was found to be 4.99±0.47 s. In addition, it was confirmed that the proposed method, that is, NA-MEMD and CCA together, are robust to noise.

Application of Discrete Cosine Transform for Pre-Filtering Signals in Electrogastrography

Electrogastrography (EGG) is the technique of the cutaneous recording of the myoelectrical activity of the stomach. Due to its noninvasiveness and correlation with the gastric motility it is the attractive complement for imaging stomach’s diagnostic methods. As the EGG signal is the mixture of the electrical activity of the stomach and surrounding organs so the raw EGG also contains the noise, the electrocardiographic (ECG), and the respiration (RESP) signals. The aim of this paper is to present the effective tool for pre-filtering EGG signal. The filtering in the Cosine Discrete Transform (DCT) domain has been proposed as an efficient tool for denoising EGG signal. The obtained results are compared with the outcomes determined by means of the traditional digital (Butterworth, in this case) filtering method.

Assessment of Slow Wave Propagation in Different Phases of Food Stimulation in the Multichannel Electrogastrographic Signal (EGG)

The electrogastrogram (EGG), a cutaneous recording of electrical activity in the stomach is a mixture of 3 cycle per minute (3 cpm) gastric pacesetter potential known as slow wave, electrical activity from other organs and noise. Proper slow wave propagation is responsible for gastric peristaltic contractions, which are the basis for emptying of solids from stomach. Delay in the stomach emptying leads to some gastric disorders such as bloating, vomiting or nausea. To assess the slow wave propagation it is necessary to obtain slow wave in each channel of multichannel EGGs. In this paper combined methods: Independent Component Analysis (ICA) and adaptive filtering in the cosine transform domain was proposed to gain a purified EGG signal from each channel. Time shift between EGG signals from various channels was estimated by means of cross covariance analysis performed after adaptive filtering of each channel with reference signal obtained from blind sources separation by ICA algorithm. The effectiveness of that proposed methods was at first validated for the synthetic data and after was applied for human EGG, recorded before and after food stimulation.

An Application of Wavelet Transform (WT) and Independent Component Analysis (ICA) for Electrogastrographic (EGG) Signals Artifacts Detection

Electrogarstrogram (EGG) is an electric signal that is propagated through the muscles of stomach controlling muscles contractions and measuring stomach nerve activity before and after food ingestion. It is easy to perform, noninvasive and relatively inexpensive test which therefore has become an attractive method for physiologic and pathophysiologic examinations of the stomach. The main component of gastric myoelectrical activity, called gastric slow waves, has a frequency about 3 cycles/min (0.05 Hz). As a result the EGG signal requires longer recording time (usually more than 1 hour). Furthermore EGG is a weaker signal then other bioelectric signals, such as ECG or respiratory noise, so the EGG is usually contaminated by artifacts, which damage the recorded data and make analysis very difficult or impossible. In order to use EGG as diagnostic tool the artifacts have to be first detected and then automatically eliminated before the analysis starts.

A new approach for denoising multichannel electrogastrographic signals

Abstract Electrogastrography (EGG) can be considered as a non-invasive method for the measurement of gastric myoelectrical activity. The multichannel signal is non-invasively captured by disposable electrodes placed on the surface of a stomach. The recorded signal can include not only EGG components, but also the interfering signals from other organs, for instance, the disturbances connected with respiratory movements and random noise. In order to correctly calculate the parameters of the EGG examination and improve the patients diagnosis, the EGG signal requires effective methods for removing disturbances. The aim of this work was to investigate a new approach for denosing the multichannel electrogastrographic signals, performed by means of the Noise-Assisted Empirical Mode Decomposition (NA-MEMD) and adaptive filtering. The proposed method uses NA-MEMD for extracting the reference signal for adaptive filtering in the cosine domain. The suggested technique was validated by comparing the obtained results with the outcomes acquired by the reference method based on the classical bandpass filtering, Independent Component Analysis (ICA) and adaptive filtering. The effectiveness of the proposed algorithm was established by examining the influence of adaptive filtering on the basic diagnostic parameters, calculated from the EGG signal, such as the dominant frequency (DF), the normogastric rhythm index (NI), the frequency instability coefficient (FIC), and the power instability coefficient (PIC). In addition, the effectiveness of the noise attenuation by the proposed method was verified. The paper presents the results of research carried out for the five healthy subjects. Validation of the proposed method was performed using real human EGG signals and real EGG signals with added synthetic noise.

Novel tumor protein markers collection by the use of highly porous organic material for the upper and lower respiratory system – preliminary results

In the era of XXI century, when modern imaging techniques allows to increase detection of upper and lower respiratory tract cancer, still almost 75% of patients are diagnosed at an advantage stage. A very important problem in diagnostic practice is a general trend to use routine methods and the lack of new techniques exploration. Nowadays laboratory diagnosticians known defects of used methods which result limited effectiveness. Despite this fact too little attention is paid to the confrontation of biomedical and physicochemical views what follows to develop new methods within the framework of interdisciplinary research.

Empirical Mode Decomposition for slow wave extraction from electrogastrographical signals.

The aim of this study was to investigate the effectiveness of Empirical Mode Decomposition (EMD) for slow wave extraction from multichannel electrogastrographical signal (EGG) the cutaneous recording of gastric myoelectrical activity. From the pacemaker region of stomach both spontaneous depolarization and repolarization occur generating the myoelectrical waves that are called the gastric pacesetter potentials, or slow waves. The 3 cycles per minute (3pcm) (0.05Hz) slow wave is fundamental electrical phenomenon in stomach responsible for the propagation and maximum frequency of stomach contractions. Appropriate spread of gastric contractions is a key for the correct stomach emptying whereas delay in this action causes various gastric disorders, such as bloating, vomiting or unexplained nausea. Unfortunately the EGG signal is not a pure one but usually a sort of mixture consisting of respiratory signals, cardiac signals, random noise and possible myoelectrical activity from other organs surrounding the stomach, such as duodenum or small intestine. Identify and removal of contaminations from different artifactual sources from the EGG recording is a major task before EGG analysis and interpretation. The use of EMD method and Hilbert spectrum combination for slow wave extraction from raw EGG signal seems to be a good choice, because this adaptive decomposition technique is unique suitable for both nolinear, no-stationary data analysis.

Identification of Slow Wave Propagation in the Multichannel (EGG) Electrogastrographical Signal

The aim of this research is to examine the effectiveness of combining two methods Independent Component Analysis (ICA) and adaptive filtering for identifying the slow waves propagation from cutaneous multichannel electrogastrographical signal (EGG). The 3 cycle per minute (3 cpm) gastric pacesetter potential so-called slow wave is fundamental electrical phenomenon of stomach. Slow waves determine the propagation and maximum frequency of stomach contractions. Appropriate spread of gastric contractions is a key for the correct stomach emptying whereas delay this action causes various gastric disorders, such as bloating, vomiting or unexplained nausea. Parameters depict EGG properties mostly based on spectral analysis and information about slow waves spread and coupling are totaly lost, so new methods for studying slow wave propagation are really desired.

Continuous Wavelet Transform as an Effective Tools for Detecting Motion Artifacts in Electrogastrographical Signals

The cutaneous recording of gastric myoelectrical activity of the stomach known as electrogastrography (EGG) seems to be the promising tool for the noninvasive assessment of gastric motility. Unfortunately the EGG recording is usually severely contaminated both by motion artefacts and endogenous biological noise source. In order to use EGG signals as reliable diagnostic tool it is necessity to look for the effective artefacts removal methods. In this paper Continuous Wavelet Transform (CWT) was applied for detection motion artefacts from the EGG data. The set of own mother wavelets extracted directly from EGG signal was created and applied for detecting motion artefacts from one channel EGG recording. The results was compared with the effects obtained by using standard mother wavelets. The proposed method based on CWT with own mother wavelet presents very good performance for detecting motion artefacts from the EGG data.