Application of 2D Extension of Hjorth's Descriptors to Distinguish Defined Groups of Bee Pollen Images.

Adulteration of food products is a serious problem in the current economy. Honey has become the third most counterfeit food product in the world and requires effective authentication methods. This article presents a new approach to the differentiation of bee pollen, which can support the development of a methodology to test honey quality based on the analysis of bee pollen. The proposed method is built on applying the Hjorth descriptors-Activity, Mobility, and Complexity-known from electroencephalography (EEG) analysis, for 2D bee pollen images. The sources for extracting the bee pollen images were the photos of honey samples, which were taken using a digital camera with a resolution of 5 megapixels connected to the tube of an optical microscope. The honey samples used were prepared according to the Polish standard PN-88/A-77626 (related to the European standard CELEX-32001L0110-PL-TXT). The effectiveness of the proposed method was positively verified for three selected groups of bee pollen-Brassica napus, Helianthus, and Phacelia-containing 35 images. Statistical analysis confirms the ability of the Hjorth descriptors to differentiate the indicated bee pollen groups. Based on the results obtained, there is a significant difference between the bee pollen groups under consideration regarding Activity p<0.00001, Mobility p<0.0001, and Complexity p<0.00001.

Higher-Order Spectral Analysis Combined with a Convolution Neural Network for Atrial Fibrillation Detection-Preliminary Study.

The global burden of atrial fibrillation (AFIB) is constantly increasing, and its early detection is still a challenge for public health and motivates researchers to improve methods for automatic AFIB prediction and management. This work proposes higher-order spectra analysis, especially the bispectrum of electrocardiogram (ECG) signals combined with the convolution neural network (CNN) for AFIB detection. Like other biomedical signals, ECG is non-stationary, non-linear, and non-Gaussian in nature, so the spectra of higher-order cumulants, in this case, bispectra, preserve valuable features. The two-dimensional (2D) bispectrum images were applied as input for the two CNN architectures with the output AFIB vs. no-AFIB: the pre-trained modified GoogLeNet and the proposed CNN called AFIB-NET. The MIT-BIH Atrial Fibrillation Database (AFDB) was used to evaluate the performance of the proposed methodology. AFIB-NET detected atrial fibrillation with a sensitivity of 95.3%, a specificity of 93.7%, and an area under the receiver operating characteristic (ROC) of 98.3%, while for GoogLeNet results for sensitivity and specificity were equal to 96.7%, 82%, respectively, and the area under ROC was equal to 96.7%. According to preliminary studies, bispectrum images as input to 2D CNN can be successfully used for AFIB rhythm detection.

Exhaled Air Metabolome Analysis for Pulmonary Arterial Hypertension Fingerprints Identification-The Preliminary Study.

Pulmonary arterial hypertension (PAH) is a rare disease with a serious prognosis. The aim of this study was to identify biomarkers for PAH in the breath phase and to prepare an automatic classification method to determine the changing metabolome trends and molecular mapping. A group of 37 patients (F/M: 8/29 women, mean age 60.4 ± 10.9 years, BMI 27.6 ± 6.0 kg/m2) with diagnosed PAH were enrolled in the study. The breath phase of all the patients was collected on a highly porous septic material using a special patented holder PL230578, OHIM 002890789-0001. The collected air was then examined with gas chromatography coupled with mass spectrometry (GC/MS). The algorithms of Spectral Clustering, KMeans, DBSCAN, and hierarchical clustering methods were used to perform the cluster analysis. The identification of the changes in the ratio of the whole spectra of biomarkers allowed us to obtain a multidimensional pathway for PAH characteristics and showed the metabolome differences in the four subgroups divided by the cluster analysis. The use of GC/MS, supported with novel porous polymeric materials, for the breath phase analysis seems to be a useful tool in selecting bio-fingerprints in patients with PAH. The four metabolome classes which were obtained constitute novel data in the PAH population.

Semi-Quantitative Method of Assessing the Thrombogenicity of Biomaterials Intended for Long-Term Blood Contact.

Biomaterials used in cardiosurgical implants and artificial valves that have long-term contact with blood pose a great challenge for researchers due to the induction of thrombogenicity. So far, the assessment of the thrombogenicity of biomaterials has been performed with the use of highly subjective descriptive methods, which has made it impossible to compare the results of various experiments. The aim of this paper was to present a new semi-quantitative method of thrombogenicity assessment based on scanning electron microscope (SEM) images of an adhered biological material deposited on the surfaces of prepared samples. The following biomaterials were used to develop the proposed method: Bionate 55D polyurethane, polyether-ether ketone, Ti6Al7Nb alloy, sintered yttria-stabilized zirconium oxide (ZrO2 + Y2O3), collagen-coated glass, and bacterial cellulose. The samples were prepared by incubating the biomaterials with platelet-rich plasma. In order to quantify the thrombogenic properties of the biomaterials, a TR parameter based on the fractal dimension was applied. The obtained results confirmed that the use of the fractal dimension enables the quantitative assessment of thrombogenicity and the proper qualification of samples in line with an expert's judgment. The polyurethanes showed the best thrombogenic properties of the tested samples: Bionate 55D (TR = 0.051) and PET-DLA 65% (average TR = 0.711). The ceramics showed the worst thrombogenic properties (TR = 1.846). All the tested materials were much less thrombogenic than the positive control (TR = 5.639).

Gastric slow wave rhythm identification using new approach based on noise-assisted multivariate empirical mode decomposition and Hilbert-Huang transform.

BACKGROUND: Electrogastrography (EGG) is the method of cutaneous recording of the myoelectrical activity of the stomach. A multi-channel signal is recorded non-invasively by means of electrodes placed outside the epigastric area. The normal electrical rhythm of the stomach (slow wave) may become significantly disturbed due to disorders of gastrointestinal tract. Abnormally fast electrical rhythms are termed tachygastria, while abnormally slow rhythms are known as bradygastria. Because some features of biological signals may go undetected using the classical methods of signal spectral analysis, we propose a new method for EGG rhythm identification. METHODS: In this study, the calculation of the basic rhythms of multi-channel EGG signals is performed by means of the noise-assisted multivariate empirical mode decomposition (NA-MEMD) and Hilbert-Huang transform (HHT), using EGG data from eight healthy subjects. The results were compared with those obtained using classical spectral analysis. KEY RESULTS: The mean values of the normogastric index for preprandial and two postprandial stages were found to be 64.78 ± 11.37%, 61.29 ± 15.86%, and 63.80 ± 13.24%, respectively. The obtained values of normogastric index are consistent with the normal human physiological value, which is approximately 70% for healthy subjects. CONCLUSIONS: This method is able to capture features of the signal which are mostly undetectable by standard EGG processing methods. The EGG dominant rhythm identification using the instantaneous normogastric, bradygastric, and tachygastric indices provides new insights into biological EGG patterns.

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.

An improvement of normogastric rhythm extraction from electrogastrographic (EGG) signal using independent component analysis.

Electrogastrographic Signal (EGG) is considered to be one of the less interesting from both registration and interpretation point of view. There are several reasons of that two facts. EGG presents gastric myoelectrical activity measured by several electrodes attached on the abdomen. Unfortunately the registration procedure does not deliver a pure signal as EGG is usually associated with some interferences caused by the other organs localized near stomach. On the other hand however there are no databases available, which could allow both comparison and proper interpretation. One of the parameter, among others, which is analyzed owing to proper registration is so called normogastric rhythm, which should cover around 70% of rhythmic behavior of the signal. Proper extraction of the normogastric rhythm is a subject of this paper. Special signal preprocessing steps should be applied before the main tool i.e. Independent Component Analysis (ICA) is applied for normogastric rhythm extraction. Also, to make this analysis possible a special registration procedure has been applied concerning two phases of registration - one with feeding and the other one without with 5 minutes brake between them.