Classification of Ataxic Gait.

Gait disorders accompany a number of neurological and musculoskeletal disorders that significantly reduce the quality of life. Motion sensors enable high-quality modelling of gait stereotypes. However, they produce large volumes of data, the evaluation of which is a challenge. In this publication, we compare different data reduction methods and classification of reduced data for use in clinical practice. The best accuracy achieved between a group of healthy individuals and patients with ataxic gait extracted from the records of 43 participants (23 ataxic, 20 healthy), forming 418 segments of straight gait pattern, is 98% by random forest classifier preprocessed by t-distributed stochastic neighbour embedding.

Motion Assessment for Accelerometric and Heart Rate Cycling Data Analysis.

Motion analysis is an important topic in the monitoring of physical activities and recognition of neurological disorders. The present paper is devoted to motion assessment using accelerometers inside mobile phones located at selected body positions and the records of changes in the heart rate during cycling, under different body loads. Acquired data include 1293 signal segments recorded by the mobile phone and the Garmin device for uphill and downhill cycling. The proposed method is based upon digital processing of the heart rate and the mean power in different frequency bands of accelerometric data. The classification of the resulting features was performed by the support vector machine, Bayesian methods, k-nearest neighbor method, and neural networks. The proposed criterion is then used to find the best positions for the sensors with the highest discrimination abilities. The results suggest the sensors be positioned on the spine for the classification of uphill and downhill cycling, yielding an accuracy of 96.5% and a cross-validation error of 0.04 evaluated by a two-layer neural network system for features based on the mean power in the frequency bands 〈 3 , 8 〉 and 〈 8 , 15 〉 Hz. This paper shows the possibility of increasing this accuracy to 98.3% by the use of more features and the influence of appropriate sensor positioning for motion monitoring and classification.

Sleep Apnea Detection with Polysomnography and Depth Sensors.

This paper is devoted to proving two goals, to show that various depth sensors can be used to record breathing rate with the same accuracy as contact sensors used in polysomnography (PSG), in addition to proving that breathing signals from depth sensors have the same sensitivity to breathing changes as in PSG records. The breathing signal from depth sensors can be used for classification of sleep [d=R2]apneaapnoa events with the same success rate as with PSG data. The recent development of computational technologies has led to a big leap in the usability of range imaging sensors. New depth sensors are smaller, have a higher sampling rate, with better resolution, and have bigger precision. They are widely used for computer vision in robotics, but they can be used as non-contact and non-invasive systems for monitoring breathing and its features. The breathing rate can be easily represented as the frequency of a recorded signal. All tested depth sensors (MS Kinect v2, RealSense SR300, R200, D415 and D435) are capable of recording depth data with enough precision in depth sensing and sampling frequency in time (20-35 frames per second (FPS)) to capture breathing rate. The spectral analysis shows a breathing rate between 0.2 Hz and 0.33 Hz, which corresponds to the breathing rate of an adult person during sleep. To test the quality of breathing signal processed by the proposed workflow, a neural network classifier (simple competitive NN) was trained on a set of 57 whole night polysomnographic records with a classification of sleep [d=R2]apneaapnoas by a sleep specialist. The resulting classifier can mark all [d=R2]apneaapnoa events with 100% accuracy when compared to the classification of a sleep specialist, which is useful to estimate the number of events per hour. [d=R2]When compared to the classification of polysomnographic breathing signal segments by a sleep specialistand, which is used for calculating length of the event, the classifier has an [d=R1] F 1 score of 92.2%Accuracy of 96.8% (sensitivity 89.1% and specificity 98.8%). The classifier also proves successful when tested on breathing signals from MS Kinect v2 and RealSense R200 with simulated sleep [d=R2]apneaapnoa events. The whole process can be fully automatic after implementation of automatic chest area segmentation of depth data.

Recognition of Patient Groups with Sleep Related Disorders using Bio-signal Processing and Deep Learning.

Accurately diagnosing sleep disorders is essential for clinical assessments and treatments. Polysomnography (PSG) has long been used for detection of various sleep disorders. In this research, electrocardiography (ECG) and electromayography (EMG) have been used for recognition of breathing and movement-related sleep disorders. Bio-signal processing has been performed by extracting EMG features exploiting entropy and statistical moments, in addition to developing an iterative pulse peak detection algorithm using synchrosqueezed wavelet transform (SSWT) for reliable extraction of heart rate and breathing-related features from ECG. A deep learning framework has been designed to incorporate EMG and ECG features. The framework has been used to classify four groups: healthy subjects, patients with obstructive sleep apnea (OSA), patients with restless leg syndrome (RLS) and patients with both OSA and RLS. The proposed deep learning framework produced a mean accuracy of 72% and weighted F1 score of 0.57 across subjects for our formulated four-class problem.

Study of the Optimum Arrangement of Spherical Particles in Containers Having Different Cross Section Shapes.

Fluidized bed porosity ɛ is a primary property of fluidized systems when determining the minimum floating velocity. The air flow rate in the fluidized bed (or in the fluid layer of the material) increases with diminishing bed porosity. This paper is devoted to porosity calculations for a fluidized bed consisting of spherical particles having different diameters (2, 4, 6, 8, 10 mm) and in differently shaped polygonal fluidized bed cells possessing different characteristic particle floating velocities. For testing purposes, porosity was experimentally measured and subsequently modelled by simulation using the Rocky code. Cells with regular triangular, tetragonal (square-shaped), pentagonal, hexagonal, heptagonal and circular cross sections were used for the experiment. All the cells possessed the same cross-section area S = 1256 mm². The weight of the spherical particle batch in the experiments was constant, 2 kg, for all of the fluidized bed cell cross section shapes described above.

Investigation of Geometric Properties of Modified Titanium White by Fluidisation for Use in the Process of Transport, Handling, Processing and Storage.

The present article deals with investigation of geometric properties of surface modified titanium white with the help of silica oxide by various methods of shape and size identification of clusters made by processing by fluidisation. For the purpose of the investigation of geometric properties the artificially made titanium oxide (titanium white) was processed by fluidisation with a defined percentage of silica oxide additive. The selected additive was represented by hydrophilic pyrogenic silica (micronised silica oxide), known under commercial name Aerosil 200, Aerosil R972 and hydrophilic pyrogenic metal oxide Aeroxide P25. The investigation began by image acquisition of the individual additives and the titanium white with scanning electron microscope and continued by investigation of clusters created by fluidisation in a vertical fluidisation cell using state-of-the-art methods of particle size identification analysis. The research was oriented toward the area of mutual impact of particles in the titanium white clusters with particles of additives.

Principal component analysis of normalized full spectrum mass spectrometry data in multiMS-toolbox: An effective tool to identify important factors for classification of different metabolic patterns and bacterial strains.

RATIONALE: Explorative statistical analysis of mass spectrometry data is still a time-consuming step. We analyzed critical factors for application of principal component analysis (PCA) in mass spectrometry and focused on two whole spectrum based normalization techniques and their application in the analysis of registered peak data and, in comparison, in full spectrum data analysis. We used this technique to identify different metabolic patterns in the bacterial culture of Cronobacter sakazakii, an important foodborne pathogen. METHODS: Two software utilities, the ms-alone, a python-based utility for mass spectrometry data preprocessing and peak extraction, and the multiMS-toolbox, an R software tool for advanced peak registration and detailed explorative statistical analysis, were implemented. The bacterial culture of Cronobacter sakazakii was cultivated on Enterobacter sakazakii Isolation Agar, Blood Agar Base and Tryptone Soya Agar for 24 h and 48 h and applied by the smear method on an Autoflex speed MALDI-TOF mass spectrometer. RESULTS: For three tested cultivation media only two different metabolic patterns of Cronobacter sakazakii were identified using PCA applied on data normalized by two different normalization techniques. Results from matched peak data and subsequent detailed full spectrum analysis identified only two different metabolic patterns - a cultivation on Enterobacter sakazakii Isolation Agar showed significant differences to the cultivation on the other two tested media. The metabolic patterns for all tested cultivation media also proved the dependence on cultivation time. CONCLUSIONS: Both whole spectrum based normalization techniques together with the full spectrum PCA allow identification of important discriminative factors in experiments with several variable condition factors avoiding any problems with improper identification of peaks or emphasis on bellow threshold peak data. The amounts of processed data remain still manageable. Both implemented software utilities are available free of charge from http://uprt.vscht.cz/ms.

Breathing Analysis Using Thermal and Depth Imaging Camera Video Records.

The paper is devoted to the study of facial region temperature changes using a simple thermal imaging camera and to the comparison of their time evolution with the pectoral area motion recorded by the MS Kinect depth sensor. The goal of this research is to propose the use of video records as alternative diagnostics of breathing disorders allowing their analysis in the home environment as well. The methods proposed include (i) specific image processing algorithms for detecting facial parts with periodic temperature changes; (ii) computational intelligence tools for analysing the associated videosequences; and (iii) digital filters and spectral estimation tools for processing the depth matrices. Machine learning applied to thermal imaging camera calibration allowed the recognition of its digital information with an accuracy close to 100% for the classification of individual temperature values. The proposed detection of breathing features was used for monitoring of physical activities by the home exercise bike. The results include a decrease of breathing temperature and its frequency after a load, with mean values -0.16 °C/min and -0.72 bpm respectively, for the given set of experiments. The proposed methods verify that thermal and depth cameras can be used as additional tools for multimodal detection of breathing patterns.

Microsoft Kinect Visual and Depth Sensors for Breathing and Heart Rate Analysis.

This paper is devoted to a new method of using Microsoft (MS) Kinect sensors for non-contact monitoring of breathing and heart rate estimation to detect possible medical and neurological disorders. Video sequences of facial features and thorax movements are recorded by MS Kinect image, depth and infrared sensors to enable their time analysis in selected regions of interest. The proposed methodology includes the use of computational methods and functional transforms for data selection, as well as their denoising, spectral analysis and visualization, in order to determine specific biomedical features. The results that were obtained verify the correspondence between the evaluation of the breathing frequency that was obtained from the image and infrared data of the mouth area and from the thorax movement that was recorded by the depth sensor. Spectral analysis of the time evolution of the mouth area video frames was also used for heart rate estimation. Results estimated from the image and infrared data of the mouth area were compared with those obtained by contact measurements by Garmin sensors (www.garmin.com). The study proves that simple image and depth sensors can be used to efficiently record biomedical multidimensional data with sufficient accuracy to detect selected biomedical features using specific methods of computational intelligence. The achieved accuracy for non-contact detection of breathing rate was 0.26% and the accuracy of heart rate estimation was 1.47% for the infrared sensor. The following results show how video frames with depth data can be used to differentiate different kinds of breathing. The proposed method enables us to obtain and analyse data for diagnostic purposes in the home environment or during physical activities, enabling efficient human-machine interaction.

Separation of overlapping dental arch objects using digital records of illuminated plaster casts.

BACKGROUND: Plaster casts of individual patients are important for orthodontic specialists during the treatment process and their analysis is still a standard diagnostical tool. But the growing capabilities of information technology enable their replacement by digital models obtained by complex scanning systems. METHOD: This paper presents the possibility of using a digital camera as a simple instrument to obtain the set of digital images for analysis and evaluation of the treatment using appropriate mathematical tools of image processing. The methods studied in this paper include the segmentation of overlapping dental bodies and the use of different illumination sources to increase the reliability of the separation process. The circular Hough transform, region growing with multiple seed points, and the convex hull detection method are applied to the segmentation of orthodontic plaster cast images to identify dental arch objects and their sizes. RESULTS: The proposed algorithm presents the methodology of improving the accuracy of segmentation of dental arch components using combined illumination sources. Dental arch parameters and distances between the canines and premolars for different segmentation methods were used as a measure to compare the results obtained. CONCLUSION: A new method of segmentation of overlapping dental arch components using digital records of illuminated plaster casts provides information with the precision required for orthodontic treatment. The distance between corresponding teeth was evaluated with a mean error of 1.38% and the Dice similarity coefficient of the evaluated dental bodies boundaries reached 0.9436 with a false positive rate [Formula: see text] and false negative rate [Formula: see text].

Motion tracking and gait feature estimation for recognising Parkinson's disease using MS Kinect.

BACKGROUND: Analysis of gait features provides important information during the treatment of neurological disorders, including Parkinson's disease. It is also used to observe the effects of medication and rehabilitation. The methodology presented in this paper enables the detection of selected gait attributes by Microsoft (MS) Kinect image and depth sensors to track movements in three-dimensional space. METHODS: The experimental part of the paper is devoted to the study of three sets of individuals: 18 patients with Parkinson's disease, 18 healthy aged-matched individuals, and 15 students. The methodological part of the paper includes the use of digital signal-processing methods for rejecting gross data-acquisition errors, segmenting video frames, and extracting gait features. The proposed algorithm describes methods for estimating the leg length, normalised average stride length (SL), and gait velocity (GV) of the individuals in the given sets using MS Kinect data. RESULTS: The main objective of this work involves the recognition of selected gait disorders in both the clinical and everyday settings. The results obtained include an evaluation of leg lengths, with a mean difference of 0.004 m in the complete set of 51 individuals studied, and of the gait features of patients with Parkinson's disease (SL: 0.38 m, GV: 0.61 m/s) and an age-matched reference set (SL: 0.54 m, GV: 0.81 m/s). Combining both features allowed for the use of neural networks to classify and evaluate the selectivity, specificity, and accuracy. The achieved accuracy was 97.2 %, which suggests the potential use of MS Kinect image and depth sensors for these applications. CONCLUSIONS: Discussion points include the possibility of using the MS Kinect sensors as inexpensive replacements for complex multi-camera systems and treadmill walking in gait-feature detection for the recognition of selected gait disorders.

Evaluation of dental morphometrics during the orthodontic treatment.

BACKGROUND: Diagnostic orthodontic and prosthetic procedures commence with an initial examination, during which a number of individual findings on occlusion or malocclusion are clarified. Nowadays we try to replace standard plaster casts by scanned objects and digital models. METHOD: Geometrically calibrated images aid in the comparison of several different steps of the treatment and show the variation of selected features belonging to individual biomedical objects. The methods used are based on geometric morphometrics, making a new approach to the evaluation of the variability of features. The study presents two different methods of measurement and shows their accuracy and reliability. RESULTS: The experimental part of the present paper is devoted to the analysis of the dental arch objects of 24 patients before and after the treatment using the distances between the canines and premolars as the features important for diagnostic purposes. Our work proved the advantage of measuring digitalized orthodontic models over manual measuring of plaster casts, with statistically significant results and accuracy sufficient for dental practice. CONCLUSION: A new method of computer imaging and measurements of a dental stone cast provides information with the precision required for orthodontic treatment. The results obtained point to the reduction in the variance of the distances between the premolars and canines during the treatment, with a regression coefficient RC=0.7 and confidence intervals close enough for dental practice. The ratio of these distances pointed to the nearly constant value of this measure close to 0.84 for the given set of 24 individuals.

Complex continuous wavelet coherence for EEG microstates detection in insight and calm meditation.

Complex continuous wavelet coherence (WTC) can be used for non-stationary signals, such as electroencephalograms. Areas of the WTC with a coherence higher than the calculated optimal threshold were obtained, and the sum of their areas was used as a criterion to differentiate between groups of experienced insight-focused meditators, calm-focused meditators and a control group. This method demonstrated the highest accuracy for the real WTC parts in the frontal region, while for the imaginary parts, the highest accuracy was shown for the frontal occipital pairs of electrodes. In the frontal area, in the broadband frequency, both types of experienced meditators demonstrated an enlargement of the increased coherence areas for the real WTC parts. For the imaginary parts unaffected by the volume conduction and global artefacts, the most significant increase occurred for the frontal occipital pair of electrodes.

Age-related changes in EEG coherence.

BACKGROUND AND PURPOSE: Coherence changes can reflect the pathophysiological processes involved in human ageing. We conducted a retrospective population study that sought to analyze the age-related changes in EEG coherence in a group of 17,722 healthy professional drivers. MATERIALS AND METHODS: The EEGs were obtained using a standard 10-20 electrode configuration on the scalp. The recordings from 19 scalp electrodes were taken while the participants' eyes were closed. The linear correlations between the age and coherence were estimated by linear regression analysis. RESULTS: Our results showed a significant decrease in coherence with age in the theta and alpha bands, and there was an increasing coherence with the beta bands. The most prominent changes occurred in the alpha bands. The delta bands contained movement artefacts, which most likely do not change with age. CONCLUSIONS: The age-related EEG desynchrony can be partly explained by the age-related reduction of cortical connectivity. Higher frequencies of oscillations require less cortical area of high coherence. These findings explain why the lowest average coherence values were observed in the beta and sigma bands, as well as why the beta bands show borderline statistical significance and the sigma bands show non-significance. The age-dependent decrease in coherence may influence the estimation of age-related changes in EEG energy due to phase cancellation.

Possibility of reconstruction of dental plaster cast from 3D digital study models.

OBJECTIVES: To compare traditional plaster casts, digital models and 3D printed copies of dental plaster casts based on various criteria. To determine whether 3D printed copies obtained using open source system RepRap can replace traditional plaster casts in dental practice. To compare and contrast the qualities of two possible 3D printing options--source system RepRap and commercially available 3D printing. DESIGN AND SETTINGS: A method comparison study on 10 dental plaster casts from the Orthodontic department, Department of Stomatology, 2nd medical Faulty, Charles University Prague, Czech Republic. MATERIAL AND METHODS: Each of 10 plaster casts were scanned by inEos Blue scanner and the printed on 3D printer RepRap [10 models] and ProJet HD3000 3D printer [1 model]. Linear measurements between selected points on the dental arches of upper and lower jaws on plaster casts and its 3D copy were recorded and statistically analyzed. RESULTS: 3D printed copies have many advantages over traditional plaster casts. The precision and accuracy of the RepRap 3D printed copies of plaster casts were confirmed based on the statistical analysis. Although the commercially available 3D printing enables to print more details than the RepRap system, it is expensive and for the purpose of clinical use can be replaced by the cheaper prints obtained from RepRap printed copies. CONCLUSIONS: Scanning of the traditional plaster casts to obtain a digital model offers a pragmatic approach. The scans can subsequently be used as a template to print the plaster casts as required. Using 3D printers can replace traditional plaster casts primarily due to their accuracy and price.

Diffuse Reflectance Spectroscopy as a Novel Method of Caries Detection-An In Vitro Comparative Study in Permanent Teeth.

This in vitro study aimed to compare outcomes of dental caries detection using visual inspection classified according to the International Caries Detection and Assessment System (ICDAS) with objective assessments using a well-established laser fluorescence system (Diagnodent pen) and a novel diffuse reflectance spectroscopy (DRS) device. One hundred extracted permanent premolars and molars were utilized, including sound teeth, teeth with non-cavitated caries, or teeth with small cavitated lesions. A total of 300 regions of interest (ROIs) were assessed using each detection method. Visual inspection, being a subjective method, was performed by two independent examiners. The presence and extent of caries were histologically verified according to Downer's criteria, serving as a reference for other detection methods. Histological results revealed 180 sound ROIs and 120 carious ROIs, categorized into three different extents of caries. Overall, there was no significant difference between the detection methods in sensitivity (0.90-0.93) and false negative rate (0.05-0.07). However, DRS exhibited superior performance in specificity (0.98), accuracy (0.95), and false positive rate (0.04) compared to other detection methods. Although the tested DRS prototype device exhibited limited penetration depth, it shows promise as a method, particularly for the detection of incipient caries.

The Effect of Face Masks on Physiological Data and the Classification of Rehabilitation Walking.

Gait analysis and the assessment of rehabilitation exercises are important processes that occur during fitness level monitoring and the treatment of neurological disorders. This paper presents the possibility of using oximetric, heart rate (HR), accelerometric, and global navigation satellite systems (GNSSs) to analyse signals recorded during uphill and downhill walking without and with a face mask to find its influence on physiological functions during selected walking patterns. The experimental dataset includes 86 signal segments acquired under different conditions. The proposed methodology is based on signal analysis in both the time and frequency domains. The results indicate that face mask use has a minimal effect on blood oxygen concentration and heart rate, with the average mean changes of these parameters being less than 2%. The support vector machine, a Bayesian method, the k -nearest neighbour method, and a two-layer neural network showed very good separation abilities and successfully classified different walking patterns only in the case when the effect of face mask wearing was not included in the classification process. Our methodology suggests that artificial intelligence and machine learning tools are efficient methods for the assessment of motion patterns in different motion conditions and that face masks have a negligible effect for short-duration experiments.

Acute and chronic blood serum proteome changes in patients with methanol poisoning.

Twenty-four blood serum samples from patients with acute methanol poisoning (M) from the mass methanol poisoning outbreak in the Czech Republic in 2012 were compared with 46 patient samples taken four years after poisoning (S) (overlap of 10 people with group M) and with a control group (C) of 24 samples of patients with a similar proportion of chronic alcohol abuse. When comparing any two groups, tens to hundreds of proteins with a significant change in concentration were identified. Fifteen proteins showed significant changes when compared between any two groups. The group with acute methanol poisoning showed significant changes in protein concentrations for at least 64 proteins compared to the other groups. Among the most important identified proteins closely related to intoxication are mainly those involved in blood coagulation, metabolism of vitamin A (increased retinol-binding protein), immune response (e.g., increased complement factor I, complement factors C3 and C5), and lipid transport (increased apolipoprotein A I, apolipoprotein A II, adiponectin). For blood coagulation, the most affected proteins with significant changes in the methanol poisoning group were von Willebrand factor, carboxypeptidase N, alpha-2-antiplasmin (all increased), inter-alpha-trypsin inhibitor heavy chain H4, kininogen-1, plasma serine protease inhibitor, plasminogen (all decreased). However, heparin administration used for the methanol poisoning group could have interfered with some of the changes in their concentrations. Data are available via ProteomeXchange with the identifier PXD035726.

Comparison of 2D OPG image versus orthopantomogram from 3D CBCT from the forensic point of view.

Forensic dental identification has employed traditionally 2D digital radiological imaging techniques. More recently, 3D cone beam computer tomography (CBCT) data, widely applied in clinical dentistry, have been gradually used. The purpose of this study was to compare the precision and quality of 2D digital orthopantomogram (OPG) and 2D OPG images generated from cone beam computed tomography (CBCT). The study sample consisted of 50 patients with archived conventional 2D OPG and 3D CBCT images. Patients signed an informed consent form to take part in our study. Measurements of the mandible, teeth and dental restorations were taken by two observers on calibrated 2D OPG and 3D CBCT-to-OPG images using measurement functionalities of DOPLHIN software. Acquired dimensions were compared side by side and images of fillings were superimposed. For better visual comparison and more efficient image registration, the methods of spline interpolation were used. The pairs of absolute measurements obtained from conventional OPG and CBCT-to-OPG-converted images were highly correlated (p < 0.05). However, larger, and horizontally measured distances were revealed to be more affected than shorter vertically taken measurements. In relative terms, CBCT-generated width/length indices of the canines and the first molars ranged from 84% to 99.8% of those acquired from traditional OPGs. In addition, corresponding points on the teeth and fillings were compared side by side and in superimposition. The average coincidence of images was 6.1%. The results revealed that for selected metric variables 2D OPGs and 3D CBCT-generated OPGs were complementary and could be used for forensic comparisons.

Deep Learning for Accelerometric Data Assessment and Ataxic Gait Monitoring.

Ataxic gait monitoring and assessment of neurological disorders belong to important multidisciplinary areas that are supported by digital signal processing methods and machine learning tools. This paper presents the possibility of using accelerometric data to optimise deep learning convolutional neural network systems to distinguish between ataxic and normal gait. The experimental dataset includes 860 signal segments of 16 ataxic patients and 19 individuals from the control set with the mean age of 38.6 and 39.6 years, respectively. The proposed methodology is based upon the analysis of frequency components of accelerometric signals simultaneously recorded at specific body positions with a sampling frequency of 60 Hz. The deep learning system uses all of the frequency components in a range of 〈0,30 〉 Hz. Our classification results are compared with those obtained by standard methods, which include the support vector machine, Bayesian methods, and the two-layer neural network with features estimated as the relative power in selected frequency bands. Our results show that the appropriate selection of sensor positions can increase the accuracy from 81.2% for the foot position to 91.7% for the spine position. Combining the input data and the deep learning methodology with five layers increased the accuracy to 95.8%. Our methodology suggests that artificial intelligence methods and deep learning are efficient methods in the assessment of motion disorders and they have a wide range of further applications.