|
|
Automatic diagnosis of the 12-lead ECG using deep learning
Blaude, Ondřej ; Smital, Lukáš (referee) ; Provazník, Valentine (advisor)
The aim of this diploma thesis is to investigate the problematics of automatic ECG diagnostics, namely on twelve-lead recordings. In the first chapter the heart and its electrical activity measurement is described shortly. In addition to that, the abnormalities which are going to be classified in this thesis are also briefly described. In the second chapter, it is described how the ECG was diagnosed earlier, by classical methods that preceded deep learning. Some of the shortcomings that the classical methods have compared to deep learning are also described here. The third part already pays attention to deep learning itself, and its contribution and advantages compared to classical methods. Convolutional neural networks and their individual blocks are also described here, later attention is paid to selected architectures that were used in some studies. The fourth chapter already focuses on the practical part, in which the data used from the PhysioNet database, the proposed algorithm and its implementation are described in more detail. In the fifth chapter the results are discussed and compared to the corresponding publications.
|
|
|
Interpreting the learning process of an atrial fibrillation classifier
Lichtblauová, Anna ; Ředina, Richard (referee) ; Novotná, Petra (advisor)
In the theoretical part of the bachelor thesis the problems of atrial fibrillation (AF) detection and principles of convolutional neural networks (CNN) are discussed. Next, two classifiers were created in the practical part. The first was designed to classify sinus rhythm, atrial fibrillation and other pathologies, while the second further distinguished the category "atrial fibrillation" according to whether it was present in the whole recording or only in a part of it. The resulting accuracies are 82.12 \% and 85.14 \% for the first and second classifiers, respectively.
|
|
|
Automatic detection of ischemia in ECG
Noremberczyk, Adam ; Potočňák, Tomáš (referee) ; Ronzhina, Marina (advisor)
This thesis discusses the utilization of the artificial neural networks (ANN) for detection of coronary artery disease (CAD) in frequency area. The first part of this thesis is orientated towards the theoretical knowledge. Describes the issue of ECG pathological changes. ECQ are converted to frequency area. Described statistical methods and methods for automatic detection of CAD and MI. Explained the issue of the perceptron and ANN. The second deals with use of Neural Network Toolbox MATLAB®. This part focuses on counting and finding suitable parameters and making connection of band. At the end of the thesis UNS is used to detect ischemic parameters and the results are discussed. Average values for the best settings are 100% accuracy.
|
|
|
Heart rate meter
Šeda, Jan ; Rampl, Ivan (referee) ; Chmelař, Milan (advisor)
The aim of the Bachelor thesis is summary of pulse measurement facilities. Heart pulse has been one of the basic measurable quantity in medical science for thousands of years. The basic quality of the given value is accuracy. The analyse of necessity of accuracy in methods for medical practice and diagnostic is the second point of the thesis. The third and most crucial point is heart pulse meter itself – it will be described in terms of mechanics, electrics and software. System based on optical measurement has been chosen in semestral project. Furthermore, accuracy of designed meter will be tested.
|
|
|
ECG Cluster Analysis
Pospíšil, David ; Kozumplík, Jiří (referee) ; Klimek, Martin (advisor)
This diploma thesis deals with the use of some methods of cluster analysis on the ECG signal in order to sort QRS complexes according to their morphology to normal and abnormal. It is used agglomerative hierarchical clustering and non-hierarchical method K – Means for which an application in Mathworks MATLAB programming equipment was developed. The first part deals with the theory of the ECG signal and cluster analysis, and then the second is the design, implementation and evaluation of the results of the usage of developed software on the ECG signal for the automatic division of QRS complexes into clusters.
|
|
|
Detection of ventricular extrasystoles
Svánovská, Zuzana ; Mézl, Martin (referee) ; Sekora, Jiří (advisor)
Ventricular extrasystoles are pathological changes in the ECG signal. Detection of ventricular extrasystoles on 12leads ECG was created in MATLAB. My work contains two algorithms. The first of these algorithms is based on comparision wides of QRS komplexes. The second algorithm matchs maximum and minimum evaluations of QRS komplexes. We look for agreements beetween these two algorithms and finally if we find these agreenments in seven leads at least we will suppose presence of ventricular extrasystoles.
|
|
|
Measurement and anaysis of electrocardiograms
Zimáková, Jana ; Vítek, Martin (referee) ; Kolářová, Jana (advisor)
The aim of my barchelor’s thesis was to become familiar with the methology of measurement of electrocardiographic signals, their description and subsequent analysis. During the measurement I used a computer system Biopac and program Matlab. The work is divided into three parts. The first part is focused on general problems of the heart activity, the generation, measurement and description of ECG curves. The second part is devoted to a description of the systém Biopac – recovery, procedure for the measurement and results measured sleep and stress ECG. The third part describes the actual processing of measured signals in Matlab.
|
|
|
Detection of poorly differentiated cardiac arrhythmias
Kantor, Marek ; Ronzhina, Marina (referee) ; Novotná, Petra (advisor)
This thesis focusses on the detection methods of atrial fibrilation, atrial flutter and sinus rhythm from ECG. Thesis also concentrate on the description of this arrhythmias and the learning algorithms used. In this thesis are implemented several classification approaches. For extraction of features is used convolution neural network and classification artifitial neural network. Selected 1D CNN method achived classification accuracy global F1 - score is 91 %. Moreover, the proposed CNN optimized with GA appears to be fast shallow network with better accuracy than the deep network. Created model are used for classification other type of arrhythmias too.
|
|
|
Averaging of biological signals
Němeček, Tomáš ; Vítek, Martin (referee) ; Smital, Lukáš (advisor)
The main objectives of this thesis are to study theory of signal averaging, filtered residue method and methods of stretching/shrinking signal. It will also test the functionality of those methods. Thesis contains theoretical analysis, explanation of principles and testing of behaving of used methods.
|
|
|
QRS complex detection in multilead ECG signals
Šlancar, Matěj ; Smital, Lukáš (referee) ; Kozumplík, Jiří (advisor)
The aim of this thesis is to introduce the principles of software QRS detection, which is based on different combinations of orthogonal (pseudoorthogonal) leads. The thesis describes the main components of the ECG signal, a selection of methods that can be used for QRS detection in orthogonal leads and finally the evaluation of the effectiveness of the chosen methods and a comparing the approaches with the results of other authors. Functionality of detection algorithm has been tested on signals of CSE standard library.
|
guest ::
