|
|
3D Model of Cardial Tissue Electrical Propagation
Míková, Monika ; Mézl, Martin (referee) ; Hejč, Jakub (advisor)
The aim of this master thesis is to create a simple 3D electro-anatomical model of cardiac tissue that will be able to simulate the electrical activation in both a healthy heart and a heart with arrhytmogenic substrate. The model of electrical activation is realized in the COMSOL Multiphysics, simulation software for modelling using the finite element method. The Fitzhugh-Nagumo equation was used to model the excitatory feature of the myocardium and 2D models of myocardial tissue describing the propagation of action potential in healthy tissue, ischemic tissue, spontaneous action potential formation in the SA node, and spiral wave formation were first developed based on appropriate parameters. Subsequently, simplified 3D models of the heart describing the spread of excitement in a healthy heart, in the presence of accessory pathway and in third-degree atrioventricular block were created. The simplified 3D heart model offers a compromise between computational load and model complexity and can be used as a diagnostic tool for tissue and whole heart adjustment with appropriate equation parameter settings.
|
|
|
Identification of Abnormal ECG Segments Using Multiple-Instance Learning
Šťávová, Karolína ; Smíšek, Radovan (referee) ; Hejč, Jakub (advisor)
Heart arrhythmias are a very common heart disease whose incidence is rising. This thesis is focused on the detection of premature ventricular contractions from 12-lead ECG records by means of deep learning. The location of these arrhythmias (key instances) in the record was found using a technique based on Multiple-Instance Learning. In the theoretical part of the thesis, basic electrophysiology of the heart and deep learning with a focus on the convolutional neural networks are described. Afterward, a program was created using the Python programming language, which contains a model based on the InceptionTime architecture, using which classification of the signals into the selected classes was performed. Grad-CAM was implemented to find locations of the key instances in the ECGs. The evaluation of the arrhythmia detection quality was done using the F1 score and the results were discussed at the end of the thesis.
|
|
|
Analysis of stabilometric signals in frequency domain
Netopil, Ondřej ; Hejč, Jakub (referee) ; Kozumplík, Jiří (advisor)
This work deals with the metods frequency and time frequency analysis of stabilometric signal. In the introroduction is described theory about posturography and posturographic measurment. The work contains describtion of stabilometric parametrs in time domain (1D and 2D parametrs) and in frequency domain. The aim is create review of basic metods used to processing and preprocessing of stabilometric signals and comparing this methods . In work is realized ferquency analysis used Frourier transfrmation and Burg method and time-frequency analysis used Short time Frourier transformation and Wavelet transformation. One part of program is aimed on comparison of this methods.
|
|
|
Analysis of High-Frequency ECG and Mechano-Electric Coupling in Isolated Heart
Novotná, Petra ; Ronzhina, Marina (referee) ; Hejč, Jakub (advisor)
Tato magisterská práce se zabývá analýzou vysokofrekvenčních složek záznamu EKG z pohledu mechano-elektrické vazby u izolovaného králičího srdce. První částí této práce je literární rešerše na zadané téma zahrnující informace o vzniku a šíření akčního potenciálu na chemické i elektrické úrovní i mechano-elektrické zpětné vazbě. Dále práce obsahuje kapitolu zabývající se tématikou průměrování signálu jako techniky ke zvýšení poměru signál-šum při analýze vysokofrekvenčních složek. V praktické části práce jsou získané poznatky aplikovány na dlouhé záznamy EKG z izolovaných králičích srdcí. Zahrnut je popis perfuzního systému podle Neelyho a jeho užití při experimentech. V realizaci byla data z 15 izolovaných králičích srdcí podrobeno analýze zkoumající přítomnost reakce systému na změnu vstupních parametrů (afterloadu a preploadu) v případě tlakově objemových dat. Výsledky byly vztaženy ke stejně získaným hodnotám z HF ECG. Dohromady tvoří popis mechano-elektriké reakce srdce na hemodynamické podněty. Výsledky byly statistisky testovány a vyhodnoceny.
|
|
|
Automatic Delineation of Multi-lead ECG Signals
Veverka, Vojtěch ; Smital, Lukáš (referee) ; Hejč, Jakub (advisor)
This semester thesis is focused on automated measurement of ECG signal. The theoretical part describes the rise and options ECG signal. Furthermore, the issue is staged principal components analysis, whose output is used as input signal for seasons. They describe the basic methods used in measurement to ECG signal. The practical part is designed in measurement algorithm for ECG signal that has been tested on basic CSE database. The results are discussed in the conclusion.
|
|
| |
|
|
Analysis of Ventricular Repolarization Parameters
Abbrent, Jakub ; Novotná, Petra (referee) ; Hejč, Jakub (advisor)
This bachelor’s thesis deals with the analysis of ventricular repolarization parameters on experimental ECG records. In the beginning of the theoretical part there are included information about heart electrophysiology, fundamental principle of ECG and cellular basis of the T-wave formation. Next chapter is focused on methods used for the analysis of ventricular repolarization, especially spatial parameters including principal component analysis (PCA). Then, in the thesis, there is described the database of experimental ECG signals created from isolated rabbit hearts. In the practical part of this bachelor’s thesis, there are implemented spatial parameters on experimental ECG records. Implementation of algorithms is performed after initial data preparation. Then, there is performed analysis of relation between spatial and hemodynamic parameters and the relation is evaluated by statistical analysis.
|
|
|
Reference signals in intracranial EEG: implementation and analysis
Uher, Daniel ; Hejč, Jakub (referee) ; Ronzhina, Marina (advisor)
The idea of a artifact-free brain activity recording has been circling around the scientific world for a few decades. Parasitic phenomenons and unwanted components may significatntly complicate the analysis of intracranial electroencephalographic (iEEG) recordings. However, with the rise of modern technology, new methods for precise removal of noise artifacts started to emerge. Here we use the concept of virtual reference signals for the elimination of such unwanted components. In this work, the algorithms for reference signal estimation using common average based method as well as more recent methods based on independent component analysis (ICA) were realized and evaluated on a variety of iEEG data. It was found that the ICA-based algorithms allow obtaining more accurate estimation of the reference signal as compared to the average-based one. Finally, all the methods were implemented into a open-source Python package đť‘źđť‘’đť‘“đť‘ đť‘–đť‘”, which is publicly available, easy to install and ready to use.
|
|
| |
|
|
Advanced classification of cardiac arrhythmias in ECG
Sláma, Štěpán ; Hejč, Jakub (referee) ; Ronzhina, Marina (advisor)
This work focuses on a theoretical explanation of heart rhythm disorders and the possibility of their automatic detection using deep learning networks. For the purposes of this work, a total of 6884 10-second ECG recordings with measured eight leads were used. Those recordings were divided into 5 groups according to heart rhythm into a group of records with atrial fibrillation, sinus rhythms, supraventricular rhythms, ventricular rhythms, and the last group consisted of the others records. Individual groups were unbalanced represented and more than 85 % of the total number of data are sinus rhythm group records. The used classification methods served effectively as a record detector of the largest group and the most effective of all was a procedure consisting of a 2D convolutional neural network into which data entered in the form of scalalograms (classification procedure number 3). It achieved results of precision of 91%, recall of 96% and F1-score values of 0.93. On the contrary, when classifying all groups at the same time, there were no such quality results for all groups. The most efficient procedure seems to be a variant composed of PCA on eight input signals with the gain of one output signal, which becomes the input of a 1D convolutional neural network (classification procedure number 5). This procedure achieved the following F1-score values: 1) group of records with atrial fibrillation 0.54, 2) group of sinus rhythms 0.91, 3) group of supraventricular rhythms 0.65, 4) group of ventricular rhythms 0.68, 5) others records 0.65.
|
guest ::
