|
|
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.
|
|
|
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.
|
|
|
Optimization of a Deep Neural Network Label Encoding in a Multi-Label Problem.
Zaťko, Martin ; Novotná, Petra (referee) ; Hejč, Jakub (advisor)
The aim of the diploma thesis is to propose a method of deep learning for the classification of arrhythmias from ECG recordings and to compare the effect of coding its outputs on the overall quality of the model. A 1D convolutional neural network was selected and methods of label coding using one-hot coding, ordinal coding, the method using an autoencoder and the word embbeding method were tested and compared on it. The obtained results show that the use of the word embbeding method can increase the classification capacity of the proposed network.
|
|
|
Generative Adversial Network for Artificial ECG Generation
Šagát, Martin ; Ronzhina, Marina (referee) ; Hejč, Jakub (advisor)
The work deals with the generation of ECG signals using generative adversarial networks (GAN). It examines in detail the basics of artificial neural networks and the principles of their operation. It theoretically describes the use and operation and the most common types of failures of generative adversarial networks. In this work, a general procedure of signal preprocessing suitable for GAN training was derived, which was used to compile a database. In this work, a total of 3 different GAN models were designed and implemented. The results of the models were visually displayed and analyzed in detail. Finally, the work comments on the achieved results and suggests further research direction of methods dealing with the generation of ECG signals.
|
|
|
Optimization of a Deep Neural Network Label Encoding in a Multi-Label Problem.
Zaťko, Martin ; Novotná, Petra (referee) ; Hejč, Jakub (advisor)
The aim of the diploma thesis is to propose a method of deep learning for the classification of arrhythmias from ECG recordings and to compare the effect of coding its outputs on the overall quality of the model. A 1D convolutional neural network was selected and methods of label coding using one-hot coding, ordinal coding, the method using an autoencoder and the word embbeding method were tested and compared on it. The obtained results show that the use of the word embbeding method can increase the classification capacity of the proposed network.
|
|
|
Effect of temperature on arrhythmogenesis during heart development
Vostárek, František ; Sedmera, David (advisor) ; Tomek, Viktor (referee) ; Naňka, Ondřej (referee)
5 Abstract: Aims: The main objective of this work was to analyze in detail the effects of acute temperature changes on the function of isolated chick embryonic heart in vitro in comparison with natural conditions in ovo. Methods: The effects of temperature change (34 řC, 37 řC and 40 řC - hypo-, normo- and hyperthermia, respectively) on calcium dynamics in four days old isolated chick hearts in vitro were investigated by high-speed calcium optical imaging. For comparison and validation of in vitro measurements, experiments were also performed in ovo using videomicroscopy. Artificial electrical stimulation experiments were performed in vitro and in ovo to uncover conduction limits of different heart segments. Results: We observed almost linear dependence of sinus frequency on temperature in our temperature range. Sinus frequency during hypothermia and hyperthermia in vitro and in ovo changed about 20% in comparison with normothermia. We observed no significant changes in amplitude of calcium transients during temperature change to hypothermia but hyperthermia caused a significant decrease in amplitude of calcium transients (atria 35%, ventricles 38%). We observed a wide spectrum of arrhythmias, which occurred spontaneously even during normothermia in vitro. Occurrence of arrhythmias in vitro significantly...
|
|
|
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.
|
|
|
Effect of temperature on arrhythmogenesis during heart development
Vostárek, František
5 Abstract: Aims: The main objective of this work was to analyze in detail the effects of acute temperature changes on the function of isolated chick embryonic heart in vitro in comparison with natural conditions in ovo. Methods: The effects of temperature change (34 řC, 37 řC and 40 řC - hypo-, normo- and hyperthermia, respectively) on calcium dynamics in four days old isolated chick hearts in vitro were investigated by high-speed calcium optical imaging. For comparison and validation of in vitro measurements, experiments were also performed in ovo using videomicroscopy. Artificial electrical stimulation experiments were performed in vitro and in ovo to uncover conduction limits of different heart segments. Results: We observed almost linear dependence of sinus frequency on temperature in our temperature range. Sinus frequency during hypothermia and hyperthermia in vitro and in ovo changed about 20% in comparison with normothermia. We observed no significant changes in amplitude of calcium transients during temperature change to hypothermia but hyperthermia caused a significant decrease in amplitude of calcium transients (atria 35%, ventricles 38%). We observed a wide spectrum of arrhythmias, which occurred spontaneously even during normothermia in vitro. Occurrence of arrhythmias in vitro significantly...
|
|
|
Generative Adversial Network for Artificial ECG Generation
Šagát, Martin ; Ronzhina, Marina (referee) ; Hejč, Jakub (advisor)
The work deals with the generation of ECG signals using generative adversarial networks (GAN). It examines in detail the basics of artificial neural networks and the principles of their operation. It theoretically describes the use and operation and the most common types of failures of generative adversarial networks. In this work, a general procedure of signal preprocessing suitable for GAN training was derived, which was used to compile a database. In this work, a total of 3 different GAN models were designed and implemented. The results of the models were visually displayed and analyzed in detail. Finally, the work comments on the achieved results and suggests further research direction of methods dealing with the generation of ECG signals.
|
|
|
The effect of pressure overload on developing heart.
Zábrodská, Eva ; Olejníčková, Veronika (advisor) ; Hrdlička, Jaroslav (referee)
The early postnatal period plays important role in heart and cardiovascular system development. The substantial increase of hemodynamic load after birth results in rapid growth and differentiation of cardiac tissue. Therefore, neonatal myocardium is characterized by specific reaction to the pathological stimuli. In adult heart, the pressure overload results to cardiac hypertrophy development. However, for the short period after the birth, the cardiac tissue possesses higher proliferative activity which could be further increased as reaction to the pressure overload. The project aims to outline current knowledge about the effect of pressure overload on developing myocardium and focused to the specific changes of heart and cardiovascular system. Key words: Neonatal myocardium, Fibrosis, Heart remodeling, Hypertrophic myocardium, Gap junction
|
guest ::
