|
|
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.
|
|
|
Identification of supraventricular tachycardia segments using multiple-instance learning
Abbrent, Jakub ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
Supraventricular tachycardias have a high incidence in the population and often cause health disorders. The aim of this thesis is to automatically detect and localize atrial fibrillation in ECG records. The algorithm, implemented in Python, uses a convolutional neural network ResNet for detection with multiple-instance learning and decision rules. The output of the detection in the form of a feature signal is used for localization. The classification achieved F1 score of 0.87 on the test dataset. Then, paroxysmal atrial fibrillation was localized with a deviation of -0.40±2.26 seconds for the onsets and 1.09±2.75 seconds for the terminations of the episodes. Lastly, the obtained results are evaluated and discussed.
|
|
|
Identification of supraventricular tachycardia segments using multiple-instance learning
Abbrent, Jakub ; Novotná, Petra (referee) ; Ronzhina, Marina (advisor)
Supraventricular tachycardias have a high incidence in the population and often cause health disorders. The aim of this thesis is to automatically detect and localize atrial fibrillation in ECG records. The algorithm, implemented in Python, uses a convolutional neural network ResNet for detection with multiple-instance learning and decision rules. The output of the detection in the form of a feature signal is used for localization. The classification achieved F1 score of 0.87 on the test dataset. Then, paroxysmal atrial fibrillation was localized with a deviation of -0.40±2.26 seconds for the onsets and 1.09±2.75 seconds for the terminations of the episodes. Lastly, the obtained results are evaluated and discussed.
|
|
|
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.
|
guest ::
