Využití alternativních způsobů spouštění magnetické rezonance

Abstract

The thesis focuses on the issue of magnetic resonance (MR) gating by cardiorespiratory activity of the patient, which is an essential part of the examination of the cardiovascular system and abdominal organs. Since measuring the cardiorespiratory activity faces many challenges within the MR environment, many studies deal with the design of novel methods that can become alternatives to standard ones. The thesis deals with these alternative methods in more detail, especially with the measurement system based on pneumatic sensors for ballistocardiography (BCG) sensing. The thesis describes validation of the function of this system in the MR environment and the assessment of sensing quality in different areas of the patient's body. The next part of the thesis is the design and comparison of methods for the automatic identification of high-quality sections of the BCG signal, which aim to increase the accuracy of the detection of significant points and reduce the burden on the operating personnel. These methods include different machine learning-based models, whose performance is compared from a complex as well as from an individual patient perspective.

Description

Subject(s)

Magnetic Resonance Gating, Digital Signal Processing, Machine Learning, Ballistocardiography, Phonocardiography, Peak Detection

Citation