|
|
|
|
OverviewMedical data from Doppler Echocardiography is currently extracted manually. The manual method is time consuming and subject to inter and intra-observer variability. An automated method that analyzes the Doppler signal is important for improving the analysis accuracy and can result in a powerful tool for noninvasive evaluation of cardiac haemodynamics, especially for patients with Atrial Fibrillation (AF). AF patients suffer from an irregular heart rate, and the shape of the Doppler signal obtained from them differs from beat to beat. This variability requires the use of multiple measures, and the averaging of them in order to produce an acceptable clinical data. In practice, the echo-technician selects a single beat as a representative/average beat, inserting additional errors and subjectivity into the analysis. The presented methodology works on signals from the Mitral Valve (MV) and the Tricuspid Valve (TV), and detects the envelope of the velocity vs. time function, the Maximal Velocity Envelope (MVE) using image processing tools. An ECG signal is used to achieve synchronization, for beat-by-beat analysis. Clinical parameters are extracted from the MVE and compared to expert-based extraction by an echo technician
For more information see slides Detailed explanation as well as experimental results can be found, in Hebrew in the thesis Publications
|
For problems or
questions regarding this web page contact
hayit@eng.tau.ac.il.
|
