A Fetal Heart Rate Extraction Method Based on Maternal ECG Signal

Abstract

The invention discloses a fetal heart rate extraction method based on maternal electrocardiographic signals, which uses the maternal abdominal wall mixed signal as an input signal, preprocesses the maternal abdominal wall mixed signal through low-pass filtering and moving average filtering, and then uses the signal quality evaluation method Select a channel maternal abdominal wall mixed signal with the best ECG signal quality as the signal to be processed, use the Mexican hat wavelet transform to calculate the energy of the signal at each moment in the 20-40 Hz frequency band, and identify the maternal QRS wave from the energy time series and eliminate it. , the peak corresponding to the remaining energy time series is the fetal ECG. The whole method is simple and easy to implement, and can effectively extract the fetal ECG signal from the mixed ECG signal of the mother's abdominal wall, providing guarantee for doctors to diagnose and treat fetal diseases.

Description

technical field [0001] The invention belongs to the technical field of medical devices, and in particular relates to a fetal heart rate extraction method based on maternal electrocardiogram signals. Background technique [0002] Fetal ECG signal is an important and common one among various ECG signals. At present, the fetal development in the womb is mainly diagnosed clinically by monitoring the changes of heart sound, heartbeat and electrocardiogram. Among them, the fetal electrocardiogram can best reflect the fetal heart activity, is more sensitive to problems in the fetal development process, and can provide a more reliable basis for clinical diagnosis. However, the fetal ECG signal is very weak, and the extraction of the fetal ECG signal from the maternal body surface will be seriously interfered by various noises, the most important being the maternal ECG signal (MECG), 50Hz power frequency interference and baseline drift, which will affect the later stage. Analytical ...

AI Technical Summary

Problems solved by technology

The blind signal separation method can detect fetal ECG signals under the assumption that the ECG signals collected by each lead are independent, but it must be carried out under the assumption that the ECG signals collected by each lead are independent and stable, and there are difficulties in modeling. , need a large number of leads and difficult to achieve and other issues

A clearer fetal ECG signal can also be obtained by using two-lead artificial neural network, but the artificial neural network method still needs the assumption that the ECG signal is a stable signal, and the artificial neural network is based on traditional statistics to minimize the fetal ECG signal. Experience risk is the learning goal, and there are many problems to be solved, such as generalization ability, structural design, local extremum, etc.

[0005] Although there are some ECG detection equipment specially designed for fetal ECG detection on the market, fetal ECG monitoring has not been widely used in clinical practice because of the lack of reliable and low-cost methods for indirect detection of fetal ECG signals.

Images