Automatic detection of ultrasonic Doppler signal episodes resulting from fetal breathing movements

Abstract

A method for automatic detection of fetal breathing movements has been proposed, based on the time-frequency structure of the corresponding continuous wave ultrasonic Doppler signals. The method uses spectral analysis of the envelope of the directional Doppler signal and cross-correlation analysis of both directional envelopes. Detection rule comprises the following criteria: presence of the peak in the envelope spectrum and of the adequate signal level in the frequency range corresponding to the fetal breathing rhythm, the peak value and the position limits of the peak of the cross-correlation coefficient of the both directional envelopes. The effect of the criteria setting on the rule performance and the tradeoff between the specificity and sensitivity was investigated. The rule is most sensitive to the threshold value of the cross-correlation coefficient of the envelopes. The limits of the position of this peak are crucial for the distinction between the breathing episodes and hiccups. The optimal settings of the criteria, resulting in average sensitivity and specificity exceeding, respectively, 0.70 and 0.80, are proposed.