一种基于自相关和平均模差算法的胎儿心率提取方法

A developed FHR detection algorithm based on autocorrelation and CMDF method

目的胎儿心率是判断孕期胎儿健康状况的一项重要指标,使用超声多普勒测量胎心率是常用的无创方法。其中,自相关算法是常用的测量胎心率的算法,但是其抗噪性差,容易出错。方法本文提出一种基于自相关与平均标准模差相结合的新算法,先通过自相关函数突显其周期性,然后用累计平均标准模差函数提取准确周期,最后通过使用该算法处理模拟器数据和临床数据,验证其精确度和抗噪性。结果相比滑动窗算法,基于自相关和平均标准模差的算法具有更高的精确度和抗噪性。结论改进后的算法可以有效计算出胎心率值。

Objective Doppler ultrasound monitors are commonly used to measure fetal heart rate （FHR） in routine screenings.One common method to acquire FHR is autocorrelation algorithm,yet it is more prone to noise and thus cannot get the accurate FHR sometimes.Methods We proposed a developed algorithm based on autocorrelation and cumulative mean normalized difference function （CMDF）,along with a noise tolerant improvement using a mixture of synthetic and real fetal heart data in order to quantify its accuracy and robustness in the presence of the signal from an ultrasound probe.Results Our proposed approach achieved higher accuracy and robustness compared to the sliding window approach.Conclusions This developed algorithm can calculate accurate fetal heart rate effectively.