Di Maria Costanzo, Liu Chengyu, Zheng Dingchang, Murray Alan, Langley Philip
Regional Medical Physics Department, Newcastle upon Tyne Hospitals NHS Foundation Trust, Newcastle upon Tyne, UK. Institute of Cellular Medicine, Medical School, Newcastle University, Newcastle upon Tyne, UK.
Physiol Meas. 2014 Aug;35(8):1649-64. doi: 10.1088/0967-3334/35/8/1649. Epub 2014 Jul 29.
This study presents a systematic comparison of different approaches to the automated selection of the principal components (PC) which optimise the detection of maternal and fetal heart beats from non-invasive maternal abdominal recordings.A public database of 75 4-channel non-invasive maternal abdominal recordings was used for training the algorithm. Four methods were developed and assessed to determine the optimal PC: (1) power spectral distribution, (2) root mean square, (3) sample entropy, and (4) QRS template. The sensitivity of the performance of the algorithm to large-amplitude noise removal (by wavelet de-noising) and maternal beat cancellation methods were also assessed. The accuracy of maternal and fetal beat detection was assessed against reference annotations and quantified using the detection accuracy score F1 [2PPVSe / (PPV + Se)], sensitivity (Se), and positive predictive value (PPV). The best performing implementation was assessed on a test dataset of 100 recordings and the agreement between the computed and the reference fetal heart rate (fHR) and fetal RR (fRR) time series quantified.The best performance for detecting maternal beats (F1 99.3%, Se 99.0%, PPV 99.7%) was obtained when using the QRS template method to select the optimal maternal PC and applying wavelet de-noising. The best performance for detecting fetal beats (F1 89.8%, Se 89.3%, PPV 90.5%) was obtained when the optimal fetal PC was selected using the sample entropy method and utilising a fixed-length time window for the cancellation of the maternal beats. The performance on the test dataset was 142.7 beats(2)/min(2) for fHR and 19.9 ms for fRR, ranking respectively 14 and 17 (out of 29) when compared to the other algorithms presented at the Physionet Challenge 2013.
本研究对从无创孕妇腹部记录中自动选择主成分（PC）以优化母婴心跳检测的不同方法进行了系统比较。使用一个包含75个4通道无创孕妇腹部记录的公共数据库来训练算法。开发并评估了四种确定最佳主成分的方法：（1）功率谱分布，（2）均方根，（3）样本熵，以及（4）QRS模板。还评估了算法性能对大幅噪声去除（通过小波去噪）和母心跳动消除方法的敏感性。根据参考注释评估母婴心跳检测的准确性，并使用检测准确率得分F1 [2PPVSe / (PPV + Se)]、敏感性（Se）和阳性预测值（PPV）进行量化。在一个包含100个记录的测试数据集上评估了表现最佳的实现方式，并对计算得到的和参考的胎儿心率（fHR）以及胎儿RR（fRR）时间序列之间的一致性进行了量化。使用QRS模板方法选择最佳母主成分并应用小波去噪时，检测母心跳动的性能最佳（F1 99.3%，Se 99.0%，PPV 99.7%）。使用样本熵方法选择最佳胎儿主成分并利用固定长度时间窗口消除母心跳动时，检测胎儿心跳的性能最佳（F1 89.8%，Se 89.3%，PPV 90.5%）。测试数据集上fHR的性能为142.7次/分钟²，fRR的性能为19.9毫秒，与2013年生理信号挑战赛中展示的其他算法相比，分别排名第14和第17（共29个）。
