Robust Fetal Heart Rate Tracking through Fetal Electrocardiography (ECG) and Photoplethysmography (PPG) Fusion.
Robust Fetal Heart Rate Tracking through Fetal Electrocardiography (ECG) and Photoplethysmography (PPG) Fusion.
复制标题
通过胎儿心电图 (ECG) 和光电容积描记法 (PPG) 融合进行稳健的胎儿心率跟踪。
DOI：
10.1109/embc40787.2023.10341068
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Ghiasi,Soheil
中科院分区：
文献类型：
--
作者：
Kasap,Begum;Vali,Kourosh;Qian,Weitai;Saffarpour,Mahya;Fowler,Randall;Ghiasi,Soheil
胎儿心电图（fECG）或光电容积描记图（fPPG）设备正在开发用于胎儿心率（FHR）监测。然而，深部组织感测受到低胎儿信噪比（SNR）的挑战。数据质量很容易因运动或母体组织的干扰而降低，并且由于通信故障可能发生数据丢失。在本文中，我们建议将联合收割机fECG和fPPG测量相结合，以提高对此类动态挑战的鲁棒性并提高FHR估计精度。据作者所知，文献中尚未研究两种感觉数据类型（fECG、fPPG）的融合用于FHR跟踪。所提出的方法进行了评估，从金标准的大型妊娠动物实验中捕获的真实世界的数据。一个粒子滤波算法与传感器融合的测量可能性，称为KUBAI，被用来估计胎心率。与单一传感器类型（仅PPG或仅ECG）数据相比，PPG和ECG数据的融合导致估计值和参考FHR值之间的均方根误差（RMSE）改善36.6%，R2相关性改善20.3%。我们证明，使用不同类型的感官数据提高了FHR跟踪的鲁棒性和准确性。
Fetal electrocardiogram (fECG) or photoplethysmogram (fPPG) devices are being developed for fetal heart rate (FHR) monitoring. However, deep tissue sensing is challenged by low fetal signal-to-noise ratio (SNR). Data quality is easily degraded by motion, or interference from maternal tissues and data losses can happen due to communication faults. In this paper, we propose to combine fECG and fPPG measurements in order to increase robustness against such dynamic challenges and increase FHR estimation accuracy. To the author’s knowledge the fusion of two sensory data types (fECG, fPPG) has not been investigated for FHR tracking purposes in the literature. The proposed methods are evaluated on real-world data captured from gold-standard large pregnant animal experiments. A particle filtering algorithm with sensor fusion in the measurement likelihood, called KUBAI, is used to estimate FHR. Fusion of PPG&ECG data resulted in 36.6% improvement in root-mean-square-error (RMSE) and 20.3% improvement in R2correlation between estimated and reference FHR values compared to single sensor-type (PPG-only or ECG-only) data. We demonstrate that using different types of sensory data improves the robustness and accuracy of FHR tracking.