HDFusion: Hierarchical Data Fusion for Robust Fetal Heart Rate Estimation using Transabdominal PPG Signals

Evaluation of fetal health during pregnancy is highly dependent on monitoring of fetal heart rate (FHR). New technologies emerge, such as the transabdominal fetal pulse oximeter (TFO), a non-invasive, light-based measurement device, to provide obstetricians with additional fetal physiological markers such as fetal oxygen saturation. Estimation of FHR from TFO's acquired photoplethysmogram (PPG) signals is necessary for deriving oxygen saturation. Non-invasive optical sensing of deep fetal tissue is inherently challenged by low signal-to-noise ratio, and unpredictable anatomical and physiological dynamics, which render a particular sensor design suboptimal. Multiple sensors can conceptually enable the system to operate more robustly under such dynamics, assuming the data acquired by different sensors can be adaptively integrated to form a coherent view of the tissue. In this paper, we present an algorithm for data fusion at several levels of information abstraction, raw data, feature, and decision levels, to improve FHR estimation. We validate the proposed technique via in-vivo data collected in gold-standard pregnant ewe experiments using TFO. The root-mean-squared error of our three-level hierarchical data fusion compared to a single-level and two-level fusion improved by over 59% and 51%, respectively. This underscores the robustness of our approach in overcoming optical deep tissue sensing challenges.