Fetal Heart Rate Extraction via Spatial Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for extracting fetal heart rate from maternal abdominal ECG recordings are unreliable due to contamination by maternal ECG signals, leading to difficulties in detecting fetal cardiac abnormalities and increased Caesarean section rates for healthy infants.
Innovation Solution
The use of spatial filtering techniques such as Principal Component Analysis (PCA) and orthogonal projection, combined with adaptive rule-based fetal QRS detection, to attenuate maternal ECG signals and extract fetal heart rate from abdominal ECG recordings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If non-invasive abdominal ECG monitoring is used to measure fetal heart rate, then the risk to mother and fetus is negligible and the method can be used after the middle of the fourth month of pregnancy, but the maternal ECG signal dominates and contaminates the fetal ECG, making it difficult to detect fetal heart rate
Solution Approach 1:
The patent extracts the maternal ECG signal from the composite abdominal ECG recording by identifying and removing the dominant maternal QRS complexes. This allows isolation of the weaker fetal ECG signal that was previously obscured by maternal signal contamination, enabling accurate fetal heart rate detection without invasive procedures.
Solution Approach 2:
The patent transforms the problem from temporal signal analysis to spatial-frequency domain analysis by applying Fourier transforms and examining spectral characteristics. This dimensional transformation allows separation of maternal and fetal signals based on their different frequency signatures, with fetal signals appearing as distinct peaks at higher frequencies.
2Measurement precision
If sophisticated signal processing techniques are applied to improve accuracy in FHR estimation, then the accuracy of fetal heart rate extraction is improved, but the complexity of the monitoring system increases
Solution Approach 1:
The patent applies preliminary filtering and preprocessing steps to the abdominal ECG signal before detailed analysis. By pre-processing the signal to enhance fetal ECG components and suppress maternal signals early in the processing chain, subsequent analysis becomes simpler and more accurate, reducing overall system complexity while maintaining high precision.
Solution Approach 2:
The patent employs iterative refinement where detected fetal QRS complexes are used to update the expected fetal heart rate, which in turn guides further signal processing and detection parameters. This feedback mechanism allows the system to adapt to varying signal conditions and improve accuracy without requiring overly complex fixed algorithms.
3Reliability
If continuous fetal heart rate monitoring is performed using current methods, then undiagnosed fetal hypoxia may be reduced, but the outputs are often unreliable and difficult to interpret, resulting in increased Caesarean section rates of deliveries of healthy infants
Solution Approach 1:
The patent segments the fetal ECG signal into distinct QRS complexes by detecting individual R-peaks and analyzing the morphology of each beat. This segmentation allows for beat-by-beat heart rate calculation and variability analysis, providing more reliable and interpretable outputs that can accurately detect fetal hypoxia without false alarms leading to unnecessary C-sections.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
System (10) for extracting a fetal heart rate from at least one maternal signal using a computer processor(26). The system includes sensors(12-18)attached to a patient to receive abdominal ECG signals and a recorder and digitizer(20)to record and digitize each at least one maternal signal in a maternal signal buffer(22A-22D). The system further includes a peak detector(40)to identify candidate peaks in the maternal signal buffer. The signal stacker(42)of the system stacks the divides at least one maternal signal buffer into a plurality of snippets, each snippet including one candidate peak and a spatial filter(44)to identify and attenuate a maternal QRS signal in the plurality of snippets of the maternal signal buffer, the spatial filter including at least one of principal component analysis and orthogonal projection, to produce a raw fetal ECG signal which is stored in a raw fetal ECG buffer. The system further includes a fetal QRS identifier(46)for identifying peaks in the raw fetal ECG buffer by at least one of principal component analysis and a peak-detector followed by rule based fQRS extraction and a merger(48)to calculate and merge the fetal heart rate from the identified peaks.