Passive fetal heart rate monitoring apparatus and method with enhanced fetal heart beat discrimination

• US 5,524,631 A
• Filed: 10/13/1994
• Issued: 06/11/1996
• Est. Priority Date: 10/13/1994
• Status: Expired due to Term

• Current Assignee: National Aeronautics and Space Administration (Government of the United States of America), The United States of America As Represented By The Secretary of Agriculture
• Original Assignee: United States Of America As Represented By The Administrator Of The National Aeronautics And Space Administration
• Inventors: Livingston, David L., Pretlow, Robert A. III, Zahorian, Stephen A.
• Primary Examiner(s): Kamm, William E.
• Application Number:
  US08/323,943
• Time in Patent Office: 607 Days
• Field of Search: 128/698
• US Class Current: 600/511
• CPC Class Codes: A61B 5/02411 of foetuses
• CPC Class Codes: A61B 5/4362 Assessing foetal parameters
• CPC Class Codes: Y10S 128/925 Neural network

Abstract

An apparatus for acquiring signals emitted by a fetus, identifying fetal heart beats and determining a fetal heart rate. Multiple sensor signals are outputted by a passive fetal heart rate monitoring sensor. Multiple parallel nonlinear filters filter these multiple sensor signals to identify fetal heart beats in the signal data. A processor determines a fetal heart rate based on these identified fetal heart beats. The processor includes the use of a figure of merit weighting of heart rate estimates based on the identified heart beats from each filter for each signal. The fetal heart rate thus determined is outputted to a display, storage, or communications channel. A method for enhanced fetal heart beat discrimination includes acquiring signals from a fetus, identifying fetal heart beats from the signals by multiple parallel nonlinear filtering, and determining a fetal heart rate based on the identified fetal heart beats. A figure of merit operation in this method provides for weighting a plurality of fetal heart rate estimates based on the identified fetal heart beats and selecting the highest ranking fetal heart rate estimate.

Claims

1. A passive fetal heart rate monitoring apparatus comprising:

a passive fetal heart rate monitoring sensor having a plurality of sensor elements for acquiring acoustic signals emitted from a fetus inside a body and outputting a plurality of sensor signals in response to the acoustic signals;

a signal processing device, including receivers, amplifiers, and filters for outputting a plurality of processed signals in response to the sensor signals;

means for detecting fetal heart beats comprising a neural network, responsive to the plurality of processed signals, for identifying regions of fetal heart beats on each signal, and for outputting a functional value indicative of the presence of fetal heart beats for each processed signal;

fetal heart rate determining means, responsive to the plurality of functional values indicative of the presence of fetal heart beats, for determining and outputting a fetal heart rate.

2. An apparatus as in claim 1, wherein said neural network comprises an input layer, a hidden layer, and an output layer, each layer comprising one or more nodes, a first node in the input layer being connected to the current input processed signal, and all other nodes in the input layer being connected to a different previous input point corresponding to a previous input processed signal, each node in the input layer being connected to each node in the hidden layer and each node in the hidden layer being connected to each node in the output layer, the output layer outputting a functional value indicative of fetal heart beats, each connection between nodes having an associated weight;

and

a training means for determining the weight for each said connection between nodes of the neural network.

3. An apparatus as in claim 2 wherein the training means comprises means for adjusting each weight by use of back propagation.

4. An apparatus as in claim 1, wherein said means for detecting fetal heart beats further comprises a plurality of neural networks connected in parallel to said neural network for providing redundant identification of the fetal heart beats from the signal, and outputting a plurality of functional values indicative of the presence of fetal heart beats for each processed signal.

5. An apparatus as in claim 1, wherein said means for detecting fetal heart beats further comprises a Teager Energy Operator connected in parallel to said neural network for providing redundant identification of the fetal heart beats for each received processed signal by outputting a plurality of functional values indicative of the presence of fetal heart beats for each processed signal, said Teager Energy Operator is defined by the equation:

space="preserve" listing-type="equation">y(n)=x 2*(n-1)-x(n)*(n-2)

where x(n) is the processed signal and y(n) is the functional value.

6. An apparatus as in claim 1 wherein the fetal heart rate determining means comprises:

means for determining and outputting a fetal heart rate estimate for each of the received functional values;

means for ranking the estimated fetal heart rates by determining a figure of merit value for each received fetal heart rate estimate; and

merit comparison processing means for comparing the received figure of merit values for each received estimated fetal heart rate and outputting the estimated fetal heart rate which has the highest figure of merit.

7. An apparatus as in claim 6, wherein said means for determining and outputting a fetal heart rate estimate comprises:

an autocorrelator for forming an autocorrelation function responsive to each of the received plurality of functional values, and

means for detecting peaks for each received autocorrelation function over a search range appropriate for fetal heart rates, converting the peaks into an estimated fetal heart rate for each autocorrelation function, and outputting each of the plurality of estimated heart rates.

8. An apparatus as in claim 1 further comprising display means for receiving and displaying the estimated fetal heart rate with the highest figure of merit.

9. An apparatus as in claim 1 wherein said signal processing device further comprises an analog to digital converter for digitizing the plurality of sensor signals.

10. A passive fetal heart rate monitoring apparatus comprising:

a passive fetal heart rate monitoring sensor having a plurality of sensor elements for acquiring acoustic signals emitted from a fetus inside a body and outputting a plurality of sensor signals in response to the acoustic signals;

a signal processing device, including receivers, amplifiers, and filters for outputting a plurality of processed signals in response to the sensor signals;

means for detecting fetal heart beats comprising a Teager Energy Operator, responsive to the plurality of processed signals, for identifying regions of fetal heart beats on each signal, and for outputting a functional value indicative of the presence of fetal heart beats for each processed signal;

fetal heart rate determining means, responsive to the plurality of functional values indicative of the presence of fetal heart beats, for determining and outputting a fetal heart rate.

11. An apparatus as in claim 10 wherein said Teager Energy Operator is defined by the equation:

space="preserve" listing-type="equation">y(n)=xΛ

2*(n-1)-x(n)*(n-2)

where x(n) is the processed signal and y(n) is the functional value.

12. An apparatus as in claim 10 wherein said means for detecting fetal heart beats further comprises Teager Energy Operators connected in parallel to said Teager Energy Operator for providing redundant identification of the fetal heart beats for each received processed signal by outputting a plurality of functional values indicative of the presence of fetal heart beats for each processed signal.

13. An apparatus as in claim 10 wherein the fetal heart rate determining means comprises:

means for determining and outputting a fetal heart rate estimate for each of the received functional values;

means for ranking the estimated fetal heart rates by determining a figure of merit value for each received fetal heart rate estimate; and

merit comparison processing means for comparing the received figure of merit values for each received estimated fetal heart rate and outputting the estimated fetal heart rate which has the highest figure of merit.

14. An apparatus as in claim 13, wherein said means for determining and outputting a fetal heart rate estimate comprises:

an autocorrelator for forming an autocorrelation function responsive to each of the received plurality of functional values, and

means for detecting peaks for each received autocorrelation function over a search range appropriate for fetal heart rates, converting the peaks into an estimated fetal heart rate for each autocorrelation function, and outputting each of the plurality of estimated heart rates.

15. An apparatus as in claim 10 further comprising display means for receiving and displaying the estimated fetal heart rate with the highest figure of merit.

16. An apparatus as in claim 10 wherein said signal processing device further comprises an analog to digital converter for digitizing the plurality of sensor signals.

17. A method for passive fetal heart rate monitoring of a fetus in a body comprising:

acquiring acoustic signals emitted from a fetus inside a body and outputting a plurality of sensor signals in response to the acoustic signals;

receiving, amplifying, and filtering outputting a plurality of processed signals in response to the sensor signals;

detecting fetal heart beats using a neural network, responsive to the plurality of processed signals, identifying regions of fetal heart beats on each signal, and outputting a functional value indicative of the presence of fetal heart beats for each processed signal;

determining and outputting the fetal heart rate in response to the plurality of functional values indicative of the presence of fetal heart beats.

18. The method of claim 17, wherein said neural network comprises an input layer, a hidden layer, and an output layer, each layer comprising one or more nodes, a first node in the input layer being connected to the current input processed signal, and all other nodes in the input layer being connected to a different previous input point corresponding to a previous input processed signal, each node in the input layer being connected to each node in the hidden layer and each node in the hidden layer being connected to each node in the output layer, the output layer outputting a functional value indicative of fetal heart beats, each connection between nodes having an associated weight;

and

a training means for determining the weight for each said connection between nodes of the neural network.

19. The method of claim 18 wherein the training means comprises means for adjusting each weight by use of back propagation.

20. The method of claim 17, wherein the step of detecting fetal heart beats further comprises the steps of providing redundant identification of the fetal heart beats from each signal using a plurality of neural networks connected in parallel to said neural network and responsive to each signal, and outputting a plurality of functional values indicative of the presence of fetal heart beats for each processed signal.

21. The method of claim 17, wherein the step of detecting fetal heart beats further comprises the steps of providing redundant identification of the fetal heart beats for each received processed signal using a Teager Energy Operator connected in parallel to said neural network and responsive to each signal, and outputting a plurality of functional values indicative of the presence of fetal heart beats for each processed signal, said Teager Energy Operator is defined by the equation:

space="preserve" listing-type="equation">y(n)=xΛ

2*(n-1)-x(n)*(n-2)

where x(n) is the processed signal and y(n) is the functional value.

22. The method of claim 17 wherein the fetal heart rate determining means comprises:

determining and outputting a fetal heart rate estimate for each of the received functional values;

ranking the estimated fetal heart rates by determining a figure of merit value for each received fetal heart rate estimate; and

comparing the received figure of merit values for each received estimated fetal heart rate and outputting the estimated fetal heart rate which has the highest figure of merit.

23. The method of claim 22, wherein the step of determining and outputting a fetal heart rate estimate comprises:

forming an autocorrelation function responsive to each of the received plurality of functional values,

detecting peaks for each received autocorrelation function over a search range appropriate for fetal heart rates, converting the peaks into an estimated fetal heart rate for each autocorrelation function, and outputting each of the plurality of estimated heart rates.

24. The method of claim 17 further comprising the steps of receiving and displaying the estimated fetal heart rate with the highest figure of merit.

25. The method of claim 17 wherein the step of processing the signals further comprises the step of digitizing the plurality of sensor signals.

26. A passive fetal heart rate monitoring method comprising the steps of:

acquiring acoustic signals emitted from a fetus inside a body and outputting a plurality of sensor signals in response to the acoustic signals;

processing the signals using a signal processing device having receivers, amplifiers, and filters, and outputting a plurality of processed signals in response to the sensor signals;

detecting fetal heart beats using a Teager Energy Operator responsive to the plurality of processed signals, identifying regions of fetal heart beats on each signal, and outputting a functional value indicative of the presence of fetal heart beats for each processed signal;

determining and outputting a fetal heart rate in response to the plurality of functional values indicative of the presence of fetal heart beats.

27. The method of claim 26 wherein said Teager Energy Operator is defined by the equation:

space="preserve" listing-type="equation">y(n)=xΛ

2*(n-1)-x(n)*(n-2)

where x(n)is the processed signal and y(n)is the functional value.

28. The method of claim 26 wherein the step of detecting fetal heart beats further comprises the steps of providing redundant identification of the fetal heart beats for each received processed signal by connecting a plurality of Teager Energy Operators in parallel to said Teager Energy Operator and outputting a plurality of functional values indicative of the presence of fetal heart beats for each processed signal.

29. The method of claim 26 wherein the fetal heart rate determining means comprises:

determining and outputting a fetal heart rate estimate for each of the received functional values;

ranking the estimated fetal heart rates by determining a figure of merit value for each received fetal heart rate estimate; and

comparing the received figure of merit values for each received estimated fetal heart rate and outputting the estimated fetal heart rate which has the highest figure of merit.

30. The method of claim 29, wherein the step of determining and outputting a fetal heart rate estimate comprises:

forming an autocorrelation function responsive to each of the received plurality of functional values,

detecting peaks for each received autocorrelation function over a search range appropriate for fetal heart rates, converting the peaks into an estimated fetal heart rate for each autocorrelation function, and outputting each of the plurality of estimated heart rates.

31. The method of claim 26 further comprising the steps of receiving and displaying the estimated fetal heart rate with the highest figure of merit.

32. The method of claim 26 wherein the step of processing the signals further comprises the step of digitizing the plurality of sensor signals.