SYSTEMS, APPARATUSES AND METHODS FOR SENSING FETAL ACTIVITY

• US 20160270674A1
• Filed: 03/16/2016
• Published: 09/22/2016
• Est. Priority Date: 03/16/2015
• Status: Active Grant

• Current Assignee: Nuvo Group Ltd.
• Original Assignee: Nuvo Group Ltd.
• Inventors: Kam, Amit, Oz, Oren, Intrator, Nathan
• Granted Patent: US 9,642,544 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: A61B 5/02405 Determining heart rate variability
• CPC Class Codes: A61B 5/02411 of foetuses
• CPC Class Codes: A61B 5/0245 by using sensing means generating electric signals, i.e. ECG signals
• CPC Class Codes: A61B 5/0255 Recording instruments specially adapted therefor
• CPC Class Codes: A61B 5/316 Modalities, i.e. specific diagnostic methods
• CPC Class Codes: A61B 5/344 Foetal cardiography
• CPC Class Codes: A61B 5/35 by template matching
• CPC Class Codes: A61B 5/352 Detecting R peaks, e.g. for synchronising diagnostic apparatus; Estimating R-R interval
• CPC Class Codes: A61B 5/4362 Assessing foetal parameters
• CPC Class Codes: A61B 5/6823 Trunk, e.g., chest, back, abdomen, hip
• CPC Class Codes: A61B 5/7203 for noise prevention, reduction or removal
• CPC Class Codes: A61B 5/7221 Determining signal validity, reliability or quality A61B5/7207 and A61B5/7217 take precedence
• CPC Class Codes: A61B 5/725 using specific filters therefor, e.g. Kalman or adaptive filters A61B5/316 take precedence
• CPC Class Codes: A61B 5/7253 characterised by using transforms
• CPC Class Codes: A61B 5/726 using Wavelet transforms
• CPC Class Codes: A61B 5/7278 Artificial waveform generation or derivation, e.g. synthesising signals from measured signals A61B5/327 takes precedence
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R

Abstract

The invention provides systems and methods for monitoring the wellbeing of a fetus by the non-invasive detection and analysis of fetal cardiac activity data, utilizing a plurality of acoustic sensors.

Claims

1. A computer-implemented method, comprising:

receiving, by at least one computer processor executing specific programmable instructions configured for the method, a plurality of Phonocardiogram (PCG) signals data inputs from a plurality of acoustic sensors;

digital signal filtering, by the at least one computer processor, utilizing a plurality of bandpass filters, the plurality of PCG signals data inputs to form a plurality of filtered PCG outputs, wherein the plurality of bandpass filters comprises a L number of bandpass filters, wherein each bandpass filter outputs a K number of filtered PCG outputs;

wavelet denoising, by the at least one computer processor, a first subset of filtered PCG outputs of the plurality of filtered PCG outputs to form a M number of denoised filtered PCG outputs, wherein M is equal to L multiply by K;

transforming, by the at least one computer processor, utilizing an Independent-Component-Analysis (ICA), a second subset of filtered PCG outputs of the plurality of filtered PCG outputs to form the M number of filtered ICA transforms;

transforming, by the at least one computer processor, utilizing the Independent-Component-Analysis (ICA), a first portion of the second subset of denoised filtered PCG outputs to form the M number of denoised filtered ICA transforms;

compiling, by the at least one computer processor, a S number of a plurality of detection heartbeat (DH) inputs, comprising;

i) the M number of filtered PCG outputs,

ii) the M number of the denoised filtered PCG outputs,

iii) the M number of the filtered ICA transforms, and

iv) the M number of the denoised filtered ICA transforms;

detecting, by the at least one computer processor, beat locations of beats in each of DH inputs;

calculating, by the at least one computer processor, a confidence score that describes a probability that the beats in each DH input of the plurality of DH inputs represent actual heartbeats and not a noise;

dividing, by the at least one computer processor, the plurality of DH inputs into at least two groups;

i) a first group of DH inputs containing fetal heartbeats,

ii) a second group of DH inputs containing maternal heartbeats;

selecting, by the at least one computer processor, from the first group of DH inputs, at least one particular fetal DH input that contains the fetal heartbeat based on a first confidence score of the at least one particular fetal DH input; and

selecting, by the at least one computer processor, from the second group of DH inputs, at least one particular maternal DH input that contains the maternal heartbeat, based on a second confidence score of the at least one particular maternal DH input.

2. The computer-implemented method of claim 1, wherein the wavelet denoising comprises:

deconstructing, by the at least one computer processor, each filtered PCG output to generate a plurality of transform coefficients, by irrelatively passing each filtered PCG output through a succession of low and high pass filters;

identifying, by the at least one computer processor, a subset of heartbeat-carrying transform coefficients from the plurality of transform coefficients,

reconstructing, by the at least one computer processor, the subset of heartbeat-carrying transform coefficients to form the M number of denoised filtered PCG outputs.

3. The computer-implemented method of claim 1, wherein K is equal to a number of the plurality of acoustic sensors, and L is equal to 6.

4. The computer-implemented method of claim 1, wherein each filter of the plurality of bandpass filters has a bandwidth of 10-100 Hz and a frequency range of 5-110 HZ.

5. The computer-implemented method of claim 1, wherein the detecting of the beat locations of the beats in each of DH inputs, comprising:

calculating, by the at least one computer processor, a predetermined transform filter;

iteratively repeating, by the at least one computer processor, based on a predetermined average window length of the predetermined transform filter;

identifying, in each DH input, a subset of peaks having a predetermined shape and a predetermined size, and

selecting a group of peaks from the subset of peaks, wherein the group of peaks has the smallest variance measure;

calculating, by the at least one computer processor, initial locations of the beats.

6. The computer-implemented method of claim 1, wherein the calculating the confidence score, comprising:

generating, by the at least one computer processor, a beat-by-beat heartbeat graph for each DH input based on the beat locations.

7. The computer-implemented method of claim 1, wherein the dividing the plurality of DH inputs into the first group of DH inputs containing fetal heartbeats and the second group of DH inputs containing maternal heartbeats, comprising:

clustering, by the at least one computer processor, the beats of each DH input according to each beat value; and

assigning, by the at least one computer processor, a particular DH input having a higher average beat rate into the first group of DH inputs containing fetal heartbeats.

8. A specifically programmed computer system, comprising:

at least one specialized computer machine, comprising;

a non-transient memory, electronically storing particular computer executable program code; and

at least one computer processor which, when executing the particular program code, becomes a specifically programmed computing processor that is configured to at least perform the following operations;

receiving a plurality of Phonocardiogram (PCG) signals data inputs from a plurality of acoustic sensors;

digital signal filtering, utilizing a plurality of bandpass filters, the plurality of PCG signals data inputs to form a plurality of filtered PCG outputs, wherein the plurality of bandpass filters comprises a L number of bandpass filters, wherein each bandpass filter outputs a K number of filtered PCG outputs;

wavelet denoising a first subset of filtered PCG outputs of the plurality of filtered PCG outputs to form a M number of denoised filtered PCG outputs, wherein M is equal to L multiply by K;

transforming, utilizing an Independent-Component-Analysis (ICA), a second subset of filtered PCG outputs of the plurality of filtered PCG outputs to form the M number of filtered ICA transforms;

transforming, utilizing the Independent-Component-Analysis (ICA), a first portion of the second subset of denoised filtered PCG outputs to form the M number of denoised filtered ICA transforms;

compiling a S number of a plurality of detection heartbeat (DH) inputs, comprising;

i) the M number of filtered PCG outputs,

ii) the M number of denoised filtered PCG outputs,

iii) the M number of filtered ICA transforms, and

iv) the M number of denoised filtered ICA transforms;

detecting beat locations of beats in each of DH inputs;

calculating a confidence score that describes a probability that the beats in each DH input of the plurality of DH inputs represent actual heartbeats and not a noise;

dividing the plurality of DH inputs into at least two groups;

i) a first group of DH inputs containing fetal heartbeats,

ii) a second group of DH inputs containing maternal heartbeats;

selecting, from the first group of DH inputs, at least one particular fetal DH input that contains the fetal heartbeat based on a first confidence score of the at least one particular fetal DH input; and

selecting, from the second group of DH inputs, at least one particular maternal DH input that contains the maternal heartbeat, based on a second confidence score of the at least one particular maternal DH input.

9. The specifically programmed computer system of claim 8, wherein the wavelet denoising comprises:

deconstructing each filtered PCG output to generate a plurality of transform coefficients, by irrelatively passing each filtered PCG output through a succession of low and high pass filters;

identifying a subset of heartbeat-carrying transform coefficients from the plurality of transform coefficients,

reconstructing the subset of heartbeat-carrying transform coefficients to form the M number of denoised filtered PCG outputs.

10. The specifically programmed computer system of claim 8, wherein K is equal to a number of the plurality of acoustic sensors, and L is equal to 6.

11. The specifically programmed computer system of claim 8, wherein each filter of the plurality of bandpass filters has a bandwidth of 10-100 Hz and a frequency range of 5-110 HZ.

12. The specifically programmed computer system of claim 8, wherein the detecting of the beat locations of the beats in each of DH inputs, comprising:

calculating a predetermined transform filter;

iteratively repeating, based on a predetermined average window length of the predetermined transform filter;

identifying, in each DH input, a subset of peaks having a predetermined shape and a predetermined size, and

selecting a group of peaks from the subset of peaks, wherein the group of peaks has the smallest variance measure;

calculating initial locations of the beats.

13. The specifically programmed computer system of claim 8, wherein the calculating the confidence score, comprising:

generating a beat-by-beat heartbeat graph for each DH input based on the beat locations.

14. The specifically programmed computer system of claim 8, wherein the dividing the plurality of DH inputs into the first group of DH inputs containing fetal heartbeats and the second group of DH inputs containing maternal heartbeats, comprising:

clustering the beats of each DH input according to each beat value; and

assigning a particular DH input having a higher average beat rate into the first group of DH inputs containing fetal heartbeats.