Extraction of heart sound of fetus from heart sound information that comprises plurality of mixtures of plurality of heart sounds of plurality of fetuses

Abstract

A heart sound analyzer component of an apparatus in one example extracts a heart sound of a fetus from heart sound information that comprises a plurality of mixtures of a plurality of heart sounds of a plurality of fetuses.

1 - 20 . (canceled) 
   
   
       21 . An apparatus, comprising:
 a plurality of acoustic sensors having nonspecific locations on a mother's abdomen; and   a processor that employs the plurality of acoustic sensors to obtain a plurality of sound mixtures of a plurality of sounds from one or more fetal hearts, an additional heart, and background noise;   wherein each of the plurality of sound mixtures obtained by the processor from the plurality of acoustic sensors comprises a different mixture of the plurality of sounds;   wherein the processor extracts from the plurality of sound mixtures any one or more of a plurality of heart sounds from one or more of the one or more fetal hearts and/or the additional heart.   
   
   
       22 . The apparatus of  claim 21 , wherein the processor employs a blind source separation algorithm that accounts for respective propagation delays of the plurality of heart sounds within the plurality of sound mixtures to extract from the plurality of sound mixtures the any one or more of the plurality of heart sounds from the one or more of the one or more fetal hearts and/or the additional heart. 
   
   
       23 . The apparatus of  claim 21 , wherein the processor employs an independent component analysis procedure to extract from the plurality of sound mixtures the any one or more of the plurality of heart sounds from the one or more of the one or more fetal hearts and/or the additional heart. 
   
   
       24 . The apparatus of  claim 21 , wherein the processor employs a neural network construct with a plurality of nodes in number at least equal to a total count of the one or more fetal hearts and the additional heart to extract from the plurality of sound mixtures the any one or more of the plurality of heart sounds from the one or more of the one or more fetal hearts and/or the additional heart. 
   
   
       25 . The apparatus of  claim 21 , wherein the processor extracts from the plurality of sound mixtures the any one or more of the plurality of heart sounds from the one or more of the one or more fetal hearts and/or the additional heart substantially free of interference from all other of the plurality of heart sounds. 
   
   
       26 . The apparatus of  claim 21 , wherein the plurality of heart sounds comprises a fetal heart sound from one fetus of the one or more fetuses and an other heart sound from an other living body;
 wherein the plurality of sound mixtures comprises a first heart sound mixture, a second heart sound mixture, and a third heart sound mixture;   wherein the first heart sound mixture comprises a contribution from the fetal heart sound, a contribution from the other heart sound, and a contribution from the background noise;   wherein the second heart sound mixture comprises:   a contribution from the fetal heart sound, different from the contribution to the first heart sound mixture;   a contribution from the other heart sound, different from the contribution to the first heart sound mixture; and   a contribution from the background noise, different from the contribution to the first heart sound mixture;   wherein the third heart sound mixture comprises:
 a contribution from the fetal heart sound, different from the contribution to the first heart sound mixture and different from the contribution to the second heart sound mixture; 
 a contribution from the other heart sound, different from the contribution to the first heart sound mixture and different from the contribution to the second heart sound mixture; and 
 a contribution from the background noise, different from the contribution to the first heart sound mixture and different from the contribution to the second heart sound mixture; 
   wherein the plurality of acoustic sensors comprises at least a first acoustic sensor having nonspecific abdomen location, a second acoustic sensor having nonspecific abdomen location, and a third acoustic sensor having nonspecific abdomen location;   wherein the processor employs the first acoustic sensor to obtain the first heart sound mixture, wherein the processor employs the second acoustic sensor to obtain the second heart sound mixture, wherein the processor employs the third acoustic sensor to obtain the third heart sound mixture.   
   
   
       27 . The apparatus of  claim 26 , wherein the processor separates the other heart sound from the fetal heart sound and the background noise and creates a statistically independent output of the other heart sound through employment of the plurality of sound mixtures. 
   
   
       28 . The apparatus of  claim 26 , wherein the processor separates the fetal heart sound from the other heart sound and the background noise and creates a statistically independent output of the fetal heart sound of the one fetus through employment of the plurality of sound mixtures. 
   
   
       29 . The apparatus of  claim 28 , wherein the plurality of acoustic sensors comprises three or more microphones locatable over a womb of the mother's abdomen at nonspecific locations for employment by the processor to capture the plurality of sound mixtures of the plurality of sounds to allow the processor to create the statistically independent output of the fetal heart sound of the one fetus. 
   
   
       30 . The apparatus of  claim 21 , wherein the plurality of acoustic sensors comprises a plurality of microphones in number at least equal to a total count of the one or more fetal hearts and the additional heart, wherein the plurality of microphones is locatable at nonspecific locations over a woman's womb that carries the one or more fetal hearts;
 wherein the processor employs the plurality of microphones to obtain and pass the plurality of sound mixtures to the processor.   
   
   
       31 . The apparatus of  claim 21 , wherein the processor sets one or more propagation delay difference estimates for the plurality of sounds;
 wherein the processor iteratively processes the plurality of sound mixtures to converge to the one or more propagation delay difference estimates closer to one or more true propagation delay differences of the plurality of sounds to allow extraction from the plurality of sound mixtures of the any one or more of the plurality of heart sounds from the one or more of the one or more fetal hearts and/or the additional heart.   
   
   
       32 . The apparatus of  claim 21 , wherein the processor collects one or more samples of the plurality of sound mixtures into a frame;
 wherein the processor calculates one or more updates for one or more propagation delay difference and weight estimates for the frame until a predetermined number of processing iterations have occurred or the one or more updates to the one or more propagation delay difference and weight estimates drop below a predetermined threshold.   
   
   
       33 . The apparatus of  claim 32 , wherein the one or more samples comprise one or more first samples, wherein the frame comprises a first frame, wherein the one or more updates comprise one or more first updates;
 wherein after the predetermined number of processing iterations have occurred or the one or more first updates to the one or more propagation delay difference and weight estimates drop below the predetermined threshold, the processor collects one or more second samples of the plurality of sound mixtures into a second frame;   wherein the processor calculates one or more second updates for the one or more propagation delay difference and weight estimates for the second frame until a predetermined number of iterations have occurred or the one or more second updates to the one or more propagation delay difference and weight estimates drop below a predetermined threshold.   
   
   
       34 . The apparatus of  claim 33 , wherein the processor processes one or more additional frames until the one or more propagation delay difference and weight estimates substantially converge to constants that allow separation of the plurality of sound mixtures into a plurality of independent components. 
   
   
       35 . A method, comprising the steps of:
 employing a processor coupled with a plurality of acoustic sensors at nonspecific locations on a mother's abdomen to obtain a plurality of different sound mixtures of a plurality of sounds from one or more fetal hearts, an additional heart, and background noise; and   employing the processor to extract from the plurality of sound mixtures any one or more of a plurality of heart sounds from one or more of the one or more fetal hearts and/or the additional heart substantially free of interference from all other of the plurality of heart sounds.