Extraction of one or more discrete heart sounds from heart sound information

• US 7,351,207 B2
• Filed: 07/16/2004
• Issued: 04/01/2008
• Est. Priority Date: 07/18/2003
• Status: Expired due to Fees

• Current Assignee: Board of Trustees of The University of Illinois
• Original Assignee: Board of Trustees of The University of Illinois
• Inventors: Priemer, Roland
• Primary Examiner(s): Manuel; George
• Assistant Examiner(s): Flory; Christopher A.
• Application Number:
  US10/893,627
• Publication Number:
  US 20050043643A1
• Time in Patent Office: 1,355 Days
• Field of Search: 600/528
• US Class Current: 600/528
• CPC Class Codes: A61B 2562/0204 Acoustic sensors
• CPC Class Codes: A61B 2562/046 in a matrix array
• CPC Class Codes: A61B 7/02 Stethoscopes acoustic details thereof G10K11/00
• CPC Class Codes: A61B 7/023 for introduction into the body, e.g. into the oesophagus oesophageal ECG probes A61B5/285
• CPC Class Codes: A61B 7/026 comprising more than one sound collector
• CPC Class Codes: A61B 7/04 Electric stethoscopes microphones, acoustic transducers therefor H04R

Abstract

A heart sound analyzer component of an apparatus in one example extracts from composite heart sound information one or more discrete heart sounds of one or more corresponding distinct heart sound sources.

Claims

1. An apparatus, comprising:

a plurality of acoustic sensors that serve to obtain substantially simultaneously a plurality of heart sound signals, wherein the plurality of heart sound signals comprises a first heart sound signal S1 and a second heart sound signal S2, wherein the first heart sound signal S1comprises a plurality of substantially contemporaneous acoustic signals produced by a first corresponding plurality of distinct heart structures of a living heart that comprises a mitral valve and a tricuspid valve; and

a processor that decomposes the first heart sound signal S1, acquired by the plurality of acoustic sensors, into one or more individual acoustic signals, that comprise an M1 sound of the mitral valve and a T1 sound of the tricuspid valve, of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures.

2. The apparatus of claim 1, wherein the processor employs independent component analysis to extract the one or more individual acoustic signals, that comprise the M1 sound of the mitral valve and the T1 sound of the tricuspid valve, of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures from the first heart sound signal S1.

3. The apparatus of claim 2,

wherein the processor implements the independent component analysis in a neural network construct that employs a plurality of nodes in number at least equal to a number of the first corresponding plurality of distinct heart structures to extract the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures from the first heart sound signal S1.

4. The apparatus of claim 1, wherein the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures comprise a first individual acoustic signal and a second individual acoustic signal;

wherein the first individual acoustic signal and the second individual acoustic signal occur substantially contemporaneously, wherein the first individual acoustic signal and the second individual acoustic signal are mixed in the first heart sound signal;

wherein the processor employs independent component analysis of the first heart sound signal S1 to create one or more statistically independent outputs that correspond to one or more of the one or more individual acoustic signals that comprise the M1 sound of the mitral valve and the T1 sound of the tricuspid valve of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures.

5. The apparatus of claim 1, further comprising:

a stethoscope sensor head that is locatable over the living heart;

wherein the stethoscope sensor head comprises a plurality of microphones in number at least equal to a number of the first corresponding plurality of distinct heart structures;

wherein the plurality of microphones obtains and passes the first heart sound signal S1 to the processor.

6. The apparatus of claim 1, further comprising:

an esophageal stethoscope sensor head that may pass down an esophagus of a patient that comprises the living heart;

wherein the esophageal stethoscope sensor head comprises a flexible tube that contains a plurality of microphones in number at least equal to a number of the first corresponding plurality of distinct heart structures;

wherein the plurality of microphones obtains and passes the first heart sound signal S1 to the processor.

7. The apparatus of claim 1, wherein a patient comprises the living heart, wherein the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures comprise an abnormal heart sound and one or more other sounds, wherein the abnormal heart sound overlaps with one or more of the one or more other sounds in the first heart sound signal S1;

wherein the abnormal heart sound is associated with a dysfunction of the living heart of the patient, wherein the processor extracts the abnormal heart sound from the first heart sound signal S1 and outputs the abnormal heart sound to a doctor for diagnosis of the dysfunction.

8. The apparatus of claim 1, wherein the processor decomposes the first heart sound signal S1 into a plurality of individual acoustic signals, that comprises the M1 sound of the mitral valve and the T1 sound of the tricuspid valve, of the substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures;

wherein the plurality of individual acoustic signals, that comprises the M1 sound of the mitral valve and the T1 sound of the tricuspid valve, of the substantially contemporaneous acoustic signals comprises the one or more individual acoustic signals that comprise the M1 sound of the mitral valve and the T1 sound of the tricuspid valve of the substantially contemporaneous acoustic signals.

9. The apparatus of claim 8, wherein the second heart sound signal S2 comprises a plurality of substantially contemporaneous acoustic signals produced by a second corresponding plurality of distinct heart structures of the living heart that comprises an aortic valve and a pulmonary valve;

wherein the processor decomposes the second heart sound signal S2 into a plurality of individual acoustic signals, that comprises an A2 sound of the aortic valve and a P2 sound of the pulmonary valve, of the substantially contemporaneous acoustic signals produced by the second corresponding plurality of distinct heart structures.

10. The apparatus of claim 8, wherein the first heart sound signal S1 is produced by nearly and/or approximately contemporaneous closures of the mitral valve and the tricuspid valve of the living hearts;

wherein the processor extracts from the first heart sound signal S1 the M1 sound as an individual acoustic signal of the closure of the mitral valve and T1 as an individual acoustic signal of the closure of the tricuspid valve;

wherein the plurality of individual acoustic signals comprises the M1 sound as the individual acoustic signal of the closure of the mitral valve and the T1 sound as the individual acoustic signal of the closure of the tricuspid valve.

11. The apparatus of claim 8, wherein the sound signal S2 is produced by nearly and/or approximately contemporaneous closures of an aortic valve and a pulmonary valve of the living heart;

wherein the processor extracts from decomposes the second heart sound signal S2 into an A2 sound as an individual acoustic signal of the closure of the aortic valve and a P2 sound as an individual acoustic signal of the closure of the pulmonary valve;

wherein the plurality of individual acoustic signals comprises the A2 sound as the individual acoustic signal of the closure of the aortic valve and the P2 sound as the individual acoustic signal of the closure of the pulmonary valve.

12. The apparatus of claim 1, wherein the processor decomposes the second heart sound signal S2 into a plurality of individual acoustic signals that comprises an A2 sound and a P2 sound produced by a second corresponding plurality of distinct heart structures of the living heart that comprises an aortic valve associated with the A2 sound and a pulmonary valve associated with the P2 sound.

13. The apparatus of claim 1, wherein the second heart sound signal S2 comprises a plurality of substantially contemporaneous acoustic signals produced by a second corresponding plurality of distinct heart structures of the living heart that comprises an aortic valve and a pulmonary valve;

wherein the processor decomposes the second heart sound signal S2 into one or more individual acoustic signals, that comprises an A2 sound of the aortic valve and a P2 sound of the pulmonary valve, of the substantially contemporaneous acoustic signals produced by the second corresponding plurality of distinct heart structures.

14. The apparatus of claim 1, wherein the processor in a time domain extracts from the first heart sound signal S1 the one or more individual acoustic signals, that comprise the M1 sound of the mitral valve and the T1 sound of the tricuspid valve, of the substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures.

15. The apparatus of claim 1, wherein a patient comprises the living heart, wherein the plurality of heart sound signals comprises one or more murmur signals, wherein the processor extracts the one or more of the murmur signals from plurality of heart sound signals and outputs the one or more of the murmur signals to a doctor for diagnosis of heart dysfunction of the living heart of the patient.

16. An apparatus, comprising:

a processor that extracts from a first heart sound signal one or more individual acoustic signals of a plurality of substantially contemporaneous acoustic signals produced by a first corresponding plurality of distinct heart structures of a living heart;

wherein the processor implements data whitening software on the first heart sound signal to facilitate blind source separation;

wherein after running the data whitening software, the processor employs dimensionality reduction software to determine one or more remaining eigen values of the first heart sound signal, wherein the processor decreases a total number of one or more eigen values until the one or more remaining eigen values are equal in number to a number of the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures;

wherein after running the dimensionality reduction software, the processor employs blind source separation software to extract the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures from the first heart sound signal.

17. The apparatus of claim 16, wherein after extraction of the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures from the first heart sound signal, the processor implements digital filtering software and/or channel permutation software to spectrally modify, spectrally shift, and/or amplify one or more of the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures.

18. The apparatus of claim 17, wherein the processor implements the digital filtering software and/or the channel permutation software to identify the first corresponding plurality of distinct heart structures associated with the one or more individual acoustic signals of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures.

19. A method, comprising the steps of:

obtaining substantially simultaneously a plurality of heart sound signals through employment of a plurality of acoustic sensors, wherein the plurality of heart sound signals comprises a first heart sound signal S1 and a second heart sound S2, wherein the first heart sound signal S1 comprises a plurality of substantially contemporaneous acoustic signals produced by a first corresponding plurality of distinct heart structures of a living heart that comprises a mitral valve and a tricuspid valve; and

decomposing the first heart sound signal S1, acquired by the plurality of acoustic sensors, into one or more individual acoustic signals, that comprise an M1 sound of the mitral valve and a T1 sound of the tricuspid valve, of the plurality of substantially contemporaneous acoustic signals produced by the first corresponding plurality of distinct heart structures.