Unlock instant, AI-driven research and patent intelligence for your innovation.

Real-time heart and lung sound automatic separation method of electrostethophone

An electronic stethoscope and automatic separation technology, applied in stethoscopes, auscultation instruments, diagnosis, etc., can solve problems such as unreserved, poor real-time signal separation, and difficult separation of heart and lung sounds

Active Publication Date: 2019-09-17
SUZHOU MELODICARE MEDICAL TECH CO LTD
View PDF22 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0017] The purpose of the present invention is to provide a real-time heart-lung sound automatic separation method for an electronic stethoscope, which solves the problems of poor real-time signal separation, difficulty in heart-lung sound separation and the inability to retain additional breath sounds caused by pathological changes in the separation of lung sounds. The problem

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Real-time heart and lung sound automatic separation method of electrostethophone
  • Real-time heart and lung sound automatic separation method of electrostethophone
  • Real-time heart and lung sound automatic separation method of electrostethophone

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 2

[0095] In order to verify the separation results of cardiopulmonary sounds when wet rales appear in the breathing sounds of the present invention, auscultation data of a 5-year-old child with pneumonia collected in the Pediatric Clinic of the Affiliated Hospital of Liaoning University of Traditional Chinese Medicine was used. The collection location was on the back and the auscultation There is almost no heart sound signal in the signal, the sampling frequency is 8000 Hz, and the sampling time is 4 seconds. The auscultation experts judged that this segment of data contained moist rales. The lung sound signal is superimposed with a heart sound signal recorded while holding the breath to generate a mixed heart and lung sound signal.

[0096] In order to simulate the real-time processing process of the electronic stethoscope, a space of 1600×16bit is allocated in the computer memory for simulating the queue Q of cardiopulmonary sounds to be separated x , and read the segment of m...

Embodiment 3

[0099] In order to verify the heart-lung sound separation results of the present invention when wheezing sounds appear in breathing sounds, auscultation data of a 10-year-old asthmatic child collected in the Pediatric Clinic of the Affiliated Hospital of Liaoning University of Traditional Chinese Medicine was used. The collection position was on the back and the auscultation signal There is almost no heart sound signal, the sampling frequency is 8000Hz, and the sampling time is 4 seconds. After the auscultation expert judges that the data contains wheezing sound, the lung sound signal is superimposed with a heart sound signal recorded when holding breath to generate A section of mixed heart-lung sound signal, the real-time processing process of the simulated electronic stethoscope is the same as that of Embodiment 1.

[0100] What Fig. 4 shows is the lung sound signal containing stridor sound before mixing, can know by this accompanying drawing, even if contain stridor sound in...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a real-time heart and lung sound automatic separation method of an electrostethophone. The real-time heart and lung sound automatic separation method comprises the following steps of establishing queues Qx, Qc and Qr; inserting cached data to the queue Qx; judging whether the queue Qx has heart sound ingredients Si; if complete Si exits, establishing a plurality of covariance matrixes by xSi through the Si ingredient in the queues Qx and Qc, and obtaining a feature vector matrix through united diagonalization; establishing a heart sound characteristic matrix; and constructing a projection matrix by using the heart sound characteristic matrix, and solving heart sound signal vectors and lung sound signal vectors, which are separated. The real-time heart and lung sound automatic separation method can be used for performing heart and lung sound separation, so that the heart sound signals and the lung sound signals can be effectively separated, for the condition that lesion of respiratory tracts causes additional breath sounds, the additional breath sounds can be well reserved in lung sound separating results, and guarantee is provided for subsequent diagnosis based on heart and lung sound separation results. The separation method has the characteristics of being high in real time and high in accuracy.

Description

technical field [0001] The invention belongs to the technical field of stethoscopes, and relates to a real-time heart-lung sound automatic separation method for an electronic stethoscope. Background technique [0002] For the heart-lung sound separation of stethoscope signals, currently published patent applications or published papers mainly solve this problem from three directions: (1) use multi-channel auscultation and blind signal separation algorithm to separate heart-lung sound; (2) through simple Filtering process "separates" the heart sound and lung sound; (3) The heart sound channel and the lung sound channel are separated by performing non-negative matrix decomposition and clustering on the short-time Fourier transform results. Specifically include: [0003] (1) Multi-channel auscultation + blind signal separation [0004] Invention patent application "An FPGA-based multi-channel stethoscope for heart-lung sound separation" (publication number CN107174277A) adopt...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): A61B7/00A61B7/02G06K9/00
CPCA61B7/003A61B7/02G06V10/96G06F2218/02G06F2218/08G06F2218/12
Inventor 蔡盛盛胡南周宁徐兴国
Owner SUZHOU MELODICARE MEDICAL TECH CO LTD