Heart sound parameter automatic extraction method based on audio frequency spectrogram

Abstract

The invention provides an automatic heart sound parameter extraction method based on an audio spectrogram, which can synchronously import a plurality of heart sound audio files into audio editing software, quickly determine the number of cardiac cycles by amplifying the heart sound spectrogram, and divide and determine S1, S2, S3 and S4 according to duration parameters. According to the method, the time length of the systolic period, the time length of the diastolic period, the mitral valve closing time and the tricuspid valve closing time are determined, strength measurement is determined, sound quality and other parameters are determined, heart sound analysis is facilitated, a plurality of different heart sound audio files are imported so that problematic audio can be analyzed, and misjudgment and misdiagnosis are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of cardiac strength analysis, and in particular to a method for automatically extracting cardiac sound parameters based on an audio spectrum diagram. Background Art

[0002] Heart sounds are produced by the mechanical vibrations of the myocardium contraction, valve opening and closing, and blood flow impacting the valve and blood vessel walls, which are transmitted to the chest wall. If these mechanical vibrations are converted into electrical signals and recorded using a transducer, a phonocardiogram is obtained. Traditional phonocardiographs have no quantitative analysis function at all, and have great limitations in the storage and processing of heart sounds, so they are rarely used in clinical practice.

[0003] At present, scholars usually use software algorithms to denoise and filter single heart sounds to identify the first heart sound, the second heart sound, the systole, and the diastole. Although this can also achieve automatic recognition, during the heart sound collection process, noise interference is irregular. It is difficult to completely achieve denoising by simply using software filtering. In this case, if software is used to automatically identify the first heart sound and the second heart sound, it may cause misjudgment and thus misdiagnosis. Therefore, obtaining the characteristic parameters of the heart sound is a problem that technical personnel in this field need to solve. Summary of the invention

[0004] The present invention aims at the deficiencies in the prior art and provides a method for automatically extracting heart sound parameters based on an audio spectrum.

[0005] In order to solve the above technical problems, the present invention is solved by the following technical solutions In order to achieve the above object, the present invention adopts the following technical solutions: The method for automatically extracting heart sound parameters based on audio spectrogram includes the following steps: Import heart sound audio files; Converting the audio file into a spectrogram; Identify the main components of heart sounds by analyzing the spectrogram, including the first heart sound S1 and the second heart sound S2; Calculate the duration of the cardiac cycle, systole, and diastole; Heart sound parameters are extracted from the preprocessed signals, including frequency parameters, intensity parameters and time domain parameters.

[0006] Preferably, the main components of the heart sounds also include the closure sound of the mitral valve and the closure sound of the tricuspid valve.

[0007] Preferably, the method further includes the step of labeling the identified heart sound components.

[0008] Preferably, the heart sound intensity parameter is extracted by calculating the maximum decibel and the minimum decibel.

[0009] Preferably, the average intensity of the heart sounds is extracted by calculating the average decibel.

[0010] Preferably, the quality of the heart sounds is analyzed by calculating frequency parameters.

[0011] Preferably, the frequency parameters include a starting frequency, a maximum frequency and an average frequency.

[0012] Preferably, the method includes exporting the extracted heart sound parameter data into an Excel format file.

[0013] Compared with the prior art, the present invention has the following beneficial effects: The present application provides a method for automatically extracting heart sound parameters based on an audio spectrum diagram, which can synchronously import multiple heart sound audio files into audio editing software, quickly determine the number of cardiac cycles by amplifying the heart sound audio spectrum diagram, and determine S1 and S2 according to the duration parameter, determine the systolic period, diastolic period, mitral valve, tricuspid valve closing time, as well as determine intensity measurement, determine sound quality and other parameters, so as to facilitate the analysis of heart sounds. Importing multiple heart sound audio files at different times facilitates the analysis of problematic audio and reduces misjudgment and misdiagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a schematic flow chart of the automatic extraction method of the present invention; Figure 2 This is a schematic diagram of importing a heart sound audio file of the present invention; DETAILED DESCRIPTION

[0016] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art can think of other obvious variations. The basic principles of the present invention defined in the following description can be used for other embodiments, variations, improvements, equivalents, and other technical solutions that do not deviate from the spirit and scope of the present invention.

[0017] Those skilled in the art should understand that, in the disclosure of the present invention, the directions or positions indicated by the terms "longitudinal", "lateral", "up", "down", "left", "right", "front", "back", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc. are based on the directions or positional relationships shown in the accompanying drawings, which are only simplified descriptions for the convenience of describing the present invention, and do not indicate or imply that the device or component referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the above terms should not be understood as limitations on the present invention.

[0018] It is to be understood that the term "one" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element may be one, while in another embodiment, the number of the element may be multiple, and the term "one" should not be understood as a limitation on the quantity.

[0019] The present invention is further described in detail below in conjunction with the accompanying drawings: See also Figure 1-Figure 2 The present invention provides a method for automatically extracting heart sound parameters based on an audio spectrum, comprising the following steps: Step 1: Import the heart sound audio file; Step 2: converting the audio file into a spectrogram; Step 3, identifying the main components of the heart sounds by analyzing the spectrum, including the first heart sound S1 and the second heart sound S2; Step 4: Calculate the duration of the cardiac cycle, systole, and diastole; Step 5: Extract heart sound parameters from the preprocessed signal, including frequency parameters, intensity parameters and time domain parameters.

[0020] In the present invention, the naming method of the heart sound audio file in step 1 is recording date-student number or case number-recording location (1 / 2 / 3 / 4 / 5)-recording time, where the recording location includes 5 valve areas, namely: 1. Mitral valve area (M): the strongest point of apical impulse, the fifth intercostal space, 0.5-1cm medial to the left midclavicular line; 2. Pulmonary valve area (P): the second intercostal space on the left side of the sternum; 3. Aortic valve area (A): the second intercostal space on the right side of the sternum; 4. The second auscultation area of ​​the aortic valve (E): the third intercostal space on the left side of the sternum; 5. Tricuspid valve area (T): between the fourth and fifth intercostal spaces on the left side of the sternum.

[0021] The recording time of each valve area was 60 seconds.

[0022] When you choose to import a heart sound audio file, you can obtain the heart sound recording information through the file name.

[0023] In the present invention, in step 2, the center tone audio file is imported into audio editing software including Audacity, etc., and the audio file is converted into a spectrum diagram.

[0024] In the present invention, analyzing the spectrum graph to identify the main components of heart sounds in step 3 includes the following steps: Zoom in on the heart rate spectrogram. Follow the diagram: Find two similar diagrams to determine the number of cardiac cycles, and then determine the heart rate; According to the duration parameter, S1 and S2 are determined, and the duration of the systolic phase, the duration of the diastolic phase, and the closing time of the mitral valve and the tricuspid valve are determined; Determine intensity measurements, including maximum decibel, minimum decibel, median decibel, and mean decibel; Determine the sound quality, including the starting frequency, median frequency, maximum frequency, minimum frequency, and average frequency; parameters such as spectral entropy and spectral shape measurement can be calculated to further evaluate the sound quality of heart sounds.

[0025] It should be noted that S1 is caused by the closure of the mitral valve and the tricuspid valve, and occurs in the early stage of ventricular contraction, marking the beginning of the ventricular contraction period; S2 is mainly caused by the closure of the semilunar valve, namely the aortic valve component and the pulmonary valve component, and is the beginning of the ventricular diastole period.

[0026] In the present invention, step 4 calculates the duration of the cardiac cycle, systolic period and diastolic period, wherein S1 lasts for 0.10-0.16 s and the recording focus is located at the apex; S2 lasts for 0.08-0.12 s and its recording focus is located on both sides of the sternum.

[0027] In the present invention, step 5 exports the extracted heart sound parameters, including frequency parameters, intensity parameters, time domain parameters and other data, into an Excel format file and saves it, which can: Extract the heart sound intensity parameters by calculating the maximum and minimum decibels; The average intensity of the heart sounds was extracted by calculating the average decibel; The quality of heart sounds is analyzed by calculating frequency parameters.

[0028] It should be noted that the present invention can import multiple heart sound files at the same time for synchronous processing and analysis.

[0029] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The purpose of the present invention has been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments, and the embodiments of the present invention may be deformed or modified in any way without departing from the principles.

Claims

1. A method for automatically extracting heart sound parameters based on an audio spectrogram, characterized in that: The following steps are involved: Import heart sound audio files; Converting the audio file into a spectrogram; Identify the main components of heart sounds by analyzing the spectrogram, including the first heart sound S1 and the second heart sound S2; Calculate the duration of the cardiac cycle, systole, and diastole; Heart sound parameters are extracted from the preprocessed signals, including frequency parameters, intensity parameters and time domain parameters.

2. The method for automatically extracting heart sound parameters based on audio spectrogram according to claim 1, characterized in that: The main components of the heart sounds also include the mitral valve closure sound and the tricuspid valve closure sound.

3. The method for automatically extracting heart sound parameters based on audio spectrogram according to claim 2, characterized in that: The method also includes the step of labeling the identified heart sound components.

4. The method for automatically extracting heart sound parameters based on audio spectrogram according to claim 3, characterized in that: The heart sound intensity parameters are extracted by calculating the maximum and minimum decibels.

5. The method for automatically extracting heart sound parameters based on audio spectrogram according to claim 4, characterized in that: The average intensity of the heart sounds was extracted by calculating the mean decibel.

6. The method for automatically extracting heart sound parameters based on audio spectrogram according to claim 5, characterized in that: The quality of heart sounds is analyzed by calculating frequency parameters.

7. The method for automatically extracting heart sound parameters based on audio spectrogram according to claim 6, characterized in that: The frequency parameters include a starting frequency, a maximum frequency and an average frequency.

8. The method for automatically extracting heart sound parameters based on audio spectrogram according to any one of claims 1 to 7, characterized in that: The method includes exporting the extracted heart sound parameter data into an Excel format file.

Images