JP6298339B2 - Respiratory sound analysis device, respiratory sound analysis method, computer program, and recording medium - Google Patents

Description

  The present invention relates to a technical field of a respiratory sound analyzing apparatus and a respiratory sound analyzing method for analyzing a respiratory sound including, for example, continuous rales, a computer program, and a recording medium.

  As this type of device, there is known a device that discriminates a plurality of sound types (for example, normal breath sound and abnormal breath sound) included in a living body breath sound detected by an electronic stethoscope or the like. For example, Patent Document 1 proposes a method of discriminating between normal breath sounds and continuous rales based on local dispersion values on the spectrum.

JP 2004-357758 A

  However, with the technique described in Patent Document 1 described above, it is not possible to classify the continuous rales into whistle sounds and similar sounds. That is, there is a technical problem that even if the breathing sound can be separated into the normal breathing sound and the continuous rabble which is the abnormal breathing sound, further separation cannot be performed on the continuous rarity sound.

  Examples of problems to be solved by the present invention include the above. It is an object of the present invention to provide a respiratory sound analysis device and a respiratory sound analysis method, a computer program, and a recording medium that can suitably analyze a continuous rale included in a respiratory sound.

  A respiratory sound analysis apparatus for solving the above problem acquires component acquisition means for acquiring a respiratory sound component including a continuous rar sound from a respiratory sound, and acquires a frequency corresponding to a predetermined feature included in the respiratory sound component. Based on the relationship between the frequency acquisition means, the frequency corresponding to the predetermined feature, and the threshold value that varies according to the frequency corresponding to the predetermined feature, the whistle voice component and the analog sound included in the respiratory sound component Determination means for determining a component.

  A respiratory sound analysis method for solving the above-described problem is a component acquisition step for acquiring a respiratory sound component including a continuous ra sound from a respiratory sound, and acquires a frequency corresponding to a predetermined feature included in the respiratory sound component. Based on the relationship between the frequency acquisition step, the frequency corresponding to the predetermined feature, and the threshold value that varies according to the frequency corresponding to the predetermined feature, the whistle voice component and the analog sound included in the respiratory sound component A determination step of determining the component.

  A computer program for solving the above problems includes a component acquisition step of acquiring a respiratory sound component including a continuous rar sound from a respiratory sound, and a frequency acquisition of acquiring a frequency corresponding to a predetermined feature included in the respiratory sound component A whistle sound component and an analog sound component included in the respiratory sound component based on a relationship between a step, a frequency corresponding to the predetermined feature, and a threshold value that varies according to the frequency corresponding to the predetermined feature; And a determination step of determining

  The above-described computer program is recorded on a recording medium for solving the above problems.

It is a block diagram which shows the whole structure of the respiratory sound analyzer which concerns on a present Example. It is a flowchart which shows operation | movement of the respiratory sound analyzer which concerns on a present Example. It is a conceptual diagram which shows the problem in the continuous rarity determination which concerns on a comparative example. It is a graph which shows the fluctuation | variation of the threshold value which concerns on a present Example. It is a table | surface which shows the specific value of the threshold value which concerns on a present Example. It is a graph (the 1) which shows the example of a display of the continuous rarity determination result which concerns on a present Example. It is a graph (the 2) which shows the example of a display of the continuous rarity determination result which concerns on a present Example. It is a conceptual diagram which shows the example which analyzes a whistle voice sound with the respiratory sound analyzer which concerns on a present Example and a comparative example. It is a conceptual diagram which shows the example which analyzes the analogy sound by the respiratory sound analyzer which concerns on a present Example and a comparative example.

<1>
The respiratory sound analysis apparatus according to the present embodiment includes a component acquisition unit that acquires a respiratory sound component including a continuous rar sound from a respiratory sound, and a frequency acquisition that acquires a frequency corresponding to a predetermined feature included in the respiratory sound component. And a whistle sound component and an analog sound component included in the respiratory sound component based on a relationship between the means, a frequency corresponding to the predetermined feature, and a threshold value that varies according to the frequency corresponding to the predetermined feature. Determination means for determining whether or not.

  According to the respiratory sound analysis apparatus according to the present embodiment, at the time of operation, first, a respiratory sound component including a continuous rarity is acquired from the respiratory sound. Specifically, a breathing sound component including a continuous rarity is extracted from a breathing sound including various sounds such as a normal breathing sound and an abnormal breathing sound using a known technique or the like. However, the respiratory sound component acquired here is not limited to the respiratory sound component including only continuous rales. That is, the acquired respiratory sound component may include a sound other than the continuous rales.

  When the respiratory sound component is acquired, a frequency corresponding to a predetermined feature included in the respiratory sound component is acquired. Here, the “predetermined feature” means a feature that occurs at a specific frequency according to the sound type included in the respiratory sound component, such as a peak that appears in a frequency-analyzed signal.

  When the frequency corresponding to the predetermined feature is acquired, the whistle vocal sound component and the analogy sound component included in the respiratory sound component are determined based on the acquired frequency. In other words, it is determined whether or not the breathing sound component including the continuous ra sound includes the whistle vocal sound component and the analog sound component that are the continuous ra sound. Note that the determination here is not particularly limited as long as it is a determination related to the presence of the whistle voice component and the like sound component in the respiratory sound component. For example, it may be determined whether the breathing sound component includes either a whistle vocal sound component or an analogy sound component, or both. Alternatively, it may be determined at what ratio the whistle voice sound component and the analogy sound component are included. Moreover, you may determine the possibility that a whistle voice sound component and a similar sound component are included.

  The determination described above is performed based on the relationship between the frequency corresponding to the predetermined feature and the threshold value that varies according to the frequency corresponding to the predetermined feature. For example, the acquired frequency and the threshold value are compared with each other, and the whistle sound component and the analogy sound component are determined based on the magnitude relationship. More specifically, for example, when the acquired frequency is higher than the threshold value, it is determined as a whistle voice component, and when it is low, it is determined as an analog sound component.

  Here, in particular, the threshold used for determination varies depending on the frequency corresponding to the acquired predetermined feature. For example, the threshold fluctuates so that the higher the acquired frequency is, the larger the ratio for determining a whistle sound is higher than that of a similar sound. In this way, if the threshold value is varied according to the frequency, it is possible to discriminate the whistle voice sound and the analogy sound more appropriately than in the case of using a fixed threshold value. In addition, what is necessary is just to set beforehand how a threshold value is fluctuated based on an experimental result. Further, the variation characteristics of the threshold may be determined according to the sex, age, height, weight, etc. of the living body to be measured.

  As described above, according to the respiratory sound analysis apparatus according to the present embodiment, it is possible to suitably discriminate whistle vocal sounds and analogy sounds that are continuous rales.

<2>
In one aspect of the respiratory sound analysis apparatus according to the present embodiment, the predetermined feature is a maximum value.

  According to this aspect, for example, a frequency analysis by a fast Fourier transform (FFT) or the like is performed on a signal indicating a respiratory sound, and information on a frequency corresponding to a maximum value (that is, a peak) of the analysis result. Is acquired. Note that the information about the frequency is acquired as corresponding to the position of the maximum value, but even if the frequency is not completely coincident with the position of the maximum value, it is acquired as information about the frequency corresponding to the position near the maximum value. Also good.

  As described above, the frequency can be acquired more easily and accurately by using the maximum value as the predetermined feature in the respiratory sound.

<3>
In another aspect of the respiratory sound analysis apparatus according to the present embodiment, the determination unit determines a ratio of the whistle sound component and the analogy sound component included in the respiratory sound component.

  According to this aspect, it is determined at what ratio the breathing sound component contains the whistle vocal sound component and the analogy sound component. Therefore, for example, it is possible to appropriately diagnose the health condition based on the respiratory sound. Note that the ratio may be determined for components other than the whistle sound component and the similar sound component.

<4>
In the aspect in which the ratio between the whistle voice component and the analog sound component is determined as described above, the higher the frequency corresponding to the predetermined feature, the higher the frequency corresponding to the predetermined feature, the higher the ratio at which the whistle voice component is included, You may change as what makes it determine so that the ratio in which a sound component is contained decreases.

  In this case, it is possible to accurately determine a whistle sound component whose frequency tends to be higher than that of the similar sound component (in other words, an analog sound component whose frequency tends to be lower than that of the whistle sound component). . The increase / decrease in the ratio of the determination result may be a linear variation or a relatively complicated variation according to a predetermined function. Alternatively, it may be a stepwise change.

<5>
The respiratory sound analysis method according to the present embodiment includes a component acquisition step of acquiring a respiratory sound component including a continuous ra sound from the respiratory sound, and a frequency acquisition of acquiring a frequency corresponding to a predetermined feature included in the respiratory sound component. A whistle sound component and an analog sound component included in the respiratory sound component based on a relationship between a step, a frequency corresponding to the predetermined feature, and a threshold value that varies according to the frequency corresponding to the predetermined feature; Determining step.

  According to the respiratory sound analysis method according to the present embodiment, it is possible to suitably discriminate the whistle vocal sound and the analogy sound that are continuous rales, as in the respiratory sound analysis device according to the present embodiment described above.

  In the respiratory sound analysis method according to the present embodiment, various aspects similar to the various aspects of the respiratory sound analysis apparatus according to the present embodiment described above can be employed.

<6>
The computer program according to the present embodiment includes a component acquisition step of acquiring a respiratory sound component including a continuous ra sound from the respiratory sound, and a frequency acquisition step of acquiring a frequency corresponding to a predetermined feature included in the respiratory sound component. And determining a whistle sound component and an analogy sound component included in the respiratory sound component based on a relationship between a frequency corresponding to the predetermined feature and a threshold value varying according to the frequency corresponding to the predetermined feature. And a determination step to be executed by the computer.

  According to the computer program according to the present embodiment, it is possible to cause the computer to execute the same processing as the respiratory sound analysis method according to the present embodiment described above. Can be determined.

  Note that the computer program according to the present embodiment can also adopt various aspects similar to the various aspects of the respiratory sound analyzer according to the present embodiment described above.

<7>
The recording medium according to the present embodiment records the above-described computer program.

  According to the recording medium according to the present embodiment, it is possible to appropriately determine the whistle sound and the like sound that are continuous rales by causing the computer program described above to be executed by a computer.

  The breathing sound analysis apparatus and breathing sound analysis method according to the present embodiment, the operation of the computer program and the recording medium, and other gains will be described in more detail in the following examples.

  Hereinafter, embodiments of a respiratory sound analysis device, a respiratory sound analysis method, a computer program, and a recording medium will be described in detail with reference to the drawings.

<Overall configuration>
First, the overall configuration of the respiratory sound analyzer according to the present embodiment will be described with reference to FIG. FIG. 1 is a block diagram showing the overall configuration of the respiratory sound analysis apparatus according to this embodiment.

  In FIG. 1, the respiratory sound analysis apparatus according to the present embodiment includes, as main components, a biological sound sensor 110, a signal storage unit 120, a signal processing unit 125, a sound output unit 130, a display unit 140, And a processing unit 200.

  The biological sound sensor 110 is a sensor configured to be able to detect a respiratory sound of a biological body. The biological sound sensor 110 includes, for example, an ECM (Electret Condenser Microphone), a microphone using a piezo, a vibration sensor, and the like.

  The signal storage unit 120 is configured as a buffer such as a RAM (Random Access Memory), for example, and temporarily stores a signal indicating a breathing sound detected by the biological sound sensor 110 (hereinafter referred to as “breathing sound signal” as appropriate). To remember. The signal storage unit 120 is configured to be able to output the stored signal to the audio output unit 130 and the processing unit 200, respectively.

  The signal processing unit 125 processes the sound acquired by the biological sound sensor 110 and outputs the processed sound to the audio output unit 130. The signal processing unit 125 functions as, for example, an equalizer or a filter, and processes the acquired sound so that it can be easily heard by a person.

  The audio output unit 130 is configured, for example, as a speaker or a headphone, and outputs a respiratory sound detected by the biological sound sensor 110 and processed by the signal processing unit 125.

  The display unit 140 is configured as a display such as a liquid crystal monitor, for example, and displays image data output from the processing unit 200.

  The processing unit 200 includes a plurality of arithmetic circuits, memories, and the like. The processing unit 200 includes a frequency analysis unit 210, a continuous rale detection unit 220, a peak frequency detection unit 230, a whistle / sound sound determination unit 240, and an image generation unit 250.

  The operation of each unit of the processing unit 200 will be described in detail later.

<Description of operation>
Next, the operation of the respiratory sound analyzer according to the present embodiment will be described with reference to FIG. FIG. 2 is a flowchart showing the operation of the respiratory sound analysis apparatus according to this embodiment.

  In FIG. 2, during the operation of the respiratory sound analysis apparatus according to the present embodiment, first, the biological sound sensor 110 detects the respiratory sound, and the processing unit 200 acquires the respiratory sound signal (step S101).

  When the respiratory sound signal is acquired, frequency analysis (for example, fast Fourier transform) is performed in the frequency analysis unit 210 (step S102). When the frequency analysis is executed, using the result, the continuous rale detection unit 220 detects a component including the continuous rale included in the respiratory sound signal (step S103). Note that the process for detecting continuous rarity may be performed in parallel with the process for detecting breathing sounds other than continuous rarity (for example, normal breathing sounds, other abnormal breathing sounds, etc.). Since each process so far can be performed using a well-known technique, detailed description is abbreviate | omitted.

  When the continuous rarity is detected (step S104: YES), the frequency peak detection unit 230 detects the peak (maximum value) of the component corresponding to the continuous rarity, and the frequency corresponding to the peak position is detected. It is detected as a peak frequency (step S105). In the case of detecting a peak, for example, a frequency having a maximum value in a frequency characteristic region may be obtained at a predetermined time interval (for example, time interval for applying FFT).

  The respiratory sound analysis apparatus according to the present embodiment determines whether the continuous ra sound is a whistle sound or an analog sound based on the peak frequency detected here. Specifically, the peak frequency is compared with a predetermined threshold, and when the peak frequency is higher than the predetermined frequency, it is determined that the sound is a whistle voice, and when the peak frequency is lower than the predetermined frequency, It is determined that the sound is similar. However, in this embodiment, in particular, a value that varies according to the peak frequency is used as a threshold value for determining the whistle voice sound and the like sound. For this reason, in this embodiment, when the peak frequency is detected, the threshold value is determined according to the peak frequency prior to the determination of the whistle voice and the analogy sound (step S106).

  Here, the threshold value determination method described above will be specifically described with reference to FIGS. Here, FIG. 3 is a conceptual diagram showing a problem in the continuous rarity determination according to the comparative example. FIG. 4 is a graph showing the variation of the threshold according to the present embodiment, and FIG. 5 is a table showing specific values of the threshold according to the present embodiment. In addition, the spectrum shown by FIG. 3 is a spectrum of the respiratory sound which notably includes a whistle voice sound in addition to a normal respiratory sound.

  In FIG. 3, the whistle sound and the analogy sound are discriminated by the pitch (that is, the frequency) so that the whistle voice sound is called a high-pitched continuous rale and the analogy sound is called a low-pitched continuous rale. Is possible. However, the peak frequency of the whistle sound and the like sound changes with time. For this reason, in the comparative example in which a single threshold value (that is, one threshold value whose value does not vary) as shown in the figure is used to determine the whistle sound and the analogy sound, the determination result is obtained as time passes. It may change. For example, if the peak frequency changes so as to cross the determination threshold, as in the whistle voice component shown in the figure, what was previously determined as a whistle voice sound is erroneously determined as a similar sound Will be done. For this reason, in the respiratory sound analysis apparatus according to the present embodiment, the threshold value is varied according to the peak frequency.

  As shown in FIGS. 4 and 5, in the respiratory sound analysis apparatus according to the present embodiment, the threshold value fluctuates so that the ratio for determining the whistle sound and the ratio for determining the analogy sound change smoothly according to the peak frequency. To do. For example, when the peak frequency is 200 Hz, it is determined that 7% of whistle sounds are included and 93% of similar sounds are included. When the peak frequency is 250 Hz, it is determined that 50% of whistle sounds are included and 50% of similar sounds are included. When the peak frequency is 280 Hz, it is determined that 78% of whistle sounds are included and 22% of similar sounds are included. The specific numerical values here are merely examples, and different values may be set. Moreover, you may make it have a variation characteristic which changes with sex, age, height, weight, etc. of the biological body which is a measuring object.

  By using the above-described fluctuating threshold, it is possible to suitably prevent erroneous determination that may occur in the case shown in FIG. That is, in the respiratory sound analysis apparatus according to the present embodiment, the threshold value for determining the whistle voice sound and the analogy sound changes so as to become an appropriate value according to the peak frequency. Compared with the case of using, more accurate determination can be performed.

  Returning to FIG. 2, the whistle / sound sound determination unit 240 determines whether the continuous ra sound is a whistle sound or a similar sound using the threshold value that fluctuates as described above ( Step S107). Then, the image generation unit 250 generates an image based on the determination result, and the determination result is displayed on the display unit 140 (step S108). Note that after the analysis result is displayed, it is determined whether or not to continue the analysis (step S109). When it is determined that the analysis is to be continued (step S109: YES), the above-described processing is restarted from step S101. On the other hand, when it is determined not to continue the analysis (step S109: NO), the series of processing ends.

  Here, the display of the analysis result on the display unit 140 will be specifically described with reference to FIGS. 6 and 7. Here, FIGS. 6 and 7 are graphs showing display examples of the continuous rarity determination result according to the present embodiment, respectively.

  As shown in FIG. 6, the ratio of the whistle sound and the analogy sound, which is the analysis result, is displayed on the display unit 150 as a bar graph. However, this display method is an example, and display may be performed in other display modes. For example, you may display the ratio of a whistle voice sound and an analogy sound as a pie chart. Alternatively, the intensity of the whistle voice sound and the analogy sound may be digitized and displayed.

  As shown in FIG. 7, when it is possible to determine sound types other than the whistle voice sound and the like sound (for example, normal breathing sound, water bubble sound, haircut sound, etc.), the ratio of these sound types is also included. You may make it display.

  Note that, instead of or in addition to the above-described output as an image, output by audio data is also possible. Specifically, the voice can be output separately for the whistle sound and the analogy sound. Alternatively, it is possible to emphasize only one of the whistle sound and the like sound and output the sound.

<Specific example of judgment result>
Finally, the advantages of the present embodiment will be described in detail with reference to specific examples of analysis results in FIGS. FIG. 8 is a conceptual diagram showing an example in which the whistle voice sound is analyzed by the breathing sound analyzer according to the present embodiment and the comparative example. FIG. 9 is a conceptual diagram showing an example in which analogy sounds are analyzed by the respiratory sound analysis apparatus according to the present embodiment and the comparative example. In the following, the respiratory sound analysis apparatus according to the present embodiment using a varying threshold (see FIGS. 4 and 5) and the respiratory sound analysis apparatus according to a comparative example using a single threshold (250 Hz), Consider the case of analyzing the spectrum of whistle sounds and similar sounds. In addition, the judgment of a whistle voice sound and an analogy sound shall be performed for every predetermined time interval (time t1-t7).

  As shown in FIG. 8, it is assumed that a whistle voice whose peak frequency decreases from about 350 Hz to about 200 Hz is an analysis target. In this case, in the breathing sound analysis apparatus according to the comparative example, it is accurately determined that the continuous rar sound to be analyzed is a whistle voice from time t1 to t6. However, at time t7, the peak frequency of the whistle voice spectrum is lowered (that is, lower than the threshold value of 250 Hz), so that it is erroneously determined as a similar sound.

  On the other hand, in the respiratory sound analysis apparatus according to the present embodiment, it is accurately determined that the continuous rar sound to be analyzed is a 100% whistle voice from time t1 to t4. Then, although the proportion of the analog sound gradually increases from time t5, it is determined that the whistle sound is included at time t7. That is, the present embodiment can present a result that there is a possibility that a whistle voice is also included in the comparative example in which the determination is completely wrong at time t7.

  As shown in FIG. 9, it is assumed that an analogy sound whose peak frequency increases from about 240 Hz to about 260 Hz and then decreases to about 180 Hz is an analysis target. In this case, in the breathing sound analysis apparatus according to the comparative example, it is accurately determined that the continuous rale to be analyzed is an analogy sound from time t1 and t4 to t7. However, at times t2 and t3, the peak frequency of the spectrum of the analogy sound temporarily rises (that is, exceeds the threshold value of 250 Hz), so that it is erroneously determined as a whistle sound.

  On the other hand, in the respiratory sound analysis apparatus according to the present embodiment, it is continuously determined that analogy sounds are included at times t2 and t3 when the peak frequency increases. That is, the present embodiment can present a result that there is a possibility that similar sounds may also be included in the comparative example in which the determination is completely wrong at the times t2 and t3.

  As described above, according to the respiratory sound analysis apparatus according to the present embodiment, it is possible to more appropriately determine the whistle voice sound and the analogy sound by using the threshold value that varies according to the peak frequency.

  The present invention is not limited to the above-described embodiment, and can be appropriately changed without departing from the spirit or idea of the invention that can be read from the claims and the entire specification, and respiratory sound analysis accompanying such changes The apparatus, the respiratory sound analysis method, the computer program, and the recording medium are also included in the technical scope of the present invention.

DESCRIPTION OF SYMBOLS 110 Body sound sensor 120 Signal memory | storage part 125 Signal processing part 130 Audio | voice output part 140 Display part 200 Processing part 210 Frequency analysis part 220 Continuation ra sound detection part 230 Peak frequency detection part 240 Whistle / sound sound determination part 250 Image generation Part

Claims (5)

Component acquisition means for acquiring a respiratory sound component including a continuous ra sound from the respiratory sound;
Frequency acquisition means for acquiring a frequency corresponding to a predetermined characteristic included in the respiratory sound component;
Output means for, based on the frequency corresponding to the predetermined characteristic, and outputs the ratio between the whistle vocal component and Ruiibiki sound component contained in the breath sound components,
Equipped with a,
The output means outputs the ratio so that the higher the frequency, the higher the ratio of the whistle voice component included and the lower the ratio of the analogy sound component. apparatus.   The respiratory sound analysis apparatus according to claim 1, wherein the predetermined feature is a local maximum value. A component acquisition step of acquiring a respiratory sound component including a continuous ra sound from the respiratory sound;
A frequency acquisition step of acquiring a frequency corresponding to a predetermined feature included in the respiratory sound component;
An output step based on the frequency corresponding to the predetermined characteristic, and outputs the ratio between the whistle vocal component and Ruiibiki sound component contained in the breath sound components,
Equipped with a,
In the output step, as the frequency is higher, the ratio of the whistle sound component is increased, and the ratio is output so that the ratio of the analogy sound component is decreased. Method. A component acquisition step of acquiring a respiratory sound component including a continuous ra sound from the respiratory sound;
A frequency acquisition step of acquiring a frequency corresponding to a predetermined feature included in the respiratory sound component;
An output step based on the frequency corresponding to the predetermined characteristic, and outputs the ratio between the whistle vocal component and Ruiibiki sound component contained in the breath sound components,
To the computer ,
In the output step, the ratio is output such that the higher the frequency, the higher the ratio of the whistle sound component included and the lower the ratio of the analogy sound component . A recording medium in which the computer program according to claim 4 is recorded.