JP4904488B2 - Lung sound diagnostic device - Google Patents

Description

The present invention relates to a preferred lung sounds diagnostic equipment is applied to collect lung sounds of patients, for example, in a medical institution.

  Conventionally, when a doctor diagnoses lung sounds in a medical institution, the doctor listens to the lung sounds directly by placing a stethoscope on the patient's chest, and the doctor himself judges whether the heard lung sounds are normal. . Such a conventional method of directly listening and judging depends largely on the experience of the doctor, and there is a problem that the diagnosis results vary depending on the skill of the doctor who makes the diagnosis. On the other hand, various proposals have been made in the past for taking lung sounds as data into an apparatus and analyzing them automatically for diagnosis.

Patent Document 1 discloses one example of a technique for capturing and analyzing heart sounds, lung sounds, and the like as data.
JP 2005-296634 A

  By the way, if you prepare a diagnostic device that automatically diagnoses lung sounds, incorporates the lung sounds into the prepared diagnostic device, and diagnoses the lung sounds with the diagnostic device, input to the diagnostic device It is conceivable that the lung sound signal to be picked up is picked up by a microphone attached to a stethoscope, for example. The lung sound signal picked up by the microphone is converted into data as in the case of processing the audio signal in the audible band in the diagnostic apparatus, and the presence or absence of abnormality is determined from the processed data. Here, since the lung sound signal itself is a signal picked up by a microphone attached to the stethoscope, there is a problem that noise is easily mixed in the signal.

  That is, the state of picking up the lung sound signal changes depending on the position of the stethoscope hitting the patient's chest and how it is applied, and the lung sound signal is not always captured in an optimal state. If the picked-up state is not appropriate, noise is mixed in the captured lung sound signal, and normal determination cannot be made.

  The present invention has been made in view of this point, and an object of the present invention is to eliminate the influence of noise and to make a good diagnosis when collecting and diagnosing lung sounds.

The present invention collects lung sound data as a plurality of breath sounds when collecting the lung sounds of the person to be measured and diagnosing the collected lung sounds. The data is divided into predetermined units to be segmented, and the presence or absence of abnormality is diagnosed for each divided segment, and the segment diagnosed as abnormal by this diagnosis is not less than a preset number of times among the plurality of times. When the breathing sound is in the same segment position, the diagnosis with abnormality is made effective.

  According to the present invention, the data of multiple breath sounds are segmented and individually diagnosed, and when the individual diagnosis results are abnormal multiple times at the same segment position, the location is regarded as abnormal. Even if it is diagnosed that a specific segment position is temporarily abnormal due to noise due to the diagnosis, if there is a case where it is diagnosed that the part is normal, the normal diagnosis result is adopted. As a result, erroneous diagnosis due to noise can be effectively eliminated.

  In this case, segmentation is performed by dividing a single exhalation section into a plurality of segments and by dividing a single inspiration section into a plurality of segments, so that one exhalation and inspiration can be divided finely. Diagnosis can be performed and diagnostic accuracy is improved.

  In addition, by comprehensively judging the diagnosis results for each segment and judging the abnormality of the subject's lungs, the state of the subject's lungs can be determined from the detailed diagnosis for each segment. It becomes possible to diagnose accurately.

  Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.

  FIG. 1 is a diagram showing an example of a lung sound collection state in this example. In this example, the lung sound of the person to be measured a (patient) is collected and diagnosed by the lung sound diagnosis apparatus 20 by the operation of the doctor b. The stethoscope 10 possessed by the doctor b is equipped with a microphone 11, and a sound (lung sound) picked up by the microphone 11 is input to the lung sound diagnosis apparatus 20. The stethoscope 10 has a microphone 11 attached in the vicinity of a distal end portion of a stethoscope of a general configuration in which the doctor b listens to lung sounds. Even when the lung sound diagnosis apparatus 20 collects lung sounds, the normal diagnosis is performed. It is also possible for the doctor b to listen to the lung sound in the same way. However, it may be configured exclusively for collection in the lung sound diagnosis apparatus 20 so that only the microphone 11 is brought into direct contact with the patient's chest and collected.

  The lung sound diagnosis apparatus 20 is composed of, for example, a computer apparatus and its peripheral devices, and displays an image for instructing an operation on a display 21 connected to the computer apparatus. Software (program) for functioning as a lung sound diagnosis apparatus is installed in the computer apparatus. The software executes an operation process shown in the flowchart of FIG. 3 to be described later, and reference data for diagnosing lung sounds is also prepared in advance. For the operation, for example, a keyboard 22 connected to a computer device is used. With this configuration, the doctor b looks at the image displayed on the display 21 and performs a lung sound collection operation. As will be described later, the display 21 displays an image indicating a point for collecting lung sounds.

  FIG. 2 is a diagram showing a configuration example of the lung sound diagnosis apparatus 20 of the present example. The output signal of the microphone 11 attached to the stethoscope 10 is supplied to the characteristic adjustment unit 24, and signal adjustment (correction) processing according to the type and individual characteristics of the stethoscope 10 is performed. As the signal adjustment processing, for example, correction of frequency characteristics is performed. The lung sound signal processed by the characteristic adjusting unit 24 is supplied to an analog / digital converter 25, and is sampled into digital data by sampling at a constant period. As the sampling period, for example, a period of 0.1 milliseconds is used.

  The digital data converted by the analog / digital converter 25 is supplied to the fast Fourier transformer 26, and the time axis is converted to the frequency axis by fast Fourier transform (FFT) calculation. As processing for conversion to the frequency axis, for example, data at 50 Hz intervals in a range from 50 Hz to 5000 Hz, and data indicating how much signal components at each frequency position exist within a certain time. That is, for example, if the waveform data of the input lung sound is, for example, the waveform shown on the time axis shown in FIG. 6A, it is shown by the level for each frequency as shown in FIG. 6B by Fourier transform. Converted to data. Here, in the case of this example, the waveform data of the segment unit described later is converted and processed.

  The Fourier-transformed data is supplied to the data processing unit 27 for data analysis processing. The analyzed data is stored in the memory 28. The memory 28 also stores lung sound data which is a reference necessary for diagnosis of lung sounds. Here, in the case of this example, the reference lung sound data is stored as data for each segment obtained by dividing one expiration and inspiration period into a plurality of periods (four periods in the example described later). is there. The memory 28 may use other storage means such as a hard disk.

  Data analysis processing in the data processing unit 27 is executed under the control of the control unit 30. Operation information of the keyboard 22 that performs operations such as start and stop of lung sound acquisition is also supplied to the control unit 30, and the control unit 30 controls each unit based on the operation information.

  The lung sound diagnosis apparatus 20 of this example includes a display control unit 29 and supplies display data created by the display control unit 29 to a display 21 connected (or built in) to the lung sound diagnosis apparatus 20. Thus, an image or the like can be displayed. The display on the display 21 by the display control unit 29 is also executed under the control of the control unit 30.

  Next, a processing example in which lung sounds are collected by the lung sound diagnosis apparatus 20 of this example and the collected lung sounds are diagnosed will be described with reference to the flowchart of FIG. First, the control unit 30 determines whether or not there is a start operation for taking in lung sounds by a keyboard operation or the like (step S11). If it is determined here that there is a start operation, at least three breathing sounds are collected here. That is, a breathing sound due to the first expiration and inspiration is collected (step S12), a breathing sound due to the second expiration and inspiration is collected (step S13), and a breathing sound due to the third expiration and inspiration. Is collected (step S14). When breathing sounds up to the third breath are collected, the expiration data and the inspiration data are segmented (step S15). In this segmentation process, for example, one exhalation period is divided into four periods, one inspiration period is divided into four periods, and each divided period is defined as one segment.

  When this segmentation is performed, each segment period data is compared with reference data prepared for the segment period, and a pass / fail determination for each segment is performed based on a search for similar reference data ( Step S16). At the time of this pass / fail judgment, for example, when similarity with lung sound data of normal lungs without disease is detected, it is determined that normal, and similarity with lung sound data of diseased lungs is detected Diagnose that there is a possibility of the disease and that there is an abnormality. In addition, when there is no similar reference data, it is determined that there is an abnormality. If there is no similar reference data, in addition to the case of some pulmonary disease, some noise may be mixed during the process of acquiring the measured lung sound, and it may be diagnosed that there is an abnormality.

  Then, after performing the pass / fail determination for each segment, it is determined whether or not the same specific segment position is diagnosed as abnormal in all breathing periods within the three breathing periods taken in. (Step S17). Here, if only one or two of the same segment positions are abnormal, or if it is determined that there is no abnormality in all breathing periods for the same segment period, The lung sound data is diagnosed as having no abnormality (step S18). And if the same specific segment position is diagnosed as abnormal in all three data, it is determined that the corresponding segment period is abnormal. Based on the disease name in the reference data, a diagnosis for estimating the content of the abnormality (disease name) is performed (step S19). If there is no similar reference data and all the same segment positions are abnormal, it is determined that there is a high possibility of an import error.

  Here, an example of processing of three actually acquired lung sound data will be described with reference to FIG. 4A, 4B, and 4C are waveform examples of lung sound data of the first breath, the second breath, and the third breath, respectively. Each lung sound data can be divided into an expiration period and an inspiration period. The boundary between the expiration period and the inspiration period is set based on a period in which the silence period continues to some extent. In this example, each of the expiration period and the inspiration period is divided into four. Here, the exhalation period is divided into four almost equally by the length of time, and the periods A1, A2, A3, A4 are set, and the inhalation period is also divided almost equally by four by the length of time, and the period B1 , B2, B3, B4 are set.

  The example of each breathing period in the example of FIG. 4 will be described. First, for the first breath, as shown in FIG. 4 (a), there is an abnormality in the periods A2, A3 of the inspiratory periods A1, A2, A3, A4. Assume that it has been determined. In this example, the abnormality in the period A2 is an abnormality due to noise, and the abnormality in the period A3 is an abnormality due to an abnormal sound (that is, an abnormal sound that may be some disease indicated by the reference data). Further, it is assumed that an abnormality is determined in the periods B3 and B4 in the expiration periods B1, B2, B3 and B4. In this example, the abnormality in the period B3 is an abnormality that may be some disease, and the abnormality in the period B4 is an abnormality due to noise.

  Next, as shown in FIG. 4B for the second breath, it is assumed that an abnormality is determined in the periods A1, A3 of the inspiratory periods A1, A2, A3, A4. In this example, the abnormality in the period A1 is an abnormality due to noise, and the abnormality in the period A3 is an abnormality that may be some disease. Further, it is assumed that an abnormality is determined in the periods B2 and B3 in the expiration periods B1, B2, B3, and B4. In this example, the abnormality in the period B1 is an abnormality due to noise, and the abnormality in the period B3 is an abnormality that may be some disease.

  Further, as shown in FIG. 4C for the third breath, it is assumed that an abnormality is determined in the periods A1, A3 of the inspiratory periods A1, A2, A3, A4. In this example, the abnormality in the period A1 is an abnormality due to noise, and the abnormality in the period A3 is an abnormality that may be some disease. Further, it is assumed that an abnormality is determined in the period B3 among the expiration periods B1, B2, B3, and B4. In this example, the abnormality in the period B3 is an abnormality that may be some disease.

  When the diagnosis results of FIG. 4 are summarized in a table, the state shown in FIG. 5 is obtained. As shown in FIG. 5, segment periods that are abnormal in any one of the three breathing periods include inspiratory periods A1, A2, and A3 and expiratory periods B1, B2, B3, and B4. is there. Here, in terms of the intake period, the intake periods A1 and A2 are abnormal only once or twice, and only the intake period A3 is an abnormal period that is continuous for three times. Similarly, in regard to the expiration period, the expiration periods B2 and B3 are abnormal only once or twice, and only the inspiration period B3 is an abnormal period that is continuous for three times.

  Here, by performing the processing shown in the flowchart of FIG. 3, in the case of this example, for the inspiratory period, only the period A3 that is abnormal for three consecutive times is finally determined as the abnormal period, and the expiratory period is determined. Finally determines only the period B3 that is abnormal three times continuously as an abnormal period, and estimates the abnormal contents based on the name of the disease diagnosed as those abnormal periods. When estimating the abnormal content, it is possible to comprehensively determine which segment period of the four segments of exhalation and inspiration is abnormal, and determine the estimated disease name.

  As reference data necessary for making a diagnosis, for example, as shown in FIG. 7A, as a normal breathing sound data, a large number of data d11, d12, d13... 20 is stored. Further, as shown in FIG. 7B, for example, as the abnormal breathing sound data, a large number of data d21, d22, d23... Are prepared for each segment and stored in the diagnostic apparatus 20, and each segment is stored. Diagnosis such as disease name is performed by determining which data is similar.

  As described above, according to the lung sound diagnosis apparatus of the present example, when capturing lung sounds, a plurality of breath sounds are captured, and the captured breath sounds are segmented into fine segments for diagnosis. By making a diagnosis that there is a corresponding abnormality when the result appears continuously in all breaths, erroneous determination due to the influence of noise can be effectively prevented.

  In addition, the setting example of the division segment shown in FIG. 4 shows an example, and is not limited to such four divisions. Further, the number of times the respiratory data is taken is also set to 3 times in the above-described embodiment, but may be set to 2 times or more. Furthermore, in the above-described embodiment, in the data of a plurality of respiratory sounds, when there is an abnormality in the same segment (same location) for all the respiratory sounds, for example, If it can be considered that it is almost all of the breathing sound, it may be diagnosed that there is an abnormality. For example, five breathing sounds may be taken and a segment in which an abnormality is detected in four of them may be diagnosed as having an abnormality.

  In the above-described embodiment, an example in which the lung sound diagnosis apparatus is configured using a computer device has been described. However, the lung sound diagnosis apparatus may be configured as a dedicated lung sound capturing apparatus. Further, software (programs) necessary for using a computer device may be distributed via the Internet or the like in addition to being stored in various storage media such as a disk.

It is explanatory drawing which shows the example of the lung sound collection state by one embodiment of this invention. It is a block diagram which shows the system configuration example by one embodiment of this invention. It is a flowchart which shows the process example by one embodiment of this invention. It is explanatory drawing which shows the waveform and the example of a diagnostic result in the segment unit in each respiration period by one embodiment of this invention. It is explanatory drawing which put together the diagnostic result of the example of FIG. It is explanatory drawing which showed the example of a waveform by one embodiment of this invention. It is explanatory drawing which showed the example of the database by one embodiment of this invention.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 10 ... Stethoscope, 11 ... Microphone, 20 ... Lung sound diagnostic apparatus, 21 ... Display, 22 ... Keyboard, 24 ... Characteristic adjustment part, 25 ... Analog-digital converter, 26 ... Fast Fourier transform, 27 ... Data processing part , 28 ... Memory, 29 ... Display control unit, 30 ... Control unit, a ... Examination subject, b ... Doctor

Claims (3)

In the lung sound diagnostic apparatus that collects the lung sounds of the subject and diagnoses the collected lung sounds,
Means for capturing lung sound data as a plurality of breath sounds;
Division means for dividing the lung sound data from a plurality of breaths taken in by the taking-in means into segments by dividing them into predetermined units;
Each segment divided by the dividing unit is diagnosed as to whether or not there is an abnormality, and the segment diagnosed as abnormal by this diagnosis is located at the same segment position of the respiratory sound more than the preset number of times among the plurality of times. In some cases, a lung sound diagnostic apparatus comprising diagnostic means for validating the diagnosis of abnormality. The lung sound diagnosis apparatus according to claim 1,
The division by the dividing means divides a period of one exhalation into a plurality of segments and divides a period of one inspiration into a plurality of segments. The lung sound diagnosis apparatus according to claim 1,
The diagnosing device according to claim 1, wherein the diagnosing means comprehensively determines a diagnosis result for each of the segments to determine abnormality of the lungs of the measurement subject.

Images