CN113331862A - Online detection method, device and system for multiple lung sounds - Google Patents
Online detection method, device and system for multiple lung sounds Download PDFInfo
- Publication number
- CN113331862A CN113331862A CN202110524309.0A CN202110524309A CN113331862A CN 113331862 A CN113331862 A CN 113331862A CN 202110524309 A CN202110524309 A CN 202110524309A CN 113331862 A CN113331862 A CN 113331862A
- Authority
- CN
- China
- Prior art keywords
- lung
- sound
- lung sound
- wave band
- segment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
- A61B7/02—Stethoscopes
- A61B7/04—Electric stethoscopes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B7/00—Instruments for auscultation
- A61B7/003—Detecting lung or respiration noise
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Pulmonology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses a method, a device and a system for online detection of multiple lung sounds, wherein the method comprises the following steps: sending an acquisition instruction, and simultaneously acquiring a plurality of lung sound segments; each lung sound segment is independent; marking each lung sound segment, and comparing with a preset lung sound segment library to determine a corresponding holder file; digitally converting each lung sound segment and forming a corresponding audio frequency recording graph; comparing the audio frequency recording graphs on line, and comparing the wave bands in the same time; if more than two wave bands are relatively similar, selecting a valley peak, a valley bottom and a middle section of the wave band to carry out independent comparison, extending the trend of the wave band, and carrying out trend comparison to determine a corresponding holder; and comparing one wave band with a lung sound record library of a relatively similar holder based on the relatively similar wave band, and overlapping the wave band and the corresponding trend of the wave band to determine the pathological stage of the lung sound.
Description
Technical Field
The invention relates to the technical field of on-line detection of lung sounds, in particular to a method, a device and a system for on-line detection of a plurality of lung sounds.
Background
The detection of the lungs is performed individually and requires a separate space, and in the related art, the sound of a single lung is easily mixed with the sound of other lungs, and it is difficult to perform the detection at the same time.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, and provides a method, a device and a system for detecting a plurality of lung sounds on line, wherein a plurality of lung sound segments are detected simultaneously, the detection of the plurality of lung sound segments is independent detection, one band is compared with a lung sound record library of a holder which is relatively approximate based on the relatively approximate band, the band and the corresponding trend of the band are overlapped to determine the pathological stage of the lung sound, so that the individual detection and diagnosis of the plurality of sound segments are realized, and the holder marking is carried out on the plurality of sound segments to facilitate the identification and diagnosis of the subsequent sound segments, thereby improving the convenience of the diagnosis of the plurality of sound segments.
In order to solve the above technical problem, an embodiment of the present invention provides an online detection method for multiple lung sounds, where the method includes: sending an acquisition instruction, and simultaneously acquiring a plurality of lung sound segments; each lung sound segment is independent; marking each lung sound segment, and comparing with a preset lung sound segment library to determine a corresponding holder file; digitally converting each lung sound segment and forming a corresponding audio frequency recording graph; comparing the audio frequency recording graphs on line, and comparing the wave bands in the same time; if more than two wave bands are relatively similar, selecting a valley peak, a valley bottom and a middle section of the wave band to carry out independent comparison, extending the trend of the wave band, and carrying out trend comparison to determine a corresponding holder; and comparing one wave band with a lung sound record library of a relatively similar holder based on the relatively similar wave band, and overlapping the wave band and the corresponding trend of the wave band to determine the pathological stage of the lung sound.
Optionally, the acquiring instruction is sent, and a plurality of lung sound segments are acquired simultaneously; each lung sound segment is independent, includes: each detection channel is shunted to the lung of the corresponding detector and is concentrated in the same system; sending an acquisition instruction by the system, and simultaneously acquiring a plurality of lung sound segments; the corresponding lung sound segments are conveyed by the corresponding detection channels; the detection channel is connected with a corresponding sound containing space, and the lung sound segments are stored and discriminated through the sound containing space; the sound containing spaces do not resonate with each other, so that the lung sound segments are detected independently and independently; detecting two ends of the lung sound segment and local wavelengths of the lung sound segment, and determining the volume sound type of the lung sound segment; the volume sound type matching based on the lung sound segment corresponds to the volume sound space, the volume sound space is provided with a plurality of volume sound spaces, and the volume sound spaces are selected based on the volume sound type selection of the lung sound segment.
Optionally, the marking each lung sound segment and comparing with a preset lung sound segment library to determine a corresponding holder file includes: obtaining an effective circulation period from the lung sound segment; acquiring a test wave in a preset position in the cycle period; collecting the interval time between the highest point and the lowest point in the test wave, and comparing the interval time with the corresponding time in the preset lung sound segment library to preliminarily determine a plurality of holder files; extracting specific waves from a plurality of holder files, and comparing the specific waves with the test waves one by one to obtain a plurality of similar ratios; the highest similar ratio and the lowest similar ratio are excluded from the similar ratios, and the characteristic waves corresponding to the rest similar ratios are placed in different environments for characteristic testing so as to obtain the tone corresponding to the characteristic waves; and comparing the plurality of tones with corresponding tones in the preset lung sound segment library to determine matching tones so as to determine corresponding holder files.
Optionally, the comparing, based on the relatively approximate bands, one of the bands with a lung sound record library of a relatively approximate holder, and overlapping trends corresponding to the bands and the bands to determine a pathological stage where the lung sound is located includes: acquiring the relatively approximate band; collecting approximate waves from the relatively approximate wave bands, and marking turning segments of the approximate waves one by one; calculating interval time and wave band energy between the turning sections, and comparing the interval time and the corresponding wave band energy with a lung sound record library of a holder which is relatively similar to the interval time so as to determine a plurality of turning sections which meet a preset similar range; comparing wave bands corresponding to the turning sections with preset wave bands in the lung sound recording library, and overlapping the wave bands and trends corresponding to the wave bands to preliminarily determine abnormal wave bands; intercepting the abnormal wave band, and carrying out duplicate removal processing on the abnormal wave band to form an optimized wave band; inputting the optimized wave band into a preset disease learning model, and outputting a corresponding pathology; and if the pathology is multiple, inputting the optimized wave band into the record map learning model, forming a corresponding pathology track, determining the final pathology according to the pathology track, and taking the final pathology as the lung disease type.
Optionally, the method further includes: collecting lung sound segments corresponding to the current pathological record chart; constructing an echo section corresponding to the lung sound section corresponding to the current pathological record chart, and performing echo adjustment based on a transmitted lung contour; constructing a lung 3D model based on the lung sound segment and the echo segment, and performing contour adjustment based on the transmitted lung contour; acquiring a sound wave band corresponding to the lung disease type, and mapping a corresponding abnormal lung sound segment; and acquiring a vocal tract region adjacent to the abnormal lung vocal tract, simulating a corresponding output position in the 3D lung model, and marking the output position.
Optionally, the acquiring a vocal tract region adjacent to the abnormal lung vocal tract, simulating a corresponding output position on the 3D lung model, and implementing a marking of the output position includes: capturing sound segment areas adjacent to the abnormal lung sound segments, and sequentially arranging the sequence numbers of the areas; marking the corresponding region and the serial number of the lung 3D model; enclosing a corresponding region of the lung 3D model, and performing bright color processing to determine a colorless region; and freezing the colorless area as the output position and marking.
Optionally, the method further includes: traversing the colorless areas and determining the number of the colorless areas; if the colorless areas are multiple and the colorless areas are mutually spaced, judging the final area; carrying out color change treatment on adjacent areas of the colorless area, and carrying out depth marking according to wave band energy corresponding to the adjacent areas; playing sound segments of sound segment areas adjacent to the abnormal lung sound segment, and extending the field along with the playing; gradually delineating a corresponding area along with the extension of the field, judging the similarity of the corresponding area and the colorless areas, and comparing the corresponding area and the colorless areas based on the turning contour of the colorless areas to determine the final area.
Optionally, the method further includes: performing neural network transformation on the lung 3D model, and giving parameter values of all regions of the lung 3D model; acquiring an influence value of the external influence on the lung, and marking a corresponding area of the influence; superposing the influence value and the parameter value of the corresponding area to change the actual parameter value of the corresponding area; evolving corresponding regional variations of the 3D model of the lung according to the actual parameter values; and acquiring the change of the corresponding region of the lung 3D model, and displaying the deterioration degree of the corresponding region through time deduction so as to warn the corresponding region.
In addition, an embodiment of the present invention further provides an online detection device for a plurality of lung sounds, where the device includes: an acquisition module: the device is used for sending an acquisition instruction and simultaneously acquiring a plurality of lung sound segments; each lung sound segment is independent; a marking module: the system is used for marking each lung sound segment and comparing the lung sound segment with a preset lung sound segment library to determine a corresponding holder file; a conversion module: the device is used for digitally converting each lung sound segment and forming a corresponding audio frequency recording graph; a comparison module: the audio frequency recording graphs are used for online comparison, and the wave bands in the same time are compared; a selecting module: if more than two wave bands are relatively similar, selecting a valley peak, a valley bottom and a middle section of the wave band to carry out independent comparison, extending the trend of the wave band, and carrying out trend comparison to determine a corresponding holder; a determination module: the method is used for comparing one wave band with a lung sound record library of a relatively similar holder based on the relatively similar wave band, and overlapping the wave band and the corresponding trend of the wave band to determine the pathological stage of the lung sound.
In addition, an embodiment of the present invention further provides an online detection system for a plurality of lung sounds, where the system includes: the system comprises an all-in-one machine screen, a computer and a color analyzer; the computer is connected with the screen of the all-in-one machine based on an HDMI (high-definition multimedia interface); the computer is connected with the color analyzer based on a USB interface; the color analyzer is in signal connection with the screen of the all-in-one machine; wherein the content of the first and second substances,
the system is configured for performing the above-described method of online detection of a plurality of lung sounds.
In the embodiment of the present invention, by the method in the embodiment of the present invention, a plurality of lung sound segments are detected simultaneously, and the detection of the plurality of lung sound segments is detected independently, and a band is compared with a lung sound record library of a relatively similar holder based on the relatively similar band, and trends corresponding to the band and the band are overlapped to determine a pathological stage where the lung sound is located, so that individual detection and diagnosis of the plurality of sound segments are realized, and holder marking is performed on the plurality of sound segments to facilitate identification and diagnosis of subsequent sound segments, thereby improving convenience in diagnosis of the plurality of sound segments.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for online detection of a plurality of lung sounds in an embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a system for online detection of multiple lung sounds according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a system for online detection of multiple lung sounds in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Examples
Referring to fig. 1, fig. 1 is a schematic flow chart of an online detection method of multiple lung sounds in an embodiment of the present invention.
As shown in fig. 1, a method for online detection of a plurality of lung sounds, the method comprising:
s11: sending an acquisition instruction, and simultaneously acquiring a plurality of lung sound segments; each lung sound segment is independent;
in the specific implementation process of the invention, the specific steps can be as follows: each detection channel is shunted to the lung of the corresponding detector and is concentrated in the same system; sending an acquisition instruction by the system, and simultaneously acquiring a plurality of lung sound segments; the corresponding lung sound segments are conveyed by the corresponding detection channels; the detection channel is connected with a corresponding sound containing space, and the lung sound segments are stored and discriminated through the sound containing space; the sound containing spaces do not resonate with each other, so that the lung sound segments are detected independently and independently; detecting two ends of the lung sound segment and local wavelengths of the lung sound segment, and determining the volume sound type of the lung sound segment; the volume sound type matching based on the lung sound segment corresponds to the volume sound space, the volume sound space is provided with a plurality of volume sound spaces, and the volume sound spaces are selected based on the volume sound type selection of the lung sound segment.
The lung sound segments are stored through the corresponding sound containing space, mechanical energy can detect and diagnose the lung sound segments in the space, and in addition, the sound containing space can be adjusted in adaptability according to the sound containing types of the lung sound segments, so that the storage and detection efficiency of the lung sound segments are improved, and the singleness of the lung sound segments is ensured.
S12: marking each lung sound segment, and comparing with a preset lung sound segment library to determine a corresponding holder file;
in the specific implementation process of the invention, a corresponding preset lung sound segment library is formed through the previous lung sound segments, the holders are continuously tracked to form a complete lung sound segment library, the holders of the lung sound segments are determined by comparing each lung sound segment with the preset lung sound segment library, and the holders are compared with each other to avoid the repetition of the holders and ensure the uniqueness of the lung sound segments in the detection process.
In addition, the marking each lung sound segment and comparing with a preset lung sound segment library to determine a corresponding holder file includes: obtaining an effective circulation period from the lung sound segment; acquiring a test wave in a preset position in the cycle period; collecting the interval time between the highest point and the lowest point in the test wave, and comparing the interval time with the corresponding time in the preset lung sound segment library to preliminarily determine a plurality of holder files; extracting specific waves from a plurality of holder files, and comparing the specific waves with the test waves one by one to obtain a plurality of similar ratios; the highest similar ratio and the lowest similar ratio are excluded from the similar ratios, and the characteristic waves corresponding to the rest similar ratios are placed in different environments for characteristic testing so as to obtain the tone corresponding to the characteristic waves; and comparing the plurality of tones with corresponding tones in the preset lung sound segment library to determine matching tones so as to determine corresponding holder files, thereby improving the accuracy of the holder.
S13: digitally converting each lung sound segment and forming a corresponding audio frequency recording graph;
in the specific implementation process of the invention, the specific steps can be as follows: establishing a coordinate schematic diagram corresponding to the lung sound segments, and marking the lung sound energy and time; recording an audio recording of at least one loop segment; inputting the audio recording diagram into a recording diagram learning model, and supplementing corresponding trend parts at the head and the tail of the audio recording diagram to form an audio recording diagram with a trend; the record chart learning model is formed by learning the conventional audio record chart, and realizes the corresponding trend of adjusting the audio record chart in the adjustment of the matching rate of the audio record chart; the trend parts corresponding to the head and tail supplements of the audio frequency recording chart are leveled in the same horizontal direction, the trend of the audio frequency recording chart is extended through the recording chart learning model, the trend is convenient to further confirm the pathology, so that the accuracy of pathological detection is improved, and in addition, the trend parts corresponding to the head and tail supplements of the audio frequency recording chart are leveled in the same horizontal direction, so that an annular trend logic is formed, and the subsequent comparative analysis is convenient.
S14: comparing the audio frequency recording graphs on line, and comparing the wave bands in the same time;
in the specific implementation process of the invention, the specific steps can be as follows: dividing the audio record into a plurality of wave bands and analyzing the plurality of wave bands; carrying out horizontal scribing treatment on each wave band, and marking audio frequency points at the same position to record repeated interval time; if a plurality of interval time exist, selecting the interval time which accords with a preset interval range as an effective time period; marking an initial point and a final point in the audio recording diagram based on two ends of the effective time period; the final point and the initial point are superposed in the horizontal direction, effective pathological wave bands are selected conveniently by analyzing each wave band one by one, and the pathological wave bands are locally determined by limiting the interval time, so that effective pathological sound bands and intervals are captured conveniently, and the accuracy of pathological detection is further improved.
S15: if more than two wave bands are relatively similar, selecting the valley peak, the valley bottom and the middle section of the wave band to carry out independent comparison, extending the trend of the wave band, and carrying out trend comparison to determine the corresponding holder.
S16: and comparing one wave band with a lung sound record library of a relatively similar holder based on the relatively similar wave band, and overlapping the wave band and the corresponding trend of the wave band to determine the pathological stage of the lung sound.
In the specific implementation process of the invention, the specific steps can be as follows: acquiring the relatively approximate band; collecting approximate waves from the relatively approximate wave bands, and marking turning segments of the approximate waves one by one; calculating interval time and wave band energy between the turning sections, and comparing the interval time and the corresponding wave band energy with a lung sound record library of a holder which is relatively similar to the interval time so as to determine a plurality of turning sections which meet a preset similar range; comparing wave bands corresponding to the turning sections with preset wave bands in the lung sound recording library, and overlapping the wave bands and trends corresponding to the wave bands to preliminarily determine abnormal wave bands; intercepting the abnormal wave band, and carrying out duplicate removal processing on the abnormal wave band to form an optimized wave band; inputting the optimized wave band into a preset disease learning model, and outputting a corresponding pathology; and if the pathology is multiple, inputting the optimized wave band into the record map learning model, forming a corresponding pathology track, determining the final pathology according to the pathology track, and taking the final pathology as the lung disease type.
The method comprises the steps of simultaneously detecting a plurality of lung sound segments, independently detecting the lung sound segments, comparing a wave band with a lung sound record library of a relatively approximate holder based on the relatively approximate wave band, and overlapping the corresponding trend of the wave band and the wave band to determine the pathological stage of the lung sound, so that the individual detection and diagnosis of the lung sound segments are realized, and the holder marking is carried out on the lung sound segments, so that the identification and diagnosis of the subsequent lung sound segments are facilitated, and the convenience of the diagnosis of the lung sound segments is improved.
Furthermore, the method for detecting a plurality of lung sounds on line further includes: playing the lung sound segments and marking the corresponding sound segment types; amplifying the first sound segment type corresponding to the lung sound, and synchronously and gradually reducing the second sound segment type corresponding to the non-lung sound; when the second sound segment type is lower than a preset disappearance threshold, freezing the first sound segment type; and performing ratio processing on the final lung sound energy of the first sound segment type and the final lung sound energy of the second sound segment type, performing synchronous optimization on a trajectory graph corresponding to the first sound segment type according to the ratio to determine an audio frequency recording graph corresponding to the lung sound segment, filtering out the influence of noise from the audio frequency recording graph, and calling back the band of the lung sound to reduce the distortion of the lung sound caused by the noise.
Optionally, the corresponding noise section is sorted by the past lung noise, and the sound which accords with the noise section in the lung sound section is processed separately, the corresponding noise section is extracted, the original lung sound section is fitted, the complete lung sound section is ensured on the premise of eliminating noise, and further analysis and processing of the lung sound section are ensured.
In addition, the method for detecting the lung sounds on line further comprises the following steps: collecting lung sound segments corresponding to the current pathological record chart; constructing an echo section corresponding to the lung sound section corresponding to the current pathological record chart, and performing echo adjustment based on a transmitted lung contour; constructing a lung 3D model based on the lung sound segment and the echo segment, and performing contour adjustment based on the transmitted lung contour; acquiring a sound wave band corresponding to the lung disease type, and mapping a corresponding abnormal lung sound segment; and acquiring a vocal tract region adjacent to the abnormal lung vocal tract, simulating a corresponding output position in the 3D lung model, and marking the output position.
By establishing the lung 3D model simulation, and marking the pathological position based on the lung 3D model simulation, pathological operation is carried out on the lung 3D model, and the pathological area is obviously displayed.
Specifically, the acquiring a vocal tract region adjacent to the abnormal lung vocal tract, simulating a corresponding output position on the 3D lung model, and implementing the marking of the output position includes: capturing sound segment areas adjacent to the abnormal lung sound segments, and sequentially arranging the sequence numbers of the areas; marking the corresponding region and the serial number of the lung 3D model; enclosing a corresponding region of the lung 3D model, and performing bright color processing to determine a colorless region; and freezing the colorless area as the output position and marking.
Furthermore, the method for detecting a plurality of lung sounds on line further includes: traversing the colorless areas and determining the number of the colorless areas; if the colorless areas are multiple and the colorless areas are mutually spaced, judging the final area; carrying out color change treatment on adjacent areas of the colorless area, and carrying out depth marking according to wave band energy corresponding to the adjacent areas; playing sound segments of sound segment areas adjacent to the abnormal lung sound segment, and extending the field along with the playing; gradually delineating a corresponding area along with the extension of the field, judging the similarity of the corresponding area and the colorless areas, and comparing the corresponding area and the colorless areas based on the turning contour of the colorless areas to determine the final area.
In addition, the method for detecting the lung sounds on line further comprises the following steps: performing neural network transformation on the lung 3D model, and giving parameter values of all regions of the lung 3D model; acquiring an influence value of the external influence on the lung, and marking a corresponding area of the influence; superposing the influence value and the parameter value of the corresponding area to change the actual parameter value of the corresponding area; evolving corresponding regional variations of the 3D model of the lung according to the actual parameter values; and acquiring the change of the corresponding region of the lung 3D model, and displaying the deterioration degree of the corresponding region through time deduction so as to warn the corresponding region. The data transformation through the neural network is used for facilitating the data transformation of each region forming the lung 3D model, the change of the region is evolved through the change of the data, and further the deterioration degree of the corresponding region can be displayed through the time passage so as to facilitate further targeted treatment.
Examples
Referring to fig. 2, fig. 2 is a schematic structural composition diagram of an online detection device for multiple lung sounds in an embodiment of the present invention.
As shown in fig. 2, an apparatus for on-line detection of a plurality of lung sounds, the apparatus comprising:
the acquisition module 21: the device is used for sending an acquisition instruction and simultaneously acquiring a plurality of lung sound segments; each lung sound segment is independent;
the marking module 22: the system is used for marking each lung sound segment and comparing the lung sound segment with a preset lung sound segment library to determine a corresponding holder file;
a conversion module 23: the device is used for digitally converting each lung sound segment and forming a corresponding audio frequency recording graph;
the comparison module 24: the audio frequency recording graphs are used for online comparison, and the wave bands in the same time are compared;
a selecting module 25: if more than two wave bands are relatively similar, selecting a valley peak, a valley bottom and a middle section of the wave band to carry out independent comparison, extending the trend of the wave band, and carrying out trend comparison to determine a corresponding holder;
the determination module 26: the method is used for comparing one wave band with a lung sound record library of a relatively similar holder based on the relatively similar wave band, and overlapping the wave band and the corresponding trend of the wave band to determine the pathological stage of the lung sound.
In the embodiment of the present invention, by the method in the embodiment of the present invention, a plurality of lung sound segments are detected simultaneously, and the detection of the plurality of lung sound segments is detected independently, and a band is compared with a lung sound record library of a relatively similar holder based on the relatively similar band, and trends corresponding to the band and the band are overlapped to determine a pathological stage where the lung sound is located, so that individual detection and diagnosis of the plurality of sound segments are realized, and holder marking is performed on the plurality of sound segments to facilitate identification and diagnosis of subsequent sound segments, thereby improving convenience in diagnosis of the plurality of sound segments.
Examples
Referring to fig. 3, fig. 3 is a schematic structural composition diagram of an online detecting system for multiple lung sounds in an embodiment of the present invention.
As shown in fig. 3, an on-line detection system for a plurality of lung sounds, the system comprising: an all-in-one machine screen 31, a computer 32 and a color analyzer 33; the computer 32 is connected with the all-in-one machine screen 31 based on an HDMI interface; the computer 32 is connected with the color analyzer 33 based on a USB interface; the color analyzer 33 is in signal connection with the all-in-one machine screen 31; wherein the content of the first and second substances,
the system is configured for performing the method of online detection of the plurality of lung sounds of any of the above.
In the specific implementation process of the present invention, please refer to the above embodiments, and details are not repeated herein.
In the embodiment of the present invention, by the method in the embodiment of the present invention, a plurality of lung sound segments are detected simultaneously, and the detection of the plurality of lung sound segments is detected independently, and a band is compared with a lung sound record library of a relatively similar holder based on the relatively similar band, and trends corresponding to the band and the band are overlapped to determine a pathological stage where the lung sound is located, so that individual detection and diagnosis of the plurality of sound segments are realized, and holder marking is performed on the plurality of sound segments to facilitate identification and diagnosis of subsequent sound segments, thereby improving convenience in diagnosis of the plurality of sound segments.
Those skilled in the art will appreciate that all or part of the steps in the methods of the above embodiments may be implemented by associated hardware instructed by a program, which may be stored in a computer-readable storage medium, and the storage medium may include: a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic or optical disk, or the like.
In addition, the method, the device and the system for online detecting a plurality of lung sounds provided by the embodiment of the present invention are described in detail above, and a specific example should be used herein to explain the principle and the implementation manner of the present invention, and the description of the above embodiment is only used to help understanding the method and the core idea of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for on-line detection of a plurality of lung sounds, the method comprising:
sending an acquisition instruction, and simultaneously acquiring a plurality of lung sound segments; each lung sound segment is independent;
marking each lung sound segment, and comparing with a preset lung sound segment library to determine a corresponding holder file;
digitally converting each lung sound segment and forming a corresponding audio frequency recording graph;
comparing the audio frequency recording graphs on line, and comparing the wave bands in the same time;
if more than two wave bands are relatively similar, selecting a valley peak, a valley bottom and a middle section of the wave band to carry out independent comparison, extending the trend of the wave band, and carrying out trend comparison to determine a corresponding holder;
and comparing one wave band with a lung sound record library of a relatively similar holder based on the relatively similar wave band, and overlapping the wave band and the corresponding trend of the wave band to determine the pathological stage of the lung sound.
2. The method for on-line detection of multiple lung sounds according to claim 1, wherein the step of issuing an acquisition instruction and simultaneously acquiring multiple lung sound segments is performed; each lung sound segment is independent, includes:
each detection channel is shunted to the lung of the corresponding detector and is concentrated in the same system;
sending an acquisition instruction by the system, and simultaneously acquiring a plurality of lung sound segments;
the corresponding lung sound segments are conveyed by the corresponding detection channels; the detection channel is connected with a corresponding sound containing space, and the lung sound segments are stored and discriminated through the sound containing space; the sound containing spaces do not resonate with each other, so that the lung sound segments are detected independently and independently;
detecting two ends of the lung sound segment and local wavelengths of the lung sound segment, and determining the volume sound type of the lung sound segment;
the volume sound type matching based on the lung sound segment corresponds to the volume sound space, the volume sound space is provided with a plurality of volume sound spaces, and the volume sound spaces are selected based on the volume sound type selection of the lung sound segment.
3. The method of claim 1, wherein the marking each lung segment and comparing it with a predetermined library of lung segments to determine a corresponding holder profile comprises:
obtaining an effective circulation period from the lung sound segment;
acquiring a test wave in a preset position in the cycle period;
collecting the interval time between the highest point and the lowest point in the test wave, and comparing the interval time with the corresponding time in the preset lung sound segment library to preliminarily determine a plurality of holder files;
extracting specific waves from a plurality of holder files, and comparing the specific waves with the test waves one by one to obtain a plurality of similar ratios;
the highest similar ratio and the lowest similar ratio are excluded from the similar ratios, and the characteristic waves corresponding to the rest similar ratios are placed in different environments for characteristic testing so as to obtain the tone corresponding to the characteristic waves;
and comparing the plurality of tones with corresponding tones in the preset lung sound segment library to determine matching tones so as to determine corresponding holder files.
4. The method of claim 1, wherein the comparing a band with a relatively similar pulmonary sound record library of a holder based on the relatively similar band and overlapping the corresponding trend of the band and the band to determine the pathological stage of the pulmonary sound comprises:
acquiring the relatively approximate band;
collecting approximate waves from the relatively approximate wave bands, and marking turning segments of the approximate waves one by one;
calculating interval time and wave band energy between the turning sections, and comparing the interval time and the corresponding wave band energy with a lung sound record library of a holder which is relatively similar to the interval time so as to determine a plurality of turning sections which meet a preset similar range;
comparing wave bands corresponding to the turning sections with preset wave bands in the lung sound recording library, and overlapping the wave bands and trends corresponding to the wave bands to preliminarily determine abnormal wave bands;
intercepting the abnormal wave band, and carrying out duplicate removal processing on the abnormal wave band to form an optimized wave band;
inputting the optimized wave band into a preset disease learning model, and outputting a corresponding pathology;
and if the pathology is multiple, inputting the optimized wave band into the record map learning model, forming a corresponding pathology track, determining the final pathology according to the pathology track, and taking the final pathology as the lung disease type.
5. The method for on-line detection of a plurality of lung sounds according to claim 1, further comprising:
collecting lung sound segments corresponding to the current pathological record chart;
constructing an echo section corresponding to the lung sound section corresponding to the current pathological record chart, and performing echo adjustment based on a transmitted lung contour;
constructing a lung 3D model based on the lung sound segment and the echo segment, and performing contour adjustment based on the transmitted lung contour;
acquiring a sound wave band corresponding to the lung disease type, and mapping a corresponding abnormal lung sound segment;
and acquiring a vocal tract region adjacent to the abnormal lung vocal tract, simulating a corresponding output position in the 3D lung model, and marking the output position.
6. The method for on-line detection of multiple lung sounds according to claim 5, wherein the obtaining of the sound segment region adjacent to the abnormal lung sound segment and the simulation of the corresponding output position on the 3D lung model and the marking of the output position comprise:
capturing sound segment areas adjacent to the abnormal lung sound segments, and sequentially arranging the sequence numbers of the areas;
marking the corresponding region and the serial number of the lung 3D model;
enclosing a corresponding region of the lung 3D model, and performing bright color processing to determine a colorless region;
and freezing the colorless area as the output position and marking.
7. The method of claim 6, further comprising:
traversing the colorless areas and determining the number of the colorless areas;
if the colorless areas are multiple and the colorless areas are mutually spaced, judging the final area;
carrying out color change treatment on adjacent areas of the colorless area, and carrying out depth marking according to wave band energy corresponding to the adjacent areas;
playing sound segments of sound segment areas adjacent to the abnormal lung sound segment, and extending the field along with the playing;
gradually delineating a corresponding area along with the extension of the field, judging the similarity of the corresponding area and the colorless areas, and comparing the corresponding area and the colorless areas based on the turning contour of the colorless areas to determine the final area.
8. The method of claim 6, further comprising:
performing neural network transformation on the lung 3D model, and giving parameter values of all regions of the lung 3D model;
acquiring an influence value of the external influence on the lung, and marking a corresponding area of the influence;
superposing the influence value and the parameter value of the corresponding area to change the actual parameter value of the corresponding area;
evolving corresponding regional variations of the 3D model of the lung according to the actual parameter values;
and acquiring the change of the corresponding region of the lung 3D model, and displaying the deterioration degree of the corresponding region through time deduction so as to warn the corresponding region.
9. An apparatus for on-line detection of a plurality of lung sounds, the apparatus comprising:
an acquisition module: the device is used for sending an acquisition instruction and simultaneously acquiring a plurality of lung sound segments; each lung sound segment is independent;
a marking module: the system is used for marking each lung sound segment and comparing the lung sound segment with a preset lung sound segment library to determine a corresponding holder file;
a conversion module: the device is used for digitally converting each lung sound segment and forming a corresponding audio frequency recording graph;
a comparison module: the audio frequency recording graphs are used for online comparison, and the wave bands in the same time are compared;
a selecting module: if more than two wave bands are relatively similar, selecting a valley peak, a valley bottom and a middle section of the wave band to carry out independent comparison, extending the trend of the wave band, and carrying out trend comparison to determine a corresponding holder;
a determination module: the method is used for comparing one wave band with a lung sound record library of a relatively similar holder based on the relatively similar wave band, and overlapping the wave band and the corresponding trend of the wave band to determine the pathological stage of the lung sound.
10. An on-line detection system for a plurality of lung sounds, the system comprising: the system comprises an all-in-one machine screen, a computer and a color analyzer; the computer is connected with the screen of the all-in-one machine based on an HDMI (high-definition multimedia interface); the computer is connected with the color analyzer based on a USB interface; the color analyzer is in signal connection with the screen of the all-in-one machine; wherein the content of the first and second substances,
the system is configured for performing the method of online detection of a plurality of lung sounds of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524309.0A CN113331862A (en) | 2021-05-13 | 2021-05-13 | Online detection method, device and system for multiple lung sounds |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110524309.0A CN113331862A (en) | 2021-05-13 | 2021-05-13 | Online detection method, device and system for multiple lung sounds |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113331862A true CN113331862A (en) | 2021-09-03 |
Family
ID=77469686
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110524309.0A Withdrawn CN113331862A (en) | 2021-05-13 | 2021-05-13 | Online detection method, device and system for multiple lung sounds |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113331862A (en) |
-
2021
- 2021-05-13 CN CN202110524309.0A patent/CN113331862A/en not_active Withdrawn
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8842842B2 (en) | Detection of audio channel configuration | |
| US6826350B1 (en) | High-speed signal search method device and recording medium for the same | |
| CN104810025B (en) | Audio similarity detection method and device | |
| CN102319064B (en) | Device and method for improving accuracy of recognizing deceleration of fetal heart rate data | |
| EP0113425A1 (en) | Method of and apparatus for establishing the characteristics of a prerecorded two-channel audio program | |
| CN103051921B (en) | Method for precisely detecting video and audio synchronous errors of video and audio processing system | |
| EP0134238A1 (en) | Signal processing and synthesizing method and apparatus | |
| US9279839B2 (en) | Domain identification and separation for precision measurement of waveforms | |
| CN111855810A (en) | Rail foot damage identification method and system based on recurrent neural network | |
| CN112750442B (en) | Crested mill population ecological system monitoring system with wavelet transformation and method thereof | |
| CN107274912B (en) | Method for identifying equipment source of mobile phone recording | |
| CN116861303A (en) | Digital twin multisource information fusion diagnosis method for transformer substation | |
| US20140351302A1 (en) | Precision Measurement of Waveforms | |
| CN116705059B (en) | Audio semi-supervised automatic clustering method, device, equipment and medium | |
| CN115985331B (en) | Audio automatic analysis method for field observation | |
| CN113331862A (en) | Online detection method, device and system for multiple lung sounds | |
| KR20120094415A (en) | Precision measurement of waveforms | |
| CN113723521A (en) | Motor abnormal sound identification method and identification system | |
| CN114842280A (en) | Automatic micro-seismic signal identification algorithm based on convolutional neural network | |
| US11100365B2 (en) | Apparatus and method for interactively viewing and clustering data segments from long data recordings | |
| CN114841218B (en) | Voice howling detection algorithm | |
| CN113270116A (en) | Diagnosis method, device and system based on lung sound diagnosis | |
| CN112365901A (en) | Mechanical audio fault detection method and device | |
| CN109273025B (en) | Chinese ethnic five-tone emotion recognition method and system | |
| CN115177267B (en) | Heart beat artifact identification method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210903 |