Method for generating lung tomographic image based on lung sound, and pulmonary monitoring system using the method

Abstract

A method of operation of a lung monitoring system operated by at least one processor comprises the steps of: acquiring a breath sound signal measured in the chest of a patient and generating a breath sound tomography image representing the breath intensity of the breath sound signal as a cross-sectional shape of the patient's lungs; calculating compliance based on the patient's positive end-expiratory pressure (PEEP) value fluctuations based on the breath sound tomography image; and determining the patient's optimal PEEP range based on the PEEP value corresponding to the optimal compliance value.

Description

Technology Field

[0001] The present disclosure relates to lung monitoring. Background Technology

[0002] Recently, the need for rapid diagnosis and real-time monitoring of respiratory and lung diseases has emerged. In particular, patients with acute respiratory distress syndrome (ARDS) require mechanical ventilation due to hypoxia caused by inflammatory lung damage resulting from various causes; however, if appropriate mechanical ventilation is not provided, ventilator-induced lung injury (VILI) may occur. Therefore, an optimal lung protective ventilation (LPV) strategy is required to minimize mechanical ventilation-induced lung injury.

[0003] Pulmonary protective ventilation strategies generally involve determining an appropriate positive end-expiratory pressure (PEEP) by comprehensively analyzing various clinical indicators, such as tidal volume, compliance, volume-pressure, and oxygen saturation (SpO2), while gradually reducing the patient's PEEP. However, there is a problem in that it is difficult to detect alveolar abnormalities or ventilatory abnormalities occurring in specific areas using only basic monitoring information provided by the ventilator, such as pressure, volume, and flow.

[0004] To this end, technologies such as chest radiography (X-ray), computed tomography (CT), and electric impedance tomography (EIT) are being actively introduced for lung monitoring. However, chest radiography images may result in reduced contrast for small lesions and foreign bodies when representing the three-dimensional structure of the lungs as a two-dimensional superimposed image, and human error may occur during interpretation depending on the image adjustment values ​​for each image. Additionally, CT images have limitations in that they are difficult to apply to real-time monitoring due to high radiation exposure and poor accessibility. While EIT images offer the advantage of enabling real-time lung monitoring, they require attaching multiple electrodes to the patient's chest to continuously apply microcurrents, and accurate lung monitoring is difficult due to their very low resolution compared to CT or X-ray.

[0005] Meanwhile, a patient's lung sounds (or respiratory sounds) are also an important indicator for diagnosing and predicting lung diseases. However, lung sounds are unstructured data in which the characteristics of each respiratory disease are not quantified, and if medical professionals directly auscultate a patient's lung sounds, diagnostic results may vary depending on the practitioner, or there may be risks of infection for the medical staff. To address this, non-contact lung sound measurement devices are used; however, conventional devices cannot measure lung sounds from multiple chest regions, so their accuracy may be lower compared to actual auscultation. The problem to be solved

[0006] The present disclosure provides a method for generating lung tomographic images based on breath sounds and a lung monitoring system using the same.

[0007] The present disclosure provides a lung tomographic image that visualizes a lung cross-section based on multichannel breath sounds acquired from multiple chest regions, and a result of analyzing the optimal positive end-expiratory pressure using the generated lung tomographic image. means of solving the problem

[0008] According to one embodiment, a method of operation of a lung monitoring system operated by at least one processor comprises: acquiring a breath sound signal measured in the chest of a patient and generating a breath sound tomography image representing the breath intensity of the breath sound signal as a cross-sectional shape of the patient's lungs; calculating compliance based on the patient's positive end-expiratory pressure (PEEP) value fluctuations based on the breath sound tomography image; and determining the patient's optimal PEEP range based on the PEEP value corresponding to the optimal compliance value.

[0009] The step of generating the above-mentioned breath sound tomography image may include the step of acquiring the breath sound signal from at least one breath sound signal measurement patch attached to the chest of the patient, the step of acquiring a lung cross-section template divided into lung regions corresponding to the location and number of the breath sound signal measurement patches attached, and the step of displaying the breath intensity distribution of the breath sound signal measured at the corresponding location in each lung region of the lung cross-section template.

[0010] The above-mentioned display step may further include a step of performing inpainting to restore any missing parts in each lung region where the respiratory intensity distribution of the respiratory sound signal is displayed.

[0011] The above breathing intensity may be a value corresponding to at least one of a peak value, effective value, minimum-maximum average, peak vector, rise-fall time, and amplitude for the signal obtained in the time domain of the breathing sound signal, or a value corresponding to at least one of an amplitude, phase, and period for the signal obtained in the frequency domain of the breathing sound signal.

[0012] The step of generating the above-mentioned breath sound tomographic images may include generating a breath sound tomographic image at a corresponding time point based on the breath sound signal acquired at regular time intervals, and generating a plurality of breath sound tomographic images in a time-series format by sequentially generating breath sound tomographic images at each time point.

[0013] The step of calculating the compliance may include the step of setting a region of interest for at least one lung region included in the respiratory sound tomography image, and the step of calculating the compliance for each lung region based on the amount of change in respiratory intensity within the region of interest.

[0014] The above change in breathing intensity may be a value corresponding to the change in brightness of pixels within the region of interest.

[0015] The above determining step may include the step of obtaining at least one respiratory-related indicator of the patient, and the step of adjusting the optimal PEEP range by analyzing the change in the at least one respiratory-related indicator based on the optimal PEEP range.

[0016] The above determining step may further include the step of providing a lung damage notification to an external terminal if the difference between the patient's current set PEEP value and the optimal PEEP range is greater than or equal to a preset threshold range.

[0017] A lung monitoring system according to one embodiment comprises a memory and a processor that executes instructions stored in the memory, wherein the processor acquires a breath sound signal measured in the chest of a patient and generates a breath sound tomography image representing the breath intensity of each breath sound signal as a cross-sectional shape of the patient's lungs, calculates compliance based on the fluctuation of the patient's positive end-expiratory pressure (PEEP) value based on the breath sound tomography image, and determines the patient's optimal PEEP range based on the PEEP value corresponding to the value at which the compliance is optimal.

[0018] The processor can acquire the breath sound signal from at least one breath sound signal measurement patch attached to the chest of the patient, acquire a lung cross-section template divided into lung regions corresponding to the location and number of the breath sound signal measurement patches attached, and generate the breath sound tomography image by displaying the breath intensity distribution of the breath sound signal measured at the corresponding location in each lung region of the lung cross-section template.

[0019] If there are missing parts in each lung region where the respiratory intensity distribution of the respiratory sound signal is displayed, the processor can restore them by performing inpainting.

[0020] The processor can generate a respiratory sound tomographic image at a given time point based on the respiratory sound signal acquired at regular time intervals, and can generate multiple respiratory sound tomographic images in a time-series format by sequentially generating respiratory sound tomographic images at each time point.

[0021] The processor can set a region of interest for at least one lung region included in the respiratory sound tomography image, and calculate the compliance for each lung region based on a change in respiratory intensity corresponding to a change in brightness of pixels within the region of interest.

[0022] The processor can acquire at least one respiratory-related indicator of the patient and adjust the optimal PEEP range by analyzing the change in the at least one respiratory-related indicator based on the optimal PEEP range.

[0023] The processor can provide a lung damage notification to an external terminal if the difference between the patient's current set PEEP value and the optimal PEEP range exceeds a preset threshold range.

[0024] A lung monitoring system operated by at least one processor according to one embodiment, a method for generating a respiratory sound tomography image, comprising the steps of: acquiring a respiratory sound signal from at least one respiratory sound signal measuring patch attached to the chest of a patient; acquiring a lung cross-section template divided into lung regions corresponding to the location and number of the respiratory sound signal measuring patches attached; and generating a respiratory sound tomography image by displaying a respiratory intensity distribution of a respiratory sound signal measured at a corresponding location in each lung region of the lung cross-section template.

[0025] The step of generating the above respiratory sound tomographic image may further include a step of performing inpainting to restore any missing parts in each lung region where the respiratory intensity distribution of the respiratory sound signal is displayed.

[0026] The above breathing intensity may be a value corresponding to at least one of a peak value, effective value, minimum-maximum average, peak vector, rise-fall time, and amplitude for the signal obtained in the time domain of the breathing sound signal, or a value corresponding to at least one of an amplitude, phase, and period for the signal obtained in the frequency domain of the breathing sound signal.

[0027] The step of generating the above-mentioned breath sound tomographic images may include generating a breath sound tomographic image at a corresponding time point based on the breath sound signal acquired at regular time intervals, and generating a plurality of breath sound tomographic images in a time-series format by sequentially generating breath sound tomographic images at each time point. Effects of the invention

[0028] According to the present disclosure, medical personnel can simultaneously provide pathophysiological information through a patient's breath sounds and anatomical information through breath sound-based lung tomography.

[0029] According to the present disclosure, since longitudinal analysis is possible by integrating a patient's breath sounds and breath sound-based lung tomography images, medical personnel can perform lung monitoring and lung disease diagnosis more accurately than with single data.

[0030] According to the present disclosure, by providing optimal positive end-expiratory pressure through breath sound-based lung tomography, a lung-protective ventilation strategy suitable for the patient can be established.

[0031] According to the present disclosure, changes in the lungs can be monitored in real time, thereby preventing lung damage that may occur during mechanical ventilation. Brief explanation of the drawing

[0032] FIG. 1 is a conceptual diagram of a lung monitoring system according to one embodiment. FIG. 2 is a configuration diagram of a lung monitoring system according to one embodiment. FIG. 3 is a drawing illustrating a closed cross-section template according to one embodiment. FIG. 4 is a diagram illustrating a method for generating a tomographic image of breath sounds according to one embodiment. FIG. 5 is an example of a breath sound tomography image generated according to one embodiment. FIG. 6 is a diagram illustrating an optimal PEEP analysis method according to one embodiment. FIG. 7 is a flowchart of a lung monitoring method according to one embodiment. FIG. 8 is a flowchart of a method for generating a tomographic image of breath sounds according to one embodiment. FIG. 9 is a flowchart of a PEEP analysis method according to one embodiment. FIG. 10 is a hardware configuration diagram of a lung monitoring system according to one embodiment. Specific details for implementing the invention

[0033] Embodiments of the present disclosure are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, the present disclosure may be embodied in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain the invention in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals.

[0034] In the present disclosure, when a part is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "…part," "…unit," and "…module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware, software, or a combination of hardware and software.

[0035] In the present disclosure, the devices are composed of hardware including at least one processor, a memory device, a communication device, etc., and a program that is executed in combination with the hardware is stored in a designated location. The hardware has a configuration and performance capable of executing the method of the present invention. The program includes instructions that implement the method of operation of the present invention described with reference to the drawings, and executes the present invention in combination with hardware such as a processor and a memory device.

[0036] In the present disclosure, "transmission or provision" may include not only direct transmission or provision but also indirect transmission or provision through another device or by using an alternative route.

[0037] Expressions described in the singular in this disclosure may be interpreted as singular or plural unless explicit expressions such as "one" or "single" are used.

[0038] In the present disclosure, the same reference numerals refer to the same components regardless of the drawings, and "and / or" includes each of the mentioned components and all combinations of one or more.

[0039] In this disclosure, terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of this disclosure, the first component may be named the second component, and similarly, the second component may be named the first component.

[0040] In the flowchart described with reference to the drawings in this disclosure, the order of operations may be changed, several operations may be merged or some operations may be divided, and certain operations may not be performed.

[0041] In the present disclosure, breath sound tomography represents data obtained by reconstructing the distribution of breath sound intensity by lung region, acquired based on a patient's multi-channel breath sound signals, into a cross-sectional shape of the lungs. Additionally, the breath sound tomography may consist of multiple data sets generated at regular time intervals over time.

[0042] FIG. 1 is a conceptual diagram of a lung monitoring system according to one embodiment.

[0043] Referring to FIG. 1, a method for generating lung tomography images based on breath sounds and a lung monitoring system using the same (simply put, a lung monitoring system) (10) is a computing device operated by at least one processor, comprising a memory for storing instructions and a processor for executing instructions, and the processor performs the operation of the present disclosure by executing instructions included in a computer program.

[0044] A lung monitoring system (10) may include at least one user terminal (100), a tomographic image generating device (200), and a PEEP analysis device (300). In this case, the user terminal (100) is a terminal used by medical personnel performing lung monitoring, and may be a system connected to a hospital via a network or an external terminal. For example, the user terminal (100) may be a smartphone, a PC, etc., but is not necessarily limited thereto, and may be any device capable of providing lung monitoring information.

[0045] The lung monitoring system (10) can be implemented to be linked with an external medical system and an external medical device. For example, the lung monitoring system (10) can receive multi-channel breath sound signals from an external breath sound measurement system (not shown) and can obtain breath-related indicators such as positive end-expiratory pressure (PEEP), tidal volume, compliance, transcutaneous oxygen saturation (SpO2), arterial oxygen partial pressure (PaO2), and inhaled oxygen concentration (FiO2) from an external monitoring device (not shown) such as a ventilator.

[0046] Here, the multichannel breath sound signal may be breath sound signals measured from multiple chests using multiple wired or wireless patches attached to the anterior and posterior sides of the patient's chest. In this case, the placement and number of patches may vary according to the judgment of the medical staff, and the shape of the breath sound tomography image may vary depending on the placement and number of patches.

[0047] The user terminal (100) can provide lung monitoring information including a breath sound tomographic image obtained from a tomographic image generating device (200) and an optimal PEEP range obtained from a PEEP analysis device (300). Additionally, the lung monitoring system (10) can provide a lung damage warning notification through the user terminal (100) if the optimal PEEP range obtained from the PEEP analysis device (300) differs from the current PEEP value by more than a preset threshold range.

[0048] In the following, a method is described in which a lung monitoring system (10) generates a respiratory sound tomography image based on multi-channel respiratory sound signals, analyzes the optimal PEEP range based on the respiratory sound tomography image and respiratory-related indicators, and provides lung monitoring information to prevent lung damage.

[0049] FIG. 2 is a configuration diagram of a lung monitoring system according to one embodiment.

[0050] Referring to FIG. 2, the lung monitoring system (10) includes a user terminal (100), a tomographic image generating device (200), and a PEEP analysis device (300). Additionally, the lung monitoring system (10) may further include an information providing device (400) for integrating various lung monitoring information and providing it to the user terminal (100).

[0051] In the present disclosure, the components are referred to as a user terminal (100), a tomographic image generating device (200), a PEEP analysis device (300), and an information providing device (400), but these are computing devices operated by at least one processor. Additionally, the interoperability between the devices constituting the lung monitoring system (10) can be modified in various ways. For example, each device may be implemented in a single computing device or distributed across separate computing devices. When the user terminal (100), the tomographic image generating device (200), the PEEP analysis device (300), and the information providing device (400) are distributed across separate computing devices, each device may communicate with each other through a communication interface.

[0052] The tomographic image generating device (200) may include a breath sound signal processing unit (210) that preprocesses multi-channel breath sound signals and an imaging unit (220) that generates a breath sound tomographic image based on the preprocessed breath sound signals.

[0053] The breath sound signal processing unit (210) can receive multi-channel breath sound signals measured in multiple chest regions of a patient from an external breath sound measurement system (not shown), and can perform a preprocessing process to remove noise, such as heart sounds other than breath sounds, from the received multi-channel breath sound signals. For example, the breath sound signal processing unit (210) can perform preprocessing using known methods such as resampling, normalization, and noise reduction.

[0054] The imaging unit (220) can generate a tomographic image of the breath sound by expressing the intensity of the preprocessed multi-channel breath sound signal in the form of a two-dimensional distribution. In the present disclosure, the intensity of the breath sound signal is described using an amplitude value obtained in the time domain of the breath sound signal as an example, but it is not necessarily limited thereto. For example, the intensity of the multi-channel breath sound signal may use at least one of a peak value, effective value, minimum-maximum average, peak vector, rise-fall time obtained in the time domain of the breath sound signal, or an amplitude, phase, and period obtained in the frequency domain.

[0055] The imaging unit (220) may receive a lung cross-section template from the user terminal (100) or set an appropriate lung cross-section template based on information related to breath sound measurement included in the multi-channel breath sound signal. For example, the information related to breath sound measurement may include the location and number of breath sound signal measurement patches attached to the patient's chest.

[0056] When an appropriate lung cross-section template is set, the imaging unit (220) can represent the breath sound signal with different brightness levels depending on its intensity. The imaging unit (220) can extract a value representing the intensity of the breath sound signal from the breath sound signal, normalize it, and convert the normalized intensity into a Gaussian distribution. Subsequently, the imaging unit (220) can map the breath sound intensity converted into a Gaussian distribution onto a two-dimensional space to represent the distribution of breath sound intensity differently depending on its brightness. For example, the imaging unit (220) can represent higher breath sound intensity with darker pixels and lower breath sound intensity with brighter pixels.

[0057] Afterward, the imaging unit (220) can generate a respiratory sound tomographic image by displaying the respiratory sound intensity, which is displayed differently depending on the brightness, in the corresponding area of ​​the lung cross-section template. For example, the respiratory sound intensity obtained from patch #1 can be placed in the #1 area of ​​the lung cross-section template, and the respiratory sound intensity obtained from patch #2 can be placed in the #2 area of ​​the lung cross-section template.

[0058] Meanwhile, depending on the shape of the lung cross-section template, there may be missing parts in each region. To this end, the imaging unit (220) can restore the missing parts by performing inpainting. For example, the imaging unit (220) can perform inpainting using known inpainting methods such as diffusion-based inpainting or example-based inpainting, or can use a pre-trained deep learning-based inpainting model. Inpainting techniques are already known, and a detailed description is omitted in this disclosure.

[0059] The imaging unit (220) can generate a tomographic image of a breath sound for a specific point in time using the method described above. However, the breath sound signal acquired by the tomographic image generating device (200) may be a signal in the form of a continuous time series. Accordingly, the imaging unit (220) can generate a tomographic image of a breath sound for each point in time at regular time intervals to finally generate a plurality of tomographic images of breath sound in the form of a continuous time series. At this time, the time interval for generating the tomographic images of breath sound may vary according to the judgment of the medical staff, and each of the generated tomographic images of breath sound may include time information.

[0060] The PEEP analysis device (300) receives multiple time-series respiratory sound tomographic images generated by the tomographic image generation device (200) and can obtain an optimal PEEP range based on the respiratory sound tomographic images.

[0061] To this end, the PEEP analysis device (300) may include a compliance calculation unit (310) that calculates compliance for each lung region and an optimal PEEP search unit (320) that searches for an optimal PEEP range based on compliance. Here, compliance is a value related to lung damage such as overinflation, collapse, etc. that may occur during mechanical ventilation, and the PEEP analysis device (300) can search for an optimal PEEP range based on compliance.

[0062] The compliance calculation unit (310) can set at least one region of interest (ROI) for each of the multiple lung regions included in the respiratory sound tomography image, and can calculate compliance for each region of interest.

[0063] Meanwhile, compliance related to lung elasticity can be calculated based on tidal volume and driving pressure. In this case, tidal volume can be estimated based on the intensity of breath sounds appearing in breath sound tomography. For example, since breath sound tomography is represented by different brightness levels depending on breath sound intensity, tidal volume can be estimated using the change in brightness of pixels within the region of interest. Additionally, driving pressure can be calculated based on the difference in alveolar pressure during inspiration and expiration. Considering that alveolar pressure and proximal airway pressure reach equilibrium when the flow rate reaches zero during mechanical ventilation, driving pressure can be calculated using plateau pressure and PEEP values.

[0064] Accordingly, the compliance calculation unit (310) can calculate the compliance using mathematical formula 1.

[0065]

[0066] Here, represents the change in brightness of pixels within the region of interest.

[0067] The compliance calculation unit (310) can calculate compliance by gradually decreasing the PEEP starting from the currently set PEEP value. That is, the compliance calculation unit (310) can calculate compliance according to the decrease in PEEP for each region of interest.

[0068] The optimal PEEP search unit (320) can search for an optimal PEEP range based on the compliance with PEEP reduction obtained for each region of interest. For example, the optimal PEEP search unit (320) can determine the point where the compliance reaches a peak as the optimal compliance, and can determine the optimal PEEP range based on the optimal compliance for each region of interest.

[0069] Additionally, the optimal PEEP search unit (320) can adjust the optimal PEEP range by additionally considering respiratory-related indicators. At this time, the respiratory-related indicators may include tidal volume, compliance, transcutaneous oxygen saturation (SpO2), arterial oxygen partial pressure (PaO2), inhaled oxygen concentration (FiO2), etc. obtained from an external monitoring system such as a ventilator.

[0070] For example, the optimal PEEP search unit (320) can adjust the optimal PEEP range by analyzing changes in breathing-related indicators when the acquired optimal PEEP range is actually applied. That is, even if a value is included within the optimal PEEP range, if a specific breathing-related indicator exceeds a pre-set threshold range, the optimal PEEP range can be adjusted by excluding the corresponding PEEP value from the optimal PEEP range.

[0071] Finally, the information providing device (400) can transmit lung monitoring information including multiple respiratory sound tomographic images in a time series and an optimal PEEP range to a user terminal (100), and the user terminal (100) can provide the received lung monitoring information through a user interface screen.

[0072] The information providing device (400) can provide a compliance graph by region of interest according to PEEP reduction and an analysis result of changes in respiratory-related indicators according to the optimal PEEP value. For example, when a medical professional selects compliance at a specific point in time from the compliance graph through a user interface, the information providing device (400) can provide information regarding the respiratory sound tomography image and the region of interest corresponding to that point in time. At this time, the information providing device (400) can visually represent and provide the corresponding lung region within the respiratory sound tomography image by overlaying it in the form of a heat map.

[0073] Additionally, the information providing device (400) can provide a lung damage warning notification through the user terminal (100) when the optimal PEEP range differs from the current PEEP value by more than a preset threshold range.

[0074] That is, based on the patient's lung monitoring information provided by the user terminal (100), the medical staff can effectively perform a lung protective ventilation (LPV) strategy to minimize the occurrence of lung injury caused by mechanical ventilation (VILI).

[0075] FIG. 3 is a drawing illustrating a closed cross-section template according to one embodiment.

[0076] Referring to FIG. 3, the breath sound signal processing unit (210) can acquire multi-channel breath sound signals measured using breath sound signal measurement patches (#1 to #4) attached to the patient's chest (1010). That is, the breath sound signal processing unit (210) can acquire breath sound signals equal to the number of breath sound signal measurement patches.

[0077] The imaging unit (220) may receive a lung cross-section template from the user terminal (100) or set an appropriate lung cross-section template based on information related to breath sound measurement included in the multi-channel breath sound signal (1020). For example, when a multi-channel breath sound signal is measured by attaching two patches (#1, #2) to the front of the chest and two patches (#3, #4) to the back of the chest, the imaging unit (220) may select the 1020_e template based on the information related to breath sound measurement (1030).

[0078] Here, the lung cross-section template (1020) may include a template with patches attached to the left and right sides of the chest (1020_a, 1020_c), a template with one patch attached to the front and back of the chest respectively (1020_b), a template with patches attached to the upper, middle, and lower parts of the chest (1020_d), and a template with multiple patches attached to the front, back, and sides of the chest (1020_e, 1020_f, 1020_g, 1020_h). Additionally, if necessary, medical personnel may add additional necessary lung cross-section templates (1020) through the user interface of the user terminal (100).

[0079] FIG. 4 is a diagram illustrating a method for generating a respiratory sound tomographic image according to one embodiment, and FIG. 5 is an example of a respiratory sound tomographic image generated according to one embodiment.

[0080] Here, a multi-channel breath sound signal measured by attaching two patches (#1, #2) to the front of the chest and two patches (#3, #4) to the back of the chest is described as an example.

[0081] Referring to FIG. 4, the breath sound signal processing unit (210) can acquire a plurality of breath sound signals (#1 to #4) measured from a plurality of breath sound signal measurement patches attached to the patient's chest (2010). At this time, the imaging unit (220) can select a template corresponding to the breath sound signal based on breath sound measurement information included in the acquired breath sound signal.

[0082] The imaging unit (220) can extract a value representing the intensity of each breath sound signal from each breath sound signal (#1 to #4), normalize it, and convert the normalized intensity into a Gaussian distribution. The imaging unit (220) can then map the breath sound intensity converted into a Gaussian distribution onto a two-dimensional space to represent the distribution of breath sound intensity differently according to brightness (2020).

[0083] The imaging unit (220) can generate a respiratory sound tomographic image for a specific point in time by displaying the respiratory sound intensity obtained from each respiratory sound signal (#1 to #4) on the corresponding area (#1 to #4) of the lung cross-section template. At this time, if there is a missing part within the lung area, the imaging unit (220) can restore it by performing inpainting (2030).

[0084] Finally, the imaging unit (220) captures a respiratory sound tomographic image for a specific point in time at regular time intervals (t1~t n Multiple tomographic images of breath sounds in a continuous time series form can be generated as shown in Fig. 5 by generating them.

[0085] FIG. 6 is a diagram illustrating an optimal PEEP analysis method according to one embodiment.

[0086] Referring to FIG. 6, the compliance calculation unit (310) can set at least one region of interest (ROI) for each of the multiple lung regions included in the breath sound tomography image, and can calculate compliance for each region of interest (3010). Here, region of interest A (ROI) in region #2 of the lung cross-section template A Set ), and in area #4, region of interest B (ROI B Explain using the example of setting ).

[0087] The compliance calculation unit (310) can calculate compliance for each region of interest by gradually decreasing the PEEP value starting from the currently set PEEP value (3020). For example, the compliance calculation unit (310) can calculate compliance for each PEEP step by decreasing the PEEP value from 25 cmH2O to 17 cmH2O in increments of 2 cmH2O.

[0088] The optimal PEEP search unit (320) can obtain an optimal PEEP range based on the compliance with PEEP reduction obtained for each region of interest. For example, region of interest A (ROI A The optimal compliance at ) is 19 cmH2O, and region of interest B (ROI B When the optimal compliance in ) is 21 cmH2O, the optimal PEEP search unit (320) can determine the range of 19 to 21 cmH2O as the optimal PEEP range.

[0089] FIG. 7 is a flowchart of a lung monitoring method according to one embodiment.

[0090] Referring to FIG. 7, the lung monitoring system (10) acquires multi-channel breath sound signals measured in the patient's chest using a plurality of breath sound signal measurement patches (S110). At this time, the location and number of breath sound signal measurement patches may vary according to the judgment of the medical staff, and the shape of the breath sound tomography image may vary depending on the location and number of patches.

[0091] The lung monitoring system (10) generates a respiratory sound tomographic image showing the distribution of respiratory sound intensity as a cross-sectional shape of the lung based on multi-channel respiratory sound signals (S120). For example, the lung monitoring system (10) can convert the intensity of the respiratory sound signal, which is normalized and extracted from the respiratory sound signal, into a Gaussian distribution form, and map the respiratory sound intensity converted into a Gaussian distribution onto a two-dimensional space to represent the distribution of respiratory sound intensity differently depending on the brightness.

[0092] The lung monitoring system (10) sets at least one region of interest for each lung region of the breath sound tomography image and calculates the compliance for each region of interest according to the reduction of PEEP (S130). At this time, the lung monitoring system (10) can calculate the compliance while gradually reducing the PEEP starting from the currently set PEEP value.

[0093] The lung monitoring system (10) determines the optimal PEEP range obtained based on the PEEP value with the maximum compliance for each area of ​​interest (S140). Additionally, if the optimal PEEP range differs from the current PEEP value by more than a preset threshold range, the lung monitoring system (10) can provide a lung damage warning notification through the user terminal (100).

[0094] FIG. 8 is a flowchart of a method for generating a tomographic image of breath sounds according to one embodiment.

[0095] Referring to FIG. 8, the lung monitoring system (10) sets a lung cross-section template corresponding to the location and number of breath sound signal measurement patches attached (S210). For example, the lung monitoring system (10) may receive a lung cross-section template from a user terminal (100) or set an appropriate lung cross-section template based on breath sound measurement information included in a multi-channel breath sound signal.

[0096] The lung monitoring system (10) generates a respiratory sound tomographic image for a specific time point by displaying the distribution of respiratory sound signal intensity corresponding to each lung region of the lung cross-section template (S220). At this time, the lung monitoring system (10) can restore missing parts in each lung region by performing inpainting.

[0097] The lung monitoring system (10) generates multiple respiratory sound tomographic images in a time series form by generating respiratory sound tomographic images for a specific time point at regular time intervals (S230). At this time, the respiratory sound tomographic images generated at each time point may include time information, and the time interval for generating the respiratory sound tomographic images may vary according to the judgment of the medical staff.

[0098] FIG. 9 is a flowchart of a PEEP analysis method according to one embodiment.

[0099] Referring to FIG. 9, the lung monitoring system (10) sets at least one region of interest for each lung region of the breath sound tomography image (S310).

[0100] The lung monitoring system (10) calculates the lung's compliance based on the change in brightness of pixels within each region of interest while gradually decreasing the PEEP from the current PEEP value (S320). At this time, the lung monitoring system (10) can estimate the tidal volume using the change in brightness of pixels within the region of interest, and can calculate the compliance based on the tidal volume and driving pressure (high pressure - PEEP).

[0101] The lung monitoring system (10) obtains an optimal PEEP range based on compliance by region of interest and adjusts the optimal PEEP range using at least one respiratory-related indicator (S330). For example, the lung monitoring system (10) can obtain respiratory-related indicators including tidal volume, compliance, transcutaneous oxygen saturation (SpO2), arterial oxygen partial pressure (PaO2), and inhaled oxygen concentration (FiO2) from an external monitoring system such as a ventilator, and can adjust the optimal PEEP range by analyzing changes in respiratory-related indicators when the optimal PEEP range is actually applied.

[0102] FIG. 10 is a hardware configuration diagram of a lung monitoring system according to one embodiment.

[0103] Referring to FIG. 10, the lung monitoring system (10) is a computing device operated by one or more processors (11), and may include a processor (11), a memory (13) for loading a computer program executed by the processor (11), a storage (15) for storing the computer program and various data, a communication interface (17), and a bus (19) connecting them. In addition, the lung monitoring system (10) may include various additional components.

[0104] A computer program may include instructions that cause a processor (11) to perform a method / operation according to various embodiments of the present disclosure when loaded into memory (13). That is, the processor (11) may perform a method / operation according to various embodiments of the present disclosure by executing the instructions. A computer program is composed of a series of computer-readable instructions grouped by function and refers to being executed by a processor. A computer program may include instructions that perform the operation described in the present disclosure.

[0105] The processor (11) controls the overall operation of each component of the lung monitoring system (10). The processor (11) may be configured to include at least one of a CPU (Central Processing Unit), MPU (Micro Processor Unit), MCU (Micro Controller Unit), GPU (Graphic Processing Unit), or any form of processor well known in the art of the present disclosure. Additionally, the processor (11) may perform operations for at least one application or computer program for executing a method / operation according to various embodiments of the present disclosure.

[0106] Memory (13) stores various data, commands and / or information. Memory (13) may load one or more computer programs from storage (15) to execute a method / operation according to various embodiments of the present disclosure. Memory (13) may be implemented as volatile memory such as RAM, but the technical scope of the present disclosure is not limited thereto.

[0107] Storage (15) can store computer programs non-temporarily. Storage (15) may be configured to include non-volatile memory such as ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), flash memory, a hard disk, a removable disk, or any form of computer-readable recording medium well known in the art to which this disclosure belongs.

[0108] The communication interface (17) supports wired and wireless internet communication of the waste monitoring system (10). Additionally, the communication interface (17) may support various communication methods other than internet communication. To this end, the communication interface (17) may be configured to include a communication module well known in the art of the present disclosure.

[0109] The bus (19) provides communication functions between components of the lung monitoring system (10). The bus (19) can be implemented as various types of buses, such as an address bus, a data bus, and a control bus.

[0110] The embodiments of the present disclosure described above are not implemented only through devices and methods, but may also be implemented through a program that realizes a function corresponding to the configuration of the embodiments of the present disclosure or a recording medium on which such program is recorded.

[0111] Although embodiments of the present disclosure have been described in detail above, the scope of the present disclosure is not limited thereto, and various modifications and improvements by those skilled in the art using the basic concepts of the present disclosure as defined in the following claims also fall within the scope of the present disclosure.

Claims

Claim 1 A method of operation of a lung monitoring system operated by at least one processor, comprising the steps of: acquiring a breath sound signal measured in the chest of a patient and generating a breath sound tomography image representing the breath intensity of the breath sound signal as a cross-sectional shape of the patient's lungs; calculating compliance based on the patient's positive end-expiratory pressure (PEEP) value fluctuations based on the breath sound tomography image; and determining an optimal PEEP range for the patient based on a PEEP value corresponding to the optimal value of compliance. Claim 2 A method of operation according to claim 1, wherein the step of generating the breath sound tomographic image comprises: acquiring the breath sound signal from at least one breath sound signal measuring patch attached to the chest of the patient; acquiring a lung cross-section template divided into lung regions corresponding to the location and number of the breath sound signal measuring patches attached; and displaying the breath intensity distribution of the breath sound signal measured at the corresponding location in each lung region of the lung cross-section template. Claim 3 In paragraph 2, the method of operation further comprises the step of performing inpainting to restore any missing parts in each lung region where the respiratory intensity distribution of the respiratory sound signal is displayed. Claim 4 A method of operation according to claim 1, wherein the breathing intensity is a value corresponding to at least one of a peak value, effective value, minimum-maximum average, peak vector, rise-fall time, and amplitude for the signal obtained in the time domain of the breathing sound signal, or a value corresponding to at least one of an amplitude, phase, and period for the signal obtained in the frequency domain of the breathing sound signal. Claim 5 A method of operation according to claim 1, wherein the step of generating the breath sound tomographic image comprises generating a breath sound tomographic image at a corresponding time point based on the breath sound signal acquired at a set time interval, and sequentially generating a plurality of breath sound tomographic images in a time series. Claim 6 A method of operation according to claim 1, wherein the step of calculating the compliance includes the step of setting a region of interest for each of at least one lung region included in the respiratory sound tomography image, and the step of calculating the compliance for each lung region based on the amount of change in respiratory intensity within the region of interest. Claim 7 In claim 6, the method of operation is a value corresponding to the change in brightness of pixels within the region of interest. Claim 8 A method of operation according to claim 1, wherein the determining step comprises the step of obtaining at least one respiratory-related indicator of the patient, and the step of adjusting the optimal PEEP range by analyzing the change in the at least one respiratory-related indicator based on the optimal PEEP range. Claim 9 A method of operation according to claim 1, wherein the determining step further includes the step of providing a lung damage notification to an external terminal when the difference between the patient's current set PEEP value and the optimal PEEP range is greater than or equal to a preset threshold range. Claim 10 A lung monitoring system comprising a memory and a processor that executes instructions stored in said memory, wherein the processor acquires a breath sound signal measured in the chest of a patient and generates a breath sound tomography image representing the breath intensity of each breath sound signal as a cross-sectional shape of the patient's lungs, calculates compliance based on the fluctuation of the patient's positive end-expiratory pressure (PEEP) value based on said breath sound tomography image, and determines the patient's optimal PEEP range based on the PEEP value corresponding to the value at which the compliance is optimal. Claim 11 A lung monitoring system according to claim 10, wherein the processor obtains a breath sound signal from at least one breath sound signal measuring patch attached to the chest of the patient, obtains a lung cross-section template divided into lung regions corresponding to the location and number of the breath sound signal measuring patches attached, and generates a breath sound tomographic image by displaying the breath intensity distribution of the breath sound signal measured at the corresponding location in each lung region of the lung cross-section template. Claim 12 A lung monitoring system according to claim 11, wherein the processor performs inpainting to restore any missing parts in each lung region where the respiratory intensity distribution of the respiratory sound signal is displayed. Claim 13 A lung monitoring system according to claim 10, wherein the processor generates a respiratory sound tomographic image at a given time point based on the respiratory sound signal acquired at regular time intervals, and sequentially generates a plurality of respiratory sound tomographic images in a time-series form. Claim 14 A lung monitoring system according to claim 10, wherein the processor sets a region of interest for at least one lung region included in the respiratory sound tomography image, and calculates a compliance for each lung region based on a change in respiratory intensity corresponding to a change in brightness of pixels within the region of interest. Claim 15 A lung monitoring system according to claim 10, wherein the processor acquires at least one respiratory-related indicator of the patient and adjusts the optimal PEEP range by analyzing a change in the at least one respiratory-related indicator based on the optimal PEEP range. Claim 16 A lung monitoring system according to claim 10, wherein the processor provides a lung damage notification to an external terminal when the difference between the patient's current set PEEP value and the optimal PEEP range exceeds a preset threshold range. Claim 17 A method for generating a respiratory sound tomography image of a lung monitoring system operated by at least one processor, comprising the steps of: acquiring a respiratory sound signal from at least one respiratory sound signal measuring patch attached to the chest of a patient; acquiring a lung cross-section template divided into lung regions corresponding to the location and number of the respiratory sound signal measuring patches attached; and generating a respiratory sound tomography image by displaying a respiratory intensity distribution of a respiratory sound signal measured at a corresponding location in each lung region of the lung cross-section template. Claim 18 In claim 17, the step of generating the above-mentioned breath sound tomographic image further comprises the step of performing inpainting to restore any missing portions in each lung region where the breath intensity distribution of the breath sound signal is displayed. Claim 19 A method for generating, wherein the breathing intensity is a value corresponding to at least one of a peak value, effective value, minimum-maximum average, peak vector, rise-fall time, and amplitude for the signal obtained in the time domain of the breathing sound signal, or a value corresponding to at least one of an amplitude, phase, and period for the signal obtained in the frequency domain of the breathing sound signal. Claim 20 In claim 17, the step of generating the above-mentioned breath sound tomographic images comprises generating a breath sound tomographic image at a corresponding time point based on the breath sound signal acquired at a set time interval, and generating a plurality of breath sound tomographic images in a time series by sequentially generating breath sound tomographic images at each time point.

Images