Pulmonary function assessment method, system and device based on respiratory impedance changes

Abstract

The present invention provides a method, system, device, medium and program product for evaluating lung function based on respiratory impedance change, and relates to the field of intelligent medical treatment. The method includes: obtaining a time-series EIT image of a subject to be tested; calculating a first fixed amount of gas exhaled from the chest at the first exhaled volume in the exhalation phase and the first moment corresponding thereto based on the time-series EIT image; extracting the time-series impedance change of each pixel between the first moment and the end of FVC exhalation moment, and obtaining the exhalation change characteristic parameter of each pixel at the first exhaled volume; constructing a first regional time distribution diagram based on the exhalation change characteristic parameter; and obtaining the distribution characteristic parameter corresponding to the subject to be tested at the first exhaled volume based on the first regional time distribution diagram; comparing the standard distribution characteristic parameters of the subject to be tested and the healthy person at the first exhaled volume, and if the distribution characteristic parameter of the subject to be tested is greater than the standard distribution characteristic parameter, outputting the result that the subject to be tested has regional ventilation function damage.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical treatment, and more specifically, to a lung function assessment method, system, device, medium and program product based on respiratory impedance changes. Background Art

[0002] Lung diseases caused by smoking, environmental pollution, etc. have become an important factor threatening human health. Early intervention can significantly delay the disease and improve the patient's prognosis. Therefore, early detection of lung function damage is crucial. Pulmonary function measurement (PFT) using a spirometer is a mature lung function measurement method, and its corresponding parameters, forced expiratory volume in one second (FEV1) and forced vital capacity (FVC), can be used to diagnose and grade the severity of the disease. However, PFT can only provide overall lung function and cannot reflect local lung ventilation changes that may occur in the early stages of the disease process.

[0003] Electrical impedance tomography (EIT) can reflect regional pulmonary ventilation function and has been widely used in clinical pulmonary ventilation function assessment, especially suitable for early screening and detection of lung function damage. However, based on dynamic time-series EIT images, how to evaluate lung function has become an important practical problem for early screening of lung function damage using EIT. At present, some scholars have proposed methods based on the spatial characteristics of pulmonary electrical impedance images based on existing PFT parameters, including regional FEV1, FEV1 / FVC, etc. These image parameters objectively characterize the exhaled volume per unit time and reflect the explosive power of human respiratory muscles. They play a good role in evaluating human lung function. However, these indicators cannot reflect the time required to exhale a unit volume of air. These parameters based on the time characteristics of pulmonary electrical impedance images are of great significance for objectively characterizing human lung function. They are not only related to the explosive power of human respiratory muscles, but also to the endurance of respiratory muscles, and can comprehensively evaluate respiratory function. Summary of the invention

[0004] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention provides a lung function assessment method and system based on respiratory impedance changes; the method of the present invention characterizes the time characteristics required to exhale different amounts of gas in FVC by determining the regional time distribution and its distribution characteristic parameters based on the change characteristics of different exhaled volumes; and then accurately and objectively characterizes the results of whether there is regional ventilation function damage in the human lung by comparing the regional time distribution and distribution characteristic parameters, overcoming the current situation that lung function examinations mainly rely on lung function measurements and symptom assessments, and also solving the problem that the indicators proposed by existing scholars cannot reflect the time required to exhale a unit volume of gas.

[0005] The first aspect of the present application discloses a method for evaluating lung function based on changes in respiratory impedance, the method comprising:

[0006] Acquire a time-series EIT image of the subject; the time-series EIT image is obtained by chest electrical impedance signal data of the subject performing FVC action time;

[0007] Calculating a first fixed amount of gas exhaled by the chest at a first exhaled volume in an exhalation phase and a first time corresponding thereto based on the time-series EIT images;

[0008] Extracting the temporal impedance change of each pixel between the first moment and the FVC end-expiration moment, and obtaining the exhalation change characteristic parameter of each pixel at the first exhaled volume;

[0009] Based on the exhalation change characteristic parameters of each pixel, a first regional time distribution diagram is constructed; and based on the first regional time distribution diagram, a distribution characteristic parameter corresponding to the first exhaled air volume of the subject is obtained;

[0010] Compare the distribution characteristic parameters of the subject at the first exhaled volume with the standard distribution characteristic parameters of a healthy person at the first exhaled volume. If the distribution characteristic parameters of the subject are greater than the standard distribution characteristic parameters, output a result indicating that the subject has regional ventilation function impairment.

[0011] The step of extracting the temporal impedance change of each pixel between the first moment and the FVC end-expiration moment to obtain the exhalation change characteristic parameters of each pixel at the first exhaled volume includes: extracting a local temporal EIT image between the first moment and the FVC end-expiration moment to obtain the temporal impedance of the i-th pixel; and fitting (exponential fitting) the temporal impedance change of each pixel based on the local temporal EIT image to obtain the exhalation change characteristic parameters of each pixel.

[0012] The first amount of gas is obtained by:

[0013] Extracting the overall chest impedance change during the FVC action time based on the time-series EIT image;

[0014] Calculating and obtaining the maximum value of the overall chest impedance change;

[0015] The first quantitative gas volume is calculated by multiplying the first exhaled volume by the maximum value; the exhaled volume is expressed as a percentage of FVC.

[0016] The distribution characteristic parameters include any one or more of the following: median, interquartile range, mean, and standard deviation.

[0017] The method further comprises:

[0018] Based on the time series EIT image, a second regional time distribution diagram corresponding to different exhaled air volumes of the subject including time characteristics is obtained; and based on the second regional time distribution diagram, regional time distribution values ​​corresponding to different exhaled air volumes are obtained;

[0019] Comparing the regional time distribution value of the subject at the second exhaled air volume with the standard value of a healthy person at the third exhaled air volume, and if the regional time distribution value of the subject is greater than the standard value, outputting the result of the respiratory muscle burst difference of the subject;

[0020] The method for acquiring the second regional time distribution diagram corresponding to different exhaled air volumes with time characteristics includes:

[0021] Calculate and obtain the maximum value of each pixel during the FVC action time;

[0022] Calculating and obtaining the quantitative amount of gas exhaled at the different exhaled air volumes, that is, the impedance change of each pixel, by multiplying different exhaled air volumes by the maximum value of each pixel;

[0023] Calculate and obtain the time corresponding to the impedance change of each pixel;

[0024] Based on the time corresponding to the impedance change of each pixel and the impedance change of each pixel, the second regional time distribution diagram is obtained.

[0025] The method further comprises: obtaining regional time distribution values ​​corresponding to at least two different exhaled air volumes based on the second regional time distribution graph;

[0026] Comparing the regional time distribution value of the subject under test at the second exhaled air volume with the standard value of healthy people at the third exhaled air volume, and comparing the regional time distribution value of the subject under test at the third exhaled air volume with the standard value of healthy people at the third exhaled air volume;

[0027] If the regional time distribution values ​​of the subject at the second exhaled volume and the third exhaled volume are both greater than the corresponding standard values, the difference between the regional time distribution value of the subject at the second exhaled volume and its corresponding standard value is calculated as the first difference, and the difference between the regional time distribution value of the subject at the third exhaled volume and its corresponding standard value is calculated as the second difference. If the first difference is less than the second difference, the result of the poor respiratory muscle endurance of the subject is output, and the second exhaled volume is less than the third exhaled volume.

[0028] The method further comprises:

[0029] Calculating a coefficient of variation of the second regional time distribution graph based on the second regional time distribution graph;

[0030] Comparing the coefficient of variation of the subject under test at the second exhaled air volume with the standard coefficient of a healthy person at the second exhaled air volume, and if the coefficient of variation of the subject under test is greater than the corresponding standard coefficient, outputting a result that the subject under test has regional ventilation function impairment;

[0031] The method for obtaining the coefficient of variation includes any one of the following: calculating the standard deviation and mean of the second regional time distribution map based on the second regional time distribution map; obtaining the coefficient of variation by dividing the mean by the standard deviation; or, calculating the coefficient of variation by a clustering method, and the clustering method includes any one or more of the following: Kmeans algorithm, DBSCAN algorithm, spectral clustering algorithm, Laplace mapping algorithm, PCA, GMM, MeanShift algorithm (mean migration), hierarchical clustering algorithm.

[0032] The second aspect of the present application discloses a lung function assessment system based on respiratory impedance changes, including a computer program, which implements the steps of the above method when executed by a processor.

[0033] The third aspect of the present application discloses a computer device, which includes: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the above method.

[0034] A fourth aspect of the present application discloses a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the above method when executed by a processor.

[0035] A fifth aspect of the present application discloses a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0036] This application has the following beneficial effects:

[0037] 1. The present application innovatively discloses a lung function assessment method based on respiratory impedance changes. The method first reconstructs a time-series EIT image of a human body during the FVC action time by taking the end of FVC exhalation as a reference, extracts the impedance change of the entire chest in the time-series EIT image, and then extracts the time-series EIT image within a specified time during the FVC action time, fits the time-series impedance change of each pixel in the EIT image within the specified time, obtains the exhalation change characteristics of each pixel (i.e., the exhalation change characteristic parameters of the corresponding pixels) according to the time-series impedance change, further constructs a regional time distribution image based on the exhaled air volume change characteristics, and then uses a histogram to display the distribution of the exhaled air change characteristic parameters, intuitively showing whether there is regional ventilation function damage in the human lungs; effectively overcomes the current situation that lung function examinations mainly rely on lung function measurements and symptom assessments, and also solves the problem that the indicators proposed by existing scholars cannot reflect the time required to exhale a unit volume of air.

[0038] 2. The present application innovatively proposes a lung function assessment method based on the time characteristics of lung electrical impedance images. Based on the time-series EIT images, a regional time distribution diagram containing time characteristics can be obtained. According to the regional time distribution of different exhaled volumes and their coefficient of variation obtained by analyzing the regional time distribution diagram, the time required for unit exhaled volume is accurately reflected, and the explosive power of the human respiratory muscles, the endurance of the respiratory muscles, and whether there is any damage to the lungs are objectively characterized, so as to more comprehensively evaluate the respiratory function of the human lungs.

[0039] 3. This application innovatively uses regional time distribution diagrams containing time characteristics to obtain relevant parameters containing time characteristics, characterizing the time characteristics required to exhale different amounts of gas in FVC, which can not only reflect the explosive power of human respiratory muscles, but also characterize the endurance of human respiratory muscles, and conduct comprehensive evaluations from multiple dimensions, greatly improving the accuracy and depth of human respiratory function analysis. In addition, the method involved in this application can reflect the local lung function status, and the non-invasive and radiation-free lung function evaluation method can more comprehensively evaluate respiratory function and is more suitable for clinical use. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0041] Figure 1 is a schematic diagram of a method flow chart provided by the first aspect of an embodiment of the present invention;

[0042] Figure 2is a schematic flow chart of a system provided by the second aspect of an embodiment of the present invention;

[0043] Figure 3 is a schematic diagram of a computer device provided by an embodiment of the present invention;

[0044] Figure 4 The embodiment of the present invention provides a healthy person in T 25 Schematic diagram of regional time distribution based on the characteristics of exhaled air volume changes;

[0045] Figure 5 The embodiment of the present invention provides a COPD patient in T 25 Schematic diagram of regional time distribution based on the characteristics of exhaled air volume changes;

[0046] Figure 6 The embodiment of the present invention provides a healthy person in T 25 , T 50 , T 75 , T 90 Schematic diagram of regional time distribution at ;

[0047] Figure 7 The embodiment of the present invention provides a COPD patient in T 25 , T 50 , T 75 , T 90 Schematic diagram of regional time distribution at . DETAILED DESCRIPTION

[0048] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0049] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0050] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0051] Figure 1 1 is a flow chart of a method for evaluating lung function based on respiratory impedance change provided by an embodiment of the present invention. Specifically, the method comprises the following steps:

[0052] 101: Acquire a time-series EIT image of the subject; the time-series EIT image is obtained by chest electrical impedance signal data of the subject performing FVC action time;

[0053] In one embodiment, the method for acquiring the time-series EIT image includes:

[0054] Acquire chest impedance signal data of the subject, wherein the chest impedance signal data is the chest impedance signal data of the time when the subject performs FVC action; in one embodiment, the method for acquiring the chest impedance signal data includes: placing N electrodes on the chest surface of the subject, the subject performs FVC action, and collecting the chest impedance signal data of the time when the subject performs FVC action in real time through an EIT device connected to the electrodes; N is a natural integer greater than or equal to 2; preferably, N electrodes are placed on the chest surface between the fourth and fifth ribs of the subject; the standard for the subject to perform FVC action includes: after three cycles of calm breathing, the subject takes a deep breath, exhales quickly and forcefully, and after completing the exhalation action, takes a deep breath and resumes calm breathing. N is preferably 16.

[0055] Taking the end-expiratory moment of FVC as a reference, the GREIT algorithm is used to reconstruct the time series EIT image of the time when the subject performs the FVC action, which is the time series EIT image. The EIT image at time t is Where N is the total number of pixels in the EIT image.

[0056] In one embodiment, the subject is a patient with abnormal respiratory function or lung disease, or a patient suspected of having abnormal respiratory function.

[0057] The GREIT algorithm is one of the commonly used electrical impedance reconstruction algorithms. In addition to the GREIT algorithm, other EIT algorithms can also be used, such as: traditional second-order norm weighted algorithm, sparse weighted algorithm, etc.

[0058] 102: Calculate a first fixed amount of gas exhaled from the chest at a first exhaled volume in an exhalation phase and a first time corresponding thereto based on the time-series EIT image;

[0059] In one embodiment, the first amount of gas is obtained by:

[0060] Extracting the overall chest impedance change during the FVC action time based on the time-series EIT image;

[0061] Calculating and obtaining the maximum value of the overall chest impedance change;

[0062] The first quantitative gas volume is calculated by multiplying the first exhaled volume by the maximum value; the exhaled volume is expressed as a percentage of FVC.

[0063] 103: extracting the time series impedance change of each pixel between the first moment and the FVC end-expiration moment, and obtaining the exhalation change characteristic parameter of each pixel at the first exhaled air volume;

[0064] In one embodiment, the extracting of the temporal impedance change of each pixel between the first moment and the FVC end-expiration moment to obtain the exhalation change characteristic parameters of each pixel at the first exhaled volume includes: extracting a local temporal EIT image between the first moment and the FVC end-expiration moment to obtain the temporal impedance of the i-th pixel; fitting (exponential fitting) the temporal impedance change of each pixel based on the local temporal EIT image to obtain the exhalation change characteristic parameters of each pixel.

[0065] 104: constructing a first regional time distribution diagram based on the exhalation change characteristic parameters of each pixel; and obtaining distribution characteristic parameters corresponding to the first exhaled air volume of the subject based on the first regional time distribution diagram;

[0066] In one embodiment, the distribution characteristic parameters include any one or more of the following: median, interquartile range, mean, and standard deviation.

[0067] 105: Compare the distribution characteristic parameters of the subject at the first exhaled volume with the standard distribution characteristic parameters of a healthy person at the first exhaled volume. If the distribution characteristic parameters of the subject are greater than the standard distribution characteristic parameters, output a result indicating that the subject has regional ventilation function impairment.

[0068] Theoretically, as long as the subject has damaged lung areas, any one of the distribution characteristic parameters will change. In this embodiment, as long as one distribution characteristic parameter is abnormal compared with the standard distribution characteristic parameter, it can be determined that there is a problem with the lung function.

[0069] In one embodiment, the method further comprises:

[0070] Based on the time series EIT image, a second regional time distribution diagram corresponding to different exhaled air volumes of the subject including time characteristics is obtained; and based on the second regional time distribution diagram, regional time distribution values ​​corresponding to different exhaled air volumes are obtained;

[0071] Comparing the regional time distribution value of the subject at the second exhaled air volume with the standard value of a healthy person at the third exhaled air volume, and if the regional time distribution value of the subject is greater than the standard value, outputting the result of the respiratory muscle burst difference of the subject;

[0072] In one embodiment, the method for acquiring the second regional time distribution diagram corresponding to different exhaled air volumes with time characteristics includes:

[0073] Calculate and obtain the maximum value of each pixel during the FVC action time;

[0074] The quantitative amount of gas exhaled at the different exhaled volumes, i.e., the impedance change of each pixel, is calculated by multiplying different exhaled volumes by the maximum value of each pixel; the exhaled volume is expressed as a percentage of FVC;

[0075] Calculating and obtaining the time corresponding to the impedance change of each pixel; fitting the corresponding time according to the selected exhaled air volume;

[0076] Based on the time corresponding to the impedance change of each pixel and the impedance change of each pixel, the second regional time distribution diagram is obtained.

[0077] In one embodiment, T x Represents the regional time distribution map, with C x Coefficient of variation of the regional time profile, where x is the expired volume expressed as a percentage of FVC. x The calculation method is as follows:

[0078] First, calculate the maximum value P of each pixel during the FVC action i max , where i represents the i-th pixel;

[0079] Secondly, calculate the amount of gas x*P exhaled by each pixel during the exhalation phase i max .

[0080] Then, calculate the impedance change x*P of each pixel i max The corresponding time Further, a second regional time distribution map is obtained

[0081] In one embodiment, the method further comprises: obtaining regional time distribution values ​​corresponding to at least two different exhaled air volumes based on the second regional time distribution graph;

[0082] Comparing the regional time distribution value of the subject under test at the second exhaled air volume with the standard value of healthy people at the third exhaled air volume, and comparing the regional time distribution value of the subject under test at the third exhaled air volume with the standard value of healthy people at the third exhaled air volume;

[0083] If the regional time distribution values ​​of the subject at the second and third exhaled volumes are both greater than the corresponding standard values, the difference between the regional time distribution value of the subject at the second exhaled volume and its corresponding standard value is calculated as the first difference, and the difference between the regional time distribution value of the subject at the third exhaled volume and its corresponding standard value is calculated as the second difference. If the first difference is less than the second difference, the result of the poor endurance of the subject's respiratory muscles is output, and the second exhaled volume is less than the third exhaled volume. Specifically, the different time distributions corresponding to at least two different exhaled volumes of the subject are calculated, and the two different exhaled volumes are respectively recorded as x1 and x2, and the time distribution corresponding to x1 is T x1 , the time corresponding to x2 is T x2 , x1 is less than x2; when the subject is at T x1 If the regional time distribution value at T is greater than the standard value, the result of the respiratory muscle burst difference of the subject is output; if the subject is at T x1 and T x2 The regional time distribution values ​​at T x1 The difference between the regional time distribution value at T and the standard value is the first difference. x2 The difference between the regional time distribution value at and the standard value is the second difference. If the first difference is less than the second difference, the result of the poor respiratory muscle endurance of the subject is output.

[0084] When compared, the first exhaled volume and the second exhaled volume refer to the same exhalation process (exhalation phase), and each exhalation process refers to the forced exhalation process of FVC. The exhalation time constant in this area is an exponential parameter obtained by an exponential fitting exhalation curve, which represents the time required to exhale a certain amount of gas (for example, 75% of the total exhaled volume):

[0085]

[0086] In one embodiment, the method further comprises:

[0087] The coefficient of variation of the second regional time distribution graph is calculated based on the second regional time distribution graph; specifically, the mean is expressed as mean(T x) indicates that the coefficient of variation C x Expressed in terms of coefficient of variation, mean refers to the average, which is mainly an arithmetic term, referring to the value obtained by dividing the sum of several unequal numbers by the number of these numbers; the mean of people with abnormal lung function will be different from that of healthy people, but the coefficient of variation can reflect whether there is a problem.

[0088] Comparing the coefficient of variation of the subject under test at the second exhaled air volume with the standard coefficient of a healthy person at the second exhaled air volume, and if the coefficient of variation of the subject under test is greater than the corresponding standard coefficient, outputting a result that the subject under test has regional ventilation function impairment;

[0089] The method for obtaining the coefficient of variation includes any one of the following: calculating the standard deviation and mean of the second regional time distribution map based on the second regional time distribution map; obtaining the coefficient of variation by dividing the mean by the standard deviation, that is, C x =std(T x ) / mean(T x ); or, the coefficient of variation is calculated by a clustering method, and the clustering method includes any one or more of the following: Kmeans algorithm, DBSCAN algorithm, spectral clustering algorithm, Laplace mapping algorithm, PCA, GMM, MeanShift algorithm (mean shift), hierarchical clustering algorithm. The principle of clustering is to reflect the degree of convergence of all pixels. The closer they are, the smaller the coefficient of variation; the larger the coefficient of variation, the greater the damage to some areas of the lungs, and the more different they are from healthy people.

[0090] Standard Deviation (also known as: mean square error) is the square root of the arithmetic mean of the squares of the deviations between the standard values ​​of each unit in the population and their mean, represented by σ. Standard Deviation is the arithmetic square root of variance. Standard Deviation is most commonly used in probability statistics as a statistical distribution, and can also reflect the degree of dispersion of a data set. Two sets of data with the same mean may not have the same standard deviation.

[0091] In one embodiment, the regional time distribution value is obtained through a regional time distribution graph.

[0092] The purpose of the present application is to disclose a lung function assessment system based on the time characteristics of lung electrical impedance images, including a computer program, which implements the steps of the above method when executed by a processor.

[0093] Figure 2 A pulmonary function assessment system based on respiratory impedance change provided by an embodiment of the present invention comprises:

[0094] An acquisition unit 201 is used to acquire a time-series EIT image of the subject; the time-series EIT image is obtained by chest electrical impedance signal data of the subject performing FVC action time;

[0095] A first processing unit 202 is configured to calculate a first fixed amount of gas exhaled from the chest at a first exhaled volume in an exhalation phase and a first time corresponding thereto based on the time-series EIT image;

[0096] The second processing unit 203 is used to extract the time series impedance change of each pixel between the first moment and the FVC end-expiration moment, and obtain the exhalation change characteristic parameter of each pixel at the first exhaled air volume;

[0097] The third processing unit 204 is used to construct a first regional time distribution diagram based on the exhalation change characteristic parameters of each pixel; and obtain the distribution characteristic parameters corresponding to the first exhaled breath volume of the subject based on the first regional time distribution diagram;

[0098] The fourth processing unit 204 is used to compare the distribution characteristic parameters of the subject at the first exhaled volume with the standard distribution characteristic parameters of a healthy person at the first exhaled volume, and if the distribution characteristic parameters of the subject are greater than the standard distribution characteristic parameters, output a result that the subject has regional ventilation function damage.

[0099] Combined with Figure 4 , Attachment Figure 5 FIG. 1 is a specific embodiment of the present invention, wherein: Figure 4 The embodiment of the present invention provides a healthy person in T 25 Schematic diagram of regional time distribution based on the characteristics of exhaled air volume changes; Figure 5 The embodiment of the present invention provides a COPD patient in T 25 Schematic diagram of regional time distribution based on the characteristics of exhaled air volume changes; Attachment Figure 4 and attached Figure 5 The horizontal and vertical coordinates in are both pixels. Specifically include:

[0100] Healthy subjects: 51 years old, male. COPD patients: 56 years old, male.

[0101] The first step is to collect the chest impedance signal of the human body when performing FVC action. The subject wears the EIT electrode belt on the subject's chest, usually between the 4th and 5th ribs. The height of the electrode belt can be adjusted appropriately according to the actual situation. Turn on the EIT machine to collect the human chest impedance signal in real time. Instruct the patient to perform FVC breathing movements, that is, after three cycles of calm breathing, take a deep breath, followed by a quick and forceful exhalation. After completing the exhalation, take a deep breath, and then gradually resume calm breathing. Taking the end of exhalation of the FVC action as a reference, reconstruct the time-series EIT image during the entire FVC action implementation period. The EIT image at time t is Wherein, N is the total number of pixels of the EIT image. In this embodiment, the GREIT algorithm is used to reconstruct the time series EIT image, and the EIT image is discretized into an image of 32*32 pixels.

[0102] The second step is to analyze the characteristic parameters based on the temporal characteristics of the EIT image.

[0103] In order to characterize the time characteristics required to exhale different amounts of gas in FVC, the embodiment of the present invention provides a regional time distribution and distribution characteristic parameters based on the variation characteristics of the exhaled volume. x represents the exhaled volume, which is expressed as a percentage of FVC.

[0104] First, extract the overall chest impedance change during FVC implementation G = [G1, G2, ..., G t ,...], where G t is the chest impedance at time t, And calculate its maximum value G max =max[G1,G2,…,G t ,…],

[0105] Secondly, calculate the amount of gas G exhaled by the entire chest during the exhalation phase x =x*G max , and the corresponding time t x .

[0106] Then, with t x and FVC at end-expiratory time t end-exp is the time limit, and the time series EIT image within the time limit is extracted. The time series impedance of the i-th pixel is

[0107] Next, the timing impedance change of each pixel is fitted in exponential form. For example, for the timing impedance of the i-th pixel, Thus, the exhalation change characteristics of each pixel are obtained, that is, the exhalation change characteristic parameter of the i-th pixel is Further construct a regional time distribution image based on the characteristics of exhaled air volume changes

[0108] Finally, the histogram is used to represent Distribution, expressed as median plus interquartile range and mean plus standard deviation Distribution characteristics.

[0109] In this embodiment, the exhalation characteristic parameter G is calculated based on the time corresponding to the exhalation of 25% of the FVC in the whole chest during the exhalation phase. 25 The corresponding time t 25 The regional time distribution and histogram of healthy people are as follows Figure 4 As shown, the median and mean are, and The regional temporal distribution and histogram of COPD patients are shown in Figure 2. Figure 5 As shown, the median and mean are, and From the results, we can see that compared with healthy people, COPD patients have a larger regional time distribution range and larger distribution characteristic parameters (mean and variability), indicating that COPD patients have obvious regional ventilation function damage. Among them, variability can be understood as the degree of uneven distribution.

[0110] Combined with Figure 6 , Attachment Figure 7 FIG. 1 is a specific embodiment of the present invention, wherein: Figure 6 The embodiment of the present invention provides a healthy person in T 25 , T 50 , T 75 , T 90 Schematic diagram of regional time distribution at ; Figure 7 The embodiment of the present invention provides a COPD patient in T 25 , T 50 , T 75 , T 90 Schematic diagram of regional time distribution at Figure 6 and attached Figure 7 In, T 25 Written as T25, T 50 Written as T50, T 75 Written as T75, T 90 Written as T90, attached Figure 6 and attached Figure 7 The horizontal and vertical axes in are both pixels, and the unit of the color scale bar is time (s). Specifically include:

[0111] This study was approved by the Ethics Committee. The subjects were a healthy person and a COPD patient, who was a patient with chronic obstructive pulmonary disease.

[0112] Healthy subjects: 51 years old, male. COPD patients: 56 years old, male.

[0113] The first step is to collect the chest impedance signal of the human body when performing FVC action. The subject wears the EIT electrode belt on the subject's chest, usually between the 4th and 5th ribs. The height of the electrode belt can be adjusted appropriately according to the actual situation. Turn on the EIT machine to collect the human chest impedance signal in real time. Instruct the patient to perform FVC breathing movements, that is, after three cycles of calm breathing, take a deep breath, followed by a quick and forceful exhalation. After completing the exhalation, take a deep breath, and then gradually resume calm breathing. Taking the end of exhalation of the FVC action as a reference, reconstruct the time-series EIT image during the entire FVC action implementation period. The EIT image at time t is Wherein, N is the total number of pixels of the EIT image. In this embodiment, the GREIT algorithm is used to reconstruct the time series EIT image, and the EIT image is discretized into an image of 32*32 pixels.

[0114] The second step is to analyze the characteristic parameters based on the temporal characteristics of the EIT image.

[0115] In order to characterize the time characteristics required to exhale different amounts of gas in FVC, an embodiment of the present invention provides a regional time distribution based on different exhaled gas volumes and its coefficient of variation.

[0116] T x Represents the regional time distribution map, with C x Coefficient of variation of the regional time profile, where x is the expired volume expressed as a percentage of FVC. x The calculation method is as follows:

[0117] First, calculate the maximum value P of each pixel during the FVC action i max , where i represents the i-th pixel;

[0118] Secondly, calculate the amount of gas x*P exhaled by each pixel during the exhalation phase i max .

[0119] Then, calculate the impedance change x*P of each pixel i max The corresponding time Further, obtain the regional time distribution map

[0120] Finally, the mean and coefficient of variation C of the regional time distribution map were calculated. x It can be calculated by dividing the mean by the standard deviation, that is, C x =std(T x) / mean(T x ), or the clustering method can be used for calculation.

[0121] In this embodiment, to obtain the result of poor respiratory muscle endurance, at least two expired air volumes are required for comparison. In this embodiment, the regional time distribution corresponding to the four expired air volumes of 25%, 50%, 75% and 90% of FVC is calculated, namely, T 25 , T 50 , T 75 and T 90 The regional temporal distribution of healthy people is as follows Figure 6 As shown in the figure, the coefficients of variation of the regional time distribution maps are C 25 =0.018, C 50 =0.023, C 75 = 0.028 and C 90 =0.034. The regional temporal distribution of COPD patients is as follows Figure 7 As shown in the figure, the coefficients of variation of the regional time distribution maps are C 25 =0.038, C 50 =0.041, C 75 =0.088 and C 90 =0.19. From the results, we can see that at T 25 , T 50 The regional time distribution values ​​of COPD patients were significantly greater than those of healthy people, and as the exhaled air volume increased, the T 75 and T 90 The regional time distribution values ​​of COPD patients are more significantly greater than those of healthy people, indicating that the respiratory muscles of COPD patients not only have poor burst, but also poor respiratory muscle endurance; moreover, compared with healthy people, the coefficient of variation of the regional time distribution of COPD patients is larger, reflecting the regional ventilation function damage of COPD patients.

[0122] Figure 3 A computer device is provided in an embodiment of the present invention, and the device comprises: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the above method.

[0123] The embodiment of the present invention further discloses a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0124] The embodiment of the present invention further discloses a computer program product, including a computer program, which implements the steps of the above method when executed by a processor.

[0125] definition:

[0126] FEV1, or forced expiratory volume in one second, is the maximum volume of air exhaled in one second after maximum inhalation and rapid exhalation. The normal value for an adult is 3.65 L. It is the most commonly used indicator in clinical practice, with good repeatability and strong force dependence. Both restrictive and obstructive disorders can lead to its decline.

[0127] FEV1 / FVC stands for forced expiratory volume in one second / forced vital capacity, which is the ratio of FEV1 to FVC. The normal range is about 83%. A decrease in its value is common in obstructive disorders, and >90% indicates the presence of restrictive disorders.

[0128] In mild airflow obstruction, the patient can fully exhale, and FVC may be basically normal or only slightly decreased, but the expiratory flow slows down, FEV1 decreases, and FEV1 / FVC also decreases accordingly; as the obstruction worsens, both FEV1 and FEVl / FVC decrease further; if the obstruction is severe, the patient often finds it difficult to complete full exhalation, and FVC also decreases significantly, and FEV1 / FVC may increase instead. Therefore, FEV1 / FVC can reflect the presence of airflow obstruction, but it cannot accurately reflect the degree of obstruction.

[0129] FEV1 is the volume of air exhaled in one second after the deepest breath. FEV1% measurement is a common indicator for judging asthma and COPD. Asthma mainly causes expiratory dyspnea, so FEV1% measurement will be lower or significantly lower. Clinically, the ratio of FEV1 / forced vital capacity FVC (rate in one second) is often used for judgment, and the normal value is 83%: obstructive or mixed type is slightly reduced to significantly reduced; restrictive type is normal or slightly increased.

[0130] The severity of COPD (chronic obstructive pulmonary disease) can be graded based on FEV1 / FVC, FEV1 as a percentage of predicted value, and symptoms:

[0131] Grade I (mild): FEV1 / FVC <70%, FEV1 as a percentage of predicted value >80%; avoid risk factors: influenza vaccination; use short-acting bronchodilators as needed

[0132] Grade II (moderate): FEV1 / FVC <70%, SFEV1 50%-80% of the predicted value, based on the previous level of treatment, regular use of one or more long-acting bronchodilators, rehabilitation treatment

[0133] Grade II (severe): FEV1 / FVC <70%, 30% SFEV1 accounts for <50% of the predicted value, and inhaled glucocorticoids can be used in addition to the previous level of treatment with repeated acute attacks.

[0134] IV (extremely severe): FEV1 / FVC <70%, FEV1 as a percentage of the predicted value <30%, or FEV1 <50% accompanied by chronic respiratory failure. On the basis of superior treatment, if there is respiratory failure, long-term oxygen therapy, and surgical treatment may be considered.

[0135] Electrical impedance tomography (EIT) means that when a certain current or voltage is added to the surface of the human body, different impedance distributions in the body will measure different voltages or currents on the body surface. Therefore, electrical impedance tomography technology is actually: injecting a known voltage into a specific part of the human body to measure the current caused on the body surface, or injecting a known current to measure the voltage caused on the body surface, using the measured current and voltage values, according to a certain reconstruction algorithm, calculate the impedance distribution of each tissue and organ in the human body under the action of the electric field, and use a computer to generate tomographic images. Specifically, if the surface boundary voltage data is measured based on the excitation current in this application, the lung perfusion EIT image is reconstructed according to the existing reconstruction algorithm.

[0136] The interquartile range, also known as the four-point difference, IQR. It is a method in descriptive statistics to determine the difference between the third quartile and the first two quartiles. Like the variance and standard deviation, it indicates the dispersion of variables in statistical data, but the four-point difference is more of a robust statistic. The interquartile range is usually used to construct box plots and a brief graphical overview of probability distributions. For a symmetrically distributed data, the median must be equal to the arithmetic mean of the third quartile and the first quartile, and half of the four-point difference is equal to the absolute median difference.

[0137] The validation results of this validation example show that assigning intrinsic weights to indications can moderately improve the performance of the method relative to the default setting.

[0138] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0139] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0140] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0141] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0142] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can 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 disk or an optical disk, etc.

[0143] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a disk or an optical disk, etc.

[0144] The above is a detailed introduction to a computer device provided by the present invention. For a person skilled in the art, according to the concept of the embodiments of the present invention, there may be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for evaluating lung function based on changes in respiratory impedance, characterized in that: The method comprises: Acquire a time-series EIT image of the subject to be tested; the time-series EIT image is obtained by chest electrical impedance signal data of the subject to be tested performing FVC action time; A first fixed amount of gas exhaled from the chest at a first exhaled volume in the exhalation phase and a first moment corresponding thereto are calculated based on the time series EIT image; a method for obtaining the first fixed amount of gas includes: extracting a change in overall chest impedance during the FVC action time based on the time series EIT image; calculating and obtaining a maximum value in the change in overall chest impedance; and calculating and obtaining the first fixed amount of gas by multiplying the first exhaled volume by the maximum value; Extracting the local time series EIT image between the first moment and the FVC end-expiration moment, and obtaining the time series impedance of the i-th pixel; fitting the time series impedance change of each pixel based on the local time series EIT image, and obtaining the exhalation change characteristic parameter of each pixel; Based on the exhalation change characteristic parameters of each pixel, a first regional time distribution diagram is constructed; and based on the first regional time distribution diagram, a distribution characteristic parameter corresponding to the first exhaled air volume of the subject is obtained; Compare the distribution characteristic parameters of the subject at the first exhaled volume with the standard distribution characteristic parameters of a healthy person at the first exhaled volume. If the distribution characteristic parameters of the subject are greater than the standard distribution characteristic parameters, output a result indicating that the subject has regional ventilation function impairment.

2. The method for evaluating lung function based on respiratory impedance changes according to claim 1, characterized in that: The expired volume is expressed as a percentage of FVC.

3. The method for evaluating lung function based on respiratory impedance changes according to claim 1, characterized in that: The distribution characteristic parameters include any one or more of the following: median, interquartile range, mean, and standard deviation.

4. The method for evaluating pulmonary function based on respiratory impedance changes according to any one of claims 1 to 3, characterized in that: The method further comprises: Based on the time series EIT image, a second regional time distribution diagram corresponding to different exhaled air volumes of the subject including time characteristics is obtained; and based on the second regional time distribution diagram, regional time distribution values ​​corresponding to different exhaled air volumes are obtained; Compare the regional time distribution value of the subject at the second exhaled volume with the standard value of a healthy person at the third exhaled volume, and if the regional time distribution value of the subject is greater than the standard value, output the result of the respiratory muscle burst difference of the subject.

5. The method for evaluating lung function based on respiratory impedance changes according to claim 4, characterized in that: The method for acquiring the second regional time distribution diagram corresponding to different exhaled air volumes with time characteristics includes: Calculate and obtain the maximum value of each pixel during the FVC action time; Calculating and obtaining the quantitative amount of gas exhaled at the different exhaled air volumes, that is, the impedance change of each pixel, by multiplying different exhaled air volumes by the maximum value of each pixel; Calculate and obtain the time corresponding to the impedance change of each pixel; Based on the time corresponding to the impedance change of each pixel and the impedance change of each pixel, the second regional time distribution diagram is obtained.

6. The method for evaluating lung function based on respiratory impedance changes according to claim 5, characterized in that: The method further comprises: obtaining regional time distribution values ​​corresponding to at least two different exhaled air volumes based on the second regional time distribution graph; Comparing the regional time distribution value of the subject under test at the second exhaled air volume with the standard value of healthy people at the third exhaled air volume, and comparing the regional time distribution value of the subject under test at the third exhaled air volume with the standard value of healthy people at the third exhaled air volume; If the regional time distribution values ​​of the subject at the second exhaled volume and the third exhaled volume are both greater than the corresponding standard values, the difference between the regional time distribution value of the subject at the second exhaled volume and its corresponding standard value is calculated as the first difference, and the difference between the regional time distribution value of the subject at the third exhaled volume and its corresponding standard value is calculated as the second difference. If the first difference is less than the second difference, the result of the poor respiratory muscle endurance of the subject is output, and the second exhaled volume is less than the third exhaled volume.

7. The method for evaluating lung function based on respiratory impedance changes according to claim 5, characterized in that: The method further comprises: Calculating a coefficient of variation of the second regional time distribution graph based on the second regional time distribution graph; Compare the coefficient of variation of the subject under test at the second exhaled air volume with the standard coefficient of a healthy person at the second exhaled air volume, and if the coefficient of variation of the subject under test is greater than the corresponding standard coefficient, output a result indicating that the subject under test has regional ventilation function impairment.

8. The method for evaluating lung function based on respiratory impedance changes according to claim 7, characterized in that: The method for obtaining the coefficient of variation includes any one of the following: calculating the standard deviation and mean of the second regional time distribution map based on the second regional time distribution map; obtaining the coefficient of variation by dividing the mean by the standard deviation; or, calculating the coefficient of variation by a clustering method, and the clustering method includes any one or more of the following: Kmeans algorithm, DBSCAN algorithm, spectral clustering algorithm, Laplace mapping algorithm, PCA, GMM, MeanShift algorithm, hierarchical clustering algorithm.

9. A system for evaluating lung function based on respiratory impedance changes, comprising a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

10. A computer device, characterized in that: The device comprises: a memory and a processor; the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, it is used to execute the steps of the method described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images