A method, system and device for guiding pulmonary rehabilitation based on EIT

Abstract

The present application relates to the field of intelligent medical treatment, and specifically to a method, system and device for guiding pulmonary rehabilitation based on EIT. It includes obtaining ventilation signal data of pulmonary rehabilitation patients; reconstructing the ventilation signal data to obtain an EIT image; and guiding the patient to perform pulmonary rehabilitation breathing based on the EIT image. The present application captures the details of pulmonary rehabilitation breathing operations through EIT, and is a potential tool for quantitatively evaluating pulmonary rehabilitation breathing performance, thereby assisting physical therapists in teaching pulmonary rehabilitation breathing operations to patients, and has great clinical value.

Description

Technical Field

[0001] The present application relates to the field of intelligent medical care, and specifically to a method, system, device and computer-readable storage medium for EIT-guided pulmonary rehabilitation. Background Art

[0002] Chronic obstructive pulmonary disease (COPD) is a serious lung disease characterized by progressive airflow limitation, which is usually associated with enhanced chronic inflammatory response in the airways and lungs caused by long-term exposure to toxic particles or gases. As a common respiratory disease, COPD has become the third leading cause of death worldwide. A recent study reported that the total number of COPD deaths in 2019 was as high as 1.04 million in China alone. In addition, the disease burden of COPD is increasing worldwide due to an aging population and increasing environmental pollution. Between 1990 and 2019, the global incidence of COPD increased by 30.17% (from 2.52 million to 3.28 million cases), and the global prevalence of COPD increased by 84.76% (from 114.9 to 212.3 million cases). To date, COPD is widely recognized as a major global health problem. Due to airflow obstruction, patients with COPD experience recurrent and progressive respiratory symptoms, including dyspnea, chronic cough, shortness of breath, wheezing, chest tightness, fatigue, and weight loss, which may limit daily life activities and reduce quality of life. Unfortunately, COPD is an irreversible and incurable disease, but treatment can relieve symptoms, slow the deterioration of lung function, and minimize patient disability. Currently, pulmonary rehabilitation, as an important part of non-drug treatment, has been recognized as the most effective therapeutic intervention to relieve symptoms and one of the most cost-effective treatments for COPD.

[0003] Pulmonary rehabilitation (PR) generally refers to a comprehensive treatment program that implements patient-centered interventions based on a comprehensive assessment of the overall condition of COPD patients by a multidisciplinary rehabilitation team. Breathing exercises are an important part of the actual implementation of PR, which aims to regulate patients' breathing patterns and improve their exercises, such as pursed lip breathing (PLB). The American Thoracic Society describes PLB as: inhaling through the nose and then exhaling slowly by pursing the lips like a whistle. Many studies have shown that PLB has a positive effect on improving dyspnea, exercise endurance, gas exchange, and ventilation efficiency. In addition, PLB exercises have no venue restrictions, do not require excessive financial investment, and can improve patients' initiative and compliance.

[0004] PLB has specific movement requirements, so COPD patients usually need to receive training and guidance from professional physical therapists to maximize the effectiveness of PLB. However, clinical practice has found that COPD patients still face some challenges in mastering PLB movements. First, most of the patients participating in the PR program are elderly (the highest prevalence of COPD is between 70-74 years old), and these patients have relatively poor language comprehension ability, which requires physical therapists to repeatedly explain the special details of PLB movements to patients. Second, elderly patients have limited breathing control ability and it is difficult to implement satisfactory PLB movements, which increases the workload of physical therapists in teaching patients PLB movements. Third, the patient's PLB performance is monitored and evaluated through the subjective observation of the physical therapist, which makes it difficult to provide further guidance to the patient based on objective measurement indicators. Therefore, there is an urgent need to develop an easy-to-use tool to assist physical therapists in teaching patients PLB movements by continuously and objectively evaluating the patient's respiratory status during the implementation of PLB. Summary of the invention

[0005] Due to the unique advantages of EIT, such as non-invasiveness, simple operation, no radiation, real-time imaging and portability, it has great potential in dynamically monitoring the patient's respiratory status during PLB. In view of the above problems, the present invention proposes a method for guiding pulmonary rehabilitation based on EIT, which specifically includes:

[0006] Obtain ventilation signal data of pulmonary rehabilitation patients;

[0007] Performing image reconstruction on the ventilation signal data to obtain an EIT image;

[0008] The patient is guided to perform pulmonary rehabilitation breathing based on the EIT image.

[0009] The guidance is performed by quantifying the EIT image, wherein the quantification includes global ventilation assessment and / or local ventilation assessment;

[0010] Preferably, the overall ventilation assessment is to first sum the pixel values ​​of the EIT image at time t to obtain a pixel sum, use the pixel sum as the overall impedance at time t, and then assess the overall ventilation based on the overall impedance;

[0011] Preferably, the overall impedance is expressed as:

[0012]

[0013] in, represents the i-th pixel value at time t, ρ t represents the overall impedance at time t, and N represents the total number of pixels of the EIT image;

[0014] Preferably, a functional EIT image is constructed based on the EIT image, and local ventilation characteristics are quantified by the functional EIT image, and local ventilation volume is evaluated by the local ventilation characteristics;

[0015] Preferably, the functional EIT image is calculated by linear regression and is expressed as:

[0016]

[0017] Among them, Δρ i (t) represents the impedance change of the i-th pixel in the original time series EIT image over time; α i and β i represents the regression coefficient of the i-th pixel, χ i represents the fitting error of the i-th pixel, represents the i-th pixel value at time t, ρ t Represents the overall impedance.

[0018] Further, the indicators used in the overall ventilation assessment include one or more of the following: inhalation depth, ratio of expiratory time to inhalation time, exhalation speed, breathing uniformity, and breathing stability;

[0019] Preferably, the inhalation depth represents the magnitude of the inhalation force, which is obtained by calculating the percentage of the inhalation volume of pulmonary rehabilitation breathing to the inhalation volume of deep breathing;

[0020] Preferably, the inhalation depth is expressed as:

[0021]

[0022] in, and Represent the changes in PLB and tidal impedance during deep breathing, respectively.

[0023] Preferably, the ratio of the exhalation time to the inhalation time is obtained by calculating the percentage of the exhalation time to the inhalation time;

[0024] Preferably, the exhalation speed is obtained by calculating the ratio of the tidal impedance change to the exhalation time;

[0025] Preferably, the exhalation speed is expressed as:

[0026]

[0027] Among them, F n Represents the breathing rate, Indicates the change of PLB moisture impedance, t exp Indicates the exhalation time;

[0028] Preferably, the breathing uniformity is obtained by calculating the change of the exhaled volume per unit time in the entire breathing phase;

[0029] Preferably, the respiratory stability is obtained by calculating the change of overall impedance at the end of breathing.

[0030] The indicators used in the local ventilation assessment include one or more of the following: ventral-dorsal ventilation ratio, left-right ventilation ratio, ventilation center, and local respiratory time constant;

[0031] Preferably, the ventral-dorsal ventilation ratio is obtained by calculating the ratio of the sum of ventral pixels to the sum of dorsal pixels;

[0032] Preferably, the calculation of the ventral-dorsal ventilation ratio VtoD is expressed as:

[0033]

[0034] in, and Respectively represent the sum of ventral pixel values ​​and dorsal pixel values, Z i is the value of the i-th pixel of the functional EIT image;

[0035] Preferably, the left-right ventilation ratio is obtained by calculating the ratio of the sum of the right pixel values ​​to the sum of the left pixel values. The calculation of the left-right ventilation ratio RtoL is expressed as:

[0036]

[0037] in, and Represents the sum of the pixel values ​​on the right and the sum of the pixel values ​​on the left, Z i is the value of the i-th pixel of the functional EIT image;

[0038] Preferably, the ventilation center is obtained by weighting the pixel value of each pixel of the functional EIT image and its coordinate position;

[0039] Preferably, the ventilation center is expressed as:

[0040] CoV=∑(Z i ·y i ) / ∑Z i 100%

[0041] Among them, CoV represents the ventilation center, y i Represents the height of the i-th pixel after scaling, Z i is the value of the i-th pixel of the functional EIT image;

[0042] Preferably, the local respiratory time constant is calculated by fitting an exponential curve to the expiratory impedance signal and then calculating the time constant of each pixel;

[0043] Preferably, the local breathing time constant is expressed as:

[0044]

[0045] Among them, τ i represents the time constant of the i-th pixel, Δρ i represents the value of the i-th pixel, C i represents the end-expiratory impedance of the ith pixel, represents the initial local breathing time constant.

[0046] The image reconstruction algorithm includes one or more of the following: discrete Fourier transform, fast Fourier transform, nearest neighbor interpolation algorithm, bilinear interpolation algorithm, singular value decomposition, GREIT algorithm;

[0047] The GREIT algorithm performs EIT image reconstruction, wherein the GREIT algorithm calculates the optimal distribution of the relative change of the patient's chest impedance Δρ by using the relative change of the boundary voltage to obtain the impedance distribution, and grids the optimal distribution into an EIT image;

[0048] Preferably, the following error of the impedance distribution is minimized by optimizing through training of a set of distributions;

[0049] Preferably, the following error is expressed as:

[0050]

[0051] Among them, ε 2 (R) represents the following error, represents the training target distribution, and the boundary change ΔV corresponds to the required impedance change W represents the weight of each target, and R represents the reconstruction matrix.

[0052] The method further comprises data preprocessing, using a filter to filter the patient ventilation signal data to obtain filtered signal data;

[0053] Preferably, the passband frequency range of the filter is set to be 0.05 Hz to 0.65 Hz.

[0054] The object of the present invention is to provide a system for guiding pulmonary rehabilitation based on EIT, comprising:

[0055] Acquisition unit: acquires ventilation signal data of pulmonary rehabilitation patients;

[0056] Reconstruction unit: performing image reconstruction on the ventilation signal data to obtain an EIT image;

[0057] Evaluation unit: guiding the patient to perform pulmonary rehabilitation breathing based on the EIT image.

[0058] The object of the present invention is to provide a device for guiding pulmonary rehabilitation based on EIT, comprising:

[0059] A memory and a processor, wherein the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, any one of the above-mentioned methods for guiding pulmonary rehabilitation based on EIT is implemented;

[0060] Preferably, the device uses an electrode belt to collect patient ventilation signal data;

[0061] Preferably, the electrode belt is worn in the intercostal space between the sternum and the patient, and the electrode belt is transversely fixed on the chest;

[0062] Preferably, the length of the electrode belt is set based on the chest circumference of the patient, n electrodes are evenly distributed on the electrode belt, n is a natural number greater than 4, and the electrodes are conductive rubber electrodes;

[0063] Preferably, the electrode belt has 16 electrodes equidistantly distributed, including 12 fixed electrodes;

[0064] Preferably, m buttons are provided on the electrode belt, where m is a natural number greater than 2, and the buttons are located on both sides of the patient's spine and sternum.

[0065] The object of the present invention is to provide a computer-readable storage medium having a computer program thereon, comprising:

[0066] When the computer program is executed by a processor, any one of the above-mentioned methods for EIT-guided pulmonary rehabilitation is implemented.

[0067] The object of the present invention is to provide a method for evaluating pulmonary rehabilitation based on EIT, the method comprising:

[0068] Using any of the EIT-guided pulmonary rehabilitation methods to obtain data on pursed-lip breathing in COPD patients;

[0069] scoring the pursed lip breathing action based on the pursed lip breathing data;

[0070] Preferably, the score is compared with a historical score to obtain the degree of lung rehabilitation.

[0071] Advantages of the present invention:

[0072] 1. For the first time, the use of EIT to evaluate PLB was demonstrated and its effectiveness was proven. EIT provides objective information for physical therapists to evaluate training results, which helps physical therapists teach and guide patients on PLB operations. Patients can also learn and adjust PLB through visual data, which is beneficial to patients' pulmonary rehabilitation training.

[0073] 2. EIT evaluates PLB using five indicators, namely inhalation depth, ratio of expiratory time to inhalation time, expiratory speed, breathing uniformity, and breathing stability, to quantify overall ventilation. Four indicators, namely ventral-dorsal ventilation ratio, left-right ventilation ratio, ventilation center, and local breathing time constant, are used to quantify local ventilation. This allows EIT to more clearly quantify the details of patients performing PLB. Physical therapists can observe the problems that patients encounter during PLB through specific parameters, which is conducive to providing corresponding guidance for specific problems.

[0074] 3. EIT can capture the volume and time characteristics of PLB in quiet breathing and pursed lip breathing, which helps patients compare the differences between the two types of breathing, thereby deepening their understanding of the key points of PLB and mastering PLB skills. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] 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.

[0076] Figure 1 A schematic flow chart of a method for guiding pulmonary rehabilitation based on EIT provided in an embodiment of the present invention;

[0077] Figure 2 A schematic diagram of a system for EIT-guided pulmonary rehabilitation provided in an embodiment of the present invention;

[0078] Figure 3 A schematic diagram of a device for EIT-guided pulmonary rehabilitation provided in an embodiment of the present invention;

[0079] Figure 4 A schematic diagram of overall ventilation and local ventilation analysis of an EIT image provided by an embodiment of the present invention;

[0080] Figure 5 Schematic diagram of overall impedance changes when one patient in each of the conventional group (a) and the EIT-guided group (b) performs quiet breathing (QB) and pursed lip breathing (PLB) provided in an embodiment of the present invention;

[0081] Figure 6Comparison of overall ventilation parameters between the conventional group and the EIT-guided group during quiet breathing (QB) and pursed lip breathing (PLB) provided in an embodiment of the present invention;

[0082] Figure 7 A schematic diagram provided for an embodiment of the present invention shows a comparison of local ventilation parameters between a conventional group and an EIT-guided group during quiet breathing (QB) and pursed lip breathing (PLB);

[0083] Figure 8 A schematic diagram of a pursed lip breathing (PLB) performance scoring analysis provided by an embodiment of the present invention;

[0084] Fig. 9 Schematic diagram of the EIT electrode belt provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0085] 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.

[0086] 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 sequence numbers of the operations, such as S101, S102, etc., are only used to distinguish between different operations, and the sequence 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.

[0087] Figure 1 A schematic diagram of a method for guiding pulmonary rehabilitation based on EIT provided by an embodiment of the present invention specifically includes:

[0088] S101: Acquire ventilation signal data of pulmonary rehabilitation patients;

[0089] In one embodiment, the pulmonary rehabilitation patients include one or more of the following:

[0090] Chronic obstructive pulmonary disease, chronic bronchial asthma, cystic fibrosis, restrictive lung disease.

[0091] In one embodiment, chronic obstructive pulmonary disease (COPD) is a common chronic disease characterized by chronic bronchitis and / or emphysema with airflow obstruction, which can further develop into cor pulmonale and respiratory failure. It is related to abnormal inflammatory response to harmful gases and particles, and has high disability and mortality rates. The global incidence rate of people over 40 years old has reached 9% to 10%.

[0092] In one specific embodiment, hospitalized patients with acute exacerbation of chronic obstructive pulmonary disease (AECOPD) between December 2022 and August 2023 were screened. Inclusion criteria were (1) younger than 90 years old; (2) no other obvious lung diseases and obvious symptoms; (3) difficulty in completing deep breathing due to coughing and other reasons; (4) AECOPD was under control and ready to be discharged; (5) planning to receive PLB training and being a PLB novice. Exclusion criteria included: difficulty in communication; chest skin damage that could not fix the EIT electrode belt; other contraindications for the use of pulmonary EIT (such as pacemakers).

[0093] In a specific embodiment, a total of 32 patients with COPD were included in the study (conventional group: 14 males and 2 females; EIT-guided group: 14 males and 2 females). Table 1 summarizes the demographic characteristics of the patients.

[0094] Table 1 Demographic characteristics and lung function parameters of the subjects

[0095]

[0096]

[0097] Values ​​are mean ± SD. FVC, forced expiratory volume; FEV1, forced expiratory volume in 1 second; pred, predicted value; meas, measured value.

[0098] In a specific embodiment, the method further comprises data preprocessing, using a filter to filter the patient ventilation signal data to obtain filtered signal data;

[0099] Preferably, the passband frequency range of the filter is set to be 0.05 Hz to 0.65 Hz.

[0100] In a specific embodiment, EIT image reconstruction: In order to improve the quality of the ventilation signal, the present invention designs a 5th bandpass filter with a passband frequency of 0.05Hz to 0.65Hz to process the collected EIT data, because the respiratory rate of all patients during quiet breathing and PLB operation is approximately 0.14Hz to 0.5Hz.

[0101] S102: performing image reconstruction on the ventilation signal data to obtain an EIT image;

[0102] In one embodiment, chest electrical impedance tomography (EIT) is a relatively new medical imaging technique that can generate real-time images of ventilation distribution over time by calculating dynamic impedance changes in the chest cavity. In chest EIT, an insensitive alternating current is injected into the chest through an external electrode array attached around the chest, and the corresponding voltage is recorded for image reconstruction.

[0103] In one embodiment, the image reconstruction algorithm includes one or more of the following: discrete Fourier transform, fast Fourier transform, nearest neighbor interpolation algorithm, bilinear interpolation algorithm, singular value decomposition, GREIT algorithm;

[0104] In one embodiment, the image reconstruction uses a GREIT algorithm to perform EIT image reconstruction, the GREIT algorithm uses the relative change of the boundary voltage to calculate the optimal distribution of the relative change of the patient's chest impedance Δρ to obtain the impedance distribution, and the optimal distribution is gridded into an EIT image;

[0105] Preferably, the following error of the impedance distribution is minimized by optimizing through training of a set of distributions;

[0106] Preferably, the following error is expressed as:

[0107]

[0108] Among them, ε 2 (R) represents the following error, represents the training target distribution, and the boundary change ΔV corresponds to the required impedance change W represents the weight of each target, and R represents the reconstruction matrix.

[0109] In a specific embodiment, GREIT (Graz consensus Reconstruction algorithm for EIT) is a lung EIT image reconstruction algorithm for reconstructing EIT images. The purpose of GREIT is to calculate the optimal distribution of the relative change Δρ of the chest impedance through the relative change ΔV of the boundary voltage:

[0110] Δρ=R·ΔV

[0111] Where Δρ=ρ t -ρ baseline , ΔV=V t -V baseline , R is the optimal reconstruction matrix determined by training and learning methods, that is, by a set of “training” objectives t (i)or its distribution, minimizing the following error:

[0112]

[0113] in, is the training target distribution. For each “training” target, its boundary change ΔV is related to the expected impedance change The weight w of each target represents the importance of its contribution. The reconstruction matrix is ​​calculated based on the chest model established by the CT image of the 4th-5th intercostal space of a healthy male and stored in advance for subsequent reconstruction of EIT images. To facilitate subsequent analysis, this study gridded each reconstructed impedance distribution into a 32×32 pixel EIT image.

[0114] For each patient, the baseline V baseline It was defined as the boundary voltage at the end of expiration of the first respiratory cycle during the last test QB period, and finally the time series EIT images of the entire last test period were reconstructed.

[0115] S103: Guiding the patient to perform pulmonary rehabilitation breathing based on the EIT image.

[0116] In one embodiment, the pulmonary rehabilitation breathing training method includes one or more of the following: pursed lip breathing, abdominal breathing, lip contraction breathing, and a three-ball breathing trainer.

[0117] In one embodiment, abdominal breathing: the patient lies flat or half-lying on the bed, with legs bent and hands placed on both sides of the body, inhales through the nose and exhales through the mouth, with the ratio of inhalation to exhalation being 1:2.

[0118] In one embodiment, lip pursed breathing: Inhale air through the nostrils, similar to a mouthpiece, whistle-style breathing.

[0119] In one embodiment, a three-ball breathing trainer: the patient is in a relatively relaxed and comfortable position, puts the breathing device in the mouth, takes the maximum inhalation through the mouthpiece and holds it for 5 seconds before exhaling.

[0120] In one embodiment, pursed lip breathing (PLB) is a strategy of slowly expelling air, controlled by puckering the lips during exhalation. PLB is indicated for COPD patients who have difficulty breathing. PLB improves ventilation, slows air trapping, prolongs airway open time, reduces respiratory rate, slows breathing rate, allows old air to flow out, and brings new airflow into the lungs.

[0121] In one embodiment, the guiding is performed by quantifying the EIT image, wherein the quantification includes global ventilation assessment and / or local ventilation assessment;

[0122] Preferably, the overall ventilation assessment is to first sum the pixel values ​​of the EIT image at time t to obtain a pixel sum, use the pixel sum as the overall impedance at time t, and then assess the overall ventilation based on the overall impedance;

[0123] Preferably, the overall impedance is expressed as:

[0124]

[0125] in, represents the i-th pixel value at time t, ρ t represents the overall impedance at time t, N represents the total number of pixels of the EIT image;

[0126] Preferably, a functional EIT image is constructed based on the EIT image, and local ventilation characteristics are quantified by the functional EIT image, and local ventilation volume is evaluated by the local ventilation characteristics;

[0127] Preferably, the functional EIT image is calculated by linear regression and is expressed as:

[0128]

[0129] Among them, Δρ i (t) represents the impedance change of the i-th pixel in the original time series EIT image over time; α i and β i represents the regression coefficient of the i-th pixel, χ i represents the fitting error of the i-th pixel, represents the i-th pixel value at time t, ρ t Represents the overall impedance. The linear regression coefficient is calculated for all pixels, and the regression coefficient α i Constructs the functional EIT image Z. α i represents the linear correlation between the ith pixel and the overall lung impedance, α i The larger the value, the more relevant the pixel is to lung ventilation.

[0130] In one embodiment, the indicators used in the overall ventilation assessment include one or more of the following: inspiratory depth, ratio of expiratory time to inspiratory time, exhalation speed, breathing uniformity, and breathing stability;

[0131] Preferably, the inhalation depth represents the magnitude of the inhalation force, which is obtained by calculating the percentage of the inhalation volume of pulmonary rehabilitation breathing to the inhalation volume of deep breathing;

[0132] Preferably, the inhalation depth is expressed as:

[0133]

[0134] in, and Represent the changes in PLB and tidal impedance during deep breathing, respectively. Tidal impedance change is the difference between the overall lung impedance at the end of inspiration and the overall lung impedance at the end of expiration.

[0135] Preferably, the ratio of the exhalation time to the inhalation time is obtained by calculating the percentage of the exhalation time to the inhalation time;

[0136] Preferably, the exhalation speed assessment exhalation speed is obtained by calculating the ratio of the inspiratory volume to the exhalation time;

[0137] Preferably, the exhalation speed is expressed as:

[0138]

[0139] Among them, F n Represents the breathing rate, Indicates the change of PLB moisture impedance, t exp Indicates the exhalation time;

[0140] Preferably, the breathing uniformity is obtained by calculating the change of the exhaled volume per unit time in the entire breathing phase;

[0141] Preferably, the respiratory stability is obtained by calculating the change of overall impedance at the end of breathing.

[0142] In one embodiment, the indicators used in the local ventilation assessment include one or more of the following: ventral-dorsal ventilation ratio, left-right ventilation ratio, ventilation center, local respiratory time constant;

[0143] Preferably, the ventral-dorsal ventilation ratio is obtained by calculating the ratio of the sum of ventral pixels to the sum of dorsal pixels;

[0144] Preferably, the calculation of the ventral-dorsal ventilation ratio VtoD is expressed as:

[0145]

[0146] in, and Respectively represent the sum of ventral pixel values ​​and dorsal pixel values, Z i is the value of the i-th pixel of the functional EIT image;

[0147] Preferably, the left-right ventilation ratio is obtained by calculating the ratio of the sum of the right pixel values ​​to the sum of the left pixel values. The calculation of the left-right ventilation ratio RtoL is expressed as:

[0148]

[0149] in, and Represents the sum of the pixel values ​​on the right and the sum of the pixel values ​​on the left, Z i is the value of the i-th pixel of the functional EIT image;

[0150] Preferably, the ventilation center is obtained by weighting the pixel value of each pixel of the functional EIT image and its coordinate position;

[0151] Preferably, the ventilation center is expressed as:

[0152] CoV=∑(Z i ·y i ) / ∑Z i 100%

[0153] Among them, CoV represents the ventilation center, y i Represents the height of the i-th pixel after scaling, Z i is the value of the i-th pixel of the functional EIT image;

[0154] Preferably, the local respiratory time constant is calculated by fitting an exponential curve to the expiratory impedance signal and then calculating the time constant of each pixel;

[0155] Preferably, the local breathing time constant is expressed as:

[0156]

[0157] Among them, Δρ i represents the value of the i-th pixel, C i represents the end-expiratory impedance of the ith pixel, represents the initial local breathing time constant. τ i is the expiratory time constant of the i-th pixel, which reflects the time required for the lung tissue at the i-th pixel to exhale 2 / 3 times the maximum expiratory volume. By calculating all pixels, the expiratory time constant of all pixels in a single respiratory cycle can be obtained. Furthermore, the expiratory time constants of each pixel in multiple respiratory cycles can be averaged, and the average value is used as the expiratory time constant of each pixel in multiple respiratory cycles.

[0158] In one specific embodiment, a physical therapist taught 16 COPD patients to do PLB with or without the help of EIT in an EIT-guided group and a conventional group, respectively. Then, the PLB of all patients was continuously monitored using EIT in the final test, and another physical therapist evaluated the PLB performance of all patients before and after observing EIT. Finally, the global and regional ventilation of the two groups of patients were compared, and the scores before and after observing EIT were compared.

[0159] In one specific embodiment, patients are alternately divided into two groups according to the order of inclusion: a conventional group and an EIT-guided group. Before the formal experiment begins, the patients are instructed to remain in a sitting position, and an experienced physical therapist teaches PLB to each patient. The breathing procedure of the PLB action is defined as follows. First, keep the auxiliary muscles of breathing relaxed, such as the neck and shoulder muscles. Second, take a slow, deep breath through the nose. Third, exhale slowly, with the exhalation time at least four times the inhalation time, and close or purse the lips when exhaling, and do not puff up the cheeks.

[0160] In one specific embodiment, in the conventional group, PLB was taught to patients through the following steps: First, the role of PLB in improving respiratory symptoms was explained to the patients so that the patients understood the significance of PLB, thereby increasing their learning enthusiasm. Second, a lit candle was placed about 25 cm in front of the patient to assess the exhalation rate, that is, during the exhalation process, the flame continued to move slightly but could not be blown out. Third, the physical therapist repeatedly explained the key points of PLB operation to the patient and demonstrated the operation multiple times to improve the patient's PLB performance. The entire teaching process was limited to 10 minutes.

[0161] In the EIT-guided group, as in the conventional group, the meaning of PLB was first explained. Second, the global and local EIT parameters were explained to the patients. Third, the key points of PLB operation were explained to the patients under the multiple operation demonstrations of the physiotherapist, and the patients improved their PLB operation by observing the EIT parameters in real time. The entire teaching process was also limited to 10 minutes.

[0162] After learning, each subject was familiarized with the PLB and was asked to complete a final test consisting of the following sequence of movements: 1 min of quiet breathing (QB), 5 cycles of breathing as deep as possible, 1 min of recovery QB, 15 cycles of PLB without EIT feedback, and then 1 min of recovery QB. During the entire test, lung EIT data were continuously measured and saved.

[0163] In a specific embodiment, PLB is assessed by EIT images, including global ventilation assessment, local ventilation assessment, such as Figure 4 Shown are time series EIT images obtained for global and regional ventilation analysis.

[0164] In a specific embodiment, overall ventilation assessment during PLB: Since there is a good correlation between impedance change and ventilation change, the sum of all pixel values ​​of each EIT image is determined as the overall impedance at a certain moment to assess the overall ventilation at a certain time point. Therefore, the overall impedance change ρ calculated from the time series EIT images is t It can be used to reflect the overall ventilation volume over time, that is, in Represents the value of the i-th pixel at time point t.

[0165] In a specific embodiment, according to the special requirements of PLB maneuvers, the following indicators are proposed to evaluate the characteristics of PLB maneuvers.

[0166] Exhalation depth: This indicator evaluates the magnitude of the inspiratory force, and is calculated as the percentage of the inspiratory volume during PLB to the inspiratory volume during deep breathing, that is, in, and Respectively represent the changes in PLB and tidal impedance during deep breathing, such as Figure 4 As shown in (a), and The average value of tidal impedance change during all respiratory cycles during PLB and deep breathing is obtained, that is, in, represents the change in tidal impedance during the respiratory cycle during PLB, Indicates the change in tidal impedance during deep breathing.

[0167] Ratio of expiratory time to inspiratory time: This index evaluates the time distribution of the entire respiratory cycle during PLB, and is calculated as the percentage of expiratory time to inspiratory time, that is, the percentage of expiratory time to inspiratory time, that is, t exp / t ins , the average value of the percentage of exhalation time to inhalation time in all respiratory cycles is taken as the final value, that is,

[0168] Exhalation speed: This indicator measures the exhalation speed during PLB, and is calculated as the ratio of inspiratory volume to exhalation time. In order to eliminate individual differences, the relative inspiratory depth is used to reflect the inspiratory volume. Therefore, the normalized exhalation speed can be obtained by:

[0169] mean(F1,F2,…F n ,…)

[0170]

[0171] in, is the change in tidal impedance during the nth respiratory cycle.

[0172] Exhalation uniformity: This index describes the uniformity of exhalation during PLB. It is calculated as the change in exhaled volume per unit time during the entire exhalation phase, that is, It represents the overall impedance change in the mth unit time in the nth respiratory cycle, such as Figure 4 In the present invention, the unit time is defined as 200 milliseconds.

[0173] Respiratory stability: This indicator describes the breathing condition during PLB and is calculated by the overall impedance change at the end of exhalation, i.e. represents the overall impedance at the end of exhalation in the respiratory cycle, such as Figure 4 (a) shown.

[0174] In a specific embodiment, in order to evaluate the local ventilation during the implementation of PLB, the present invention constructs a functional EIT (fEIT) image using time series EIT images to quantify specific local ventilation characteristics. The present invention adopts the global-local impedance change regression method because it is robust to signals with different phase information. The fEIT image (Z) of PLB is calculated for each subject, and the image consists of the regression coefficients of the following linear regression formula:

[0175]

[0176] Δρ i (t) represents the impedance change of the ith pixel in the original time series EIT image over time, α and β represent the regression coefficients, and χ represents the fitting error. i and β i represents the regression coefficient of the i-th pixel, χ i represents the fitting error of the i-th pixel.

[0177] Since PLB is a breathing pattern controlled by the patient, the local ventilation distribution may be affected by the respiratory muscles. To measure these effects, the ventral-dorsal ratio (VtoD), the left-right lung ratio (RtoL), and the ventilation center (CoV) were calculated. VtoD is calculated by calculating the ratio of the sum of dorsal pixels to the sum of ventral pixels, that is, RtoL is CoV is another parameter that describes the ventilation distribution and is calculated by weighting the impedance value with the position in the anterior-posterior coordinates:

[0178] CoV=∑(Z i ·y i ) / ∑Z i100%

[0179] Among them, y i is the height in pixels after scaling so that the bottom (back) of the image is 100%.

[0180] In addition, considering the longer exhalation time during PLB, the local exhalation time constant was also calculated to evaluate the local airflow. The time constant of each pixel was calculated by fitting an exponential curve to the exhalation impedance signal:

[0181]

[0182] Among them, τ i is the time constant of the pixel, and is the end-expiratory impedance. In the present invention, the time constants of all pixels in the lung local are calculated to obtain an EIT-derived time constant image, wherein the lung local consists of pixels whose fEIT image values ​​are greater than 20%*maximum. For each subject, the final EIT-derived time constant EIT image is obtained by calculating the average of the time constant EIT images of all respiratory cycles during PLB. In addition, the final EIT time constant, the median of the EIT image distribution, is used as the final expiratory time constant for each patient.

[0183] In a specific embodiment, statistical analysis was performed using SPSS26 (IBM Software, Armonk, New York), and a P value of less than 0.05 was considered statistically significant. In terms of overall ventilation, five indices (inspiratory depth, ratio of expiratory time to inspiratory time, expiratory velocity, expiratory uniformity, and respiratory stability) were compared between the conventional group and the EIT-guided group during the final PLB test and quiet breathing by one-way analysis of variance and post hoc test. In terms of local ventilation distribution, three indices (VtoD, RtoL, CoV, and expiratory time constant) during PLB and QB were also compared between the two groups. In terms of scoring, the difference in the scores of the two groups was first compared, and then the scores with or without EIT were compared by Bran-Altman plots and Student's t-test.

[0184] In a specific embodiment, Figure 5 Figure 2 shows the overall ventilation changes during QB and PLB in one patient from the conventional group and the EIT-guided group. Tidal volumes during PLB were greater than those during quiet breathing in both groups, whereas the opposite was true for respiratory rate. Expiratory time was significantly longer than inspiratory time during PLB compared with QB.

[0185] In a specific embodiment, Figure 6Comparison of overall ventilation parameters between the conventional and EIT-guided groups during QB and PLB, including inspiratory depth, expiratory to inspiratory time ratio, expiratory rate, expiratory uniformity, and respiratory stability, was shown. In terms of QB, there were no significant differences in overall ventilation parameters between the conventional and EIT-guided groups.

[0186] The inspiratory depth of the two groups of patients during PLB was significantly greater than that during QB. Figure 6 (a), P<0.001). The inspiratory depth during PLB in the EIT-guided group (0.74±0.09) was greater than that in the conventional group (0.60±0.19, P<0.001). However, in the EIT-guided group, the inspiratory depth of all patients was relatively high. These results were similar to the ratio of expiratory time to inspiratory time, as shown in Figure 2. Figure 6 Shown in (b). In the EIT-guided group, only 3 patients had an expiratory to inspiratory time ratio of less than 4 during PLB, compared with 10 patients in the conventional group.

[0187] The exhalation speed of the two groups of patients during PLB was significantly lower than that during QB. Figure 6 As shown in (c), P < 0.001, but there was no significant difference in the exhalation speed between the two groups of patients during PLB (P = 0.428), indicating that both groups of patients actively controlled the exhalation process. The exhalation uniformity during PLB in the conventional group was significantly greater than that during QB, as shown in Figure 6 As shown in (d), P < 0.05, while there was no significant difference in the EIT-guided group (P = 0.789), indicating that patients in the EIT-guided group had better control over the exhalation process.

[0188] The respiratory stability during PLB in the conventional group was significantly greater than that during QB, e.g. Figure 6 As shown in (e), P < 0.01, indicating that PLB makes the respiratory rhythm unstable. In contrast, the respiratory stability during PLB in the EIT-guided group was not significantly different from that during QB (P = 0.0541), and was also significantly lower than that during PLB in the conventional group (P < 0.001), indicating that the respiratory rhythm of patients in the EIT-guided group was more stable.

[0189] In one embodiment, a comparison of local ventilation during PLB is performed. Figure 7The comparison of local ventilation parameters during QB and PLB between the conventional group and the EIT-guided group is shown. (a) Time series EIT images during QB and PLB in the conventional group; (b) Time series EIT images during QB and PLB in the EIT-guided group; (c) Comparison of ventral-to-dorsal ratio; (d) Comparison of left and right ventilation ratios; (e) Comparison of ventilation centers; (f) Comparison of expiratory time constants. During QB, there were no significant differences in the four local ventilation parameters between the two groups. During PLB, the ventral-to-dorsal ratio increased in both groups (P = 0.125, as shown in Figure 5). Figure 7 (c)), but only the EIT-guided group showed a significant difference (P<0.01). There was no significant difference in the ratio of left and right ventilation between the two groups (as shown in Figure 7 Compared with QB, CoV decreased significantly in both groups during PLB (as shown in (d)). Figure 7 As shown in (e), conventional group P<0.05, EIT-guided group P<0.01). The expiratory time constants during PLB in both groups were significantly greater than those during QB (P<0.001), and the expiratory time constants during PLB in the EIT-guided group were greater than those in the conventional group (P<0.001).

[0190] In one specific embodiment, PLB performance scores are compared. Figure 8 The analysis of the scores of PLB performance with and without the help of EIT is shown. The Bland-Altman plot analysis showed that the differences between the conventional group and the EIT-guided group were 87.5% and 100%, respectively, both within the 95% agreement range (e.g. Figure 8 (a) and (b)), indicating that there was a high degree of agreement between the subjective score and the EIT-assisted score. In addition, the scores of both groups after EIT observation were significantly lower than the subjective scores (P<0.05), which means that EIT reveals more details of the respiratory status during PLB. In addition, the score decrease in the conventional group (from -5 to -1, -2.68±1.1) was significantly greater than that in the EIT-guided group (from -2 to 0, -1.19±0.72), indicating that EIT can sensitively quantify the performance of different levels of PLB.

[0191] In a specific embodiment, in this prospective study, the present invention demonstrated for the first time a method for evaluating PLB using EIT and explored its effectiveness in guiding the training process and evaluating training results. The results of the present invention showed that the global and local ventilation parameters of the EIT-guided group were better than those of the conventional group. Experienced physiotherapists gave higher scores to the EIT group. On the other hand, physiotherapists adjusted their scores after reviewing the EIT data, indicating that EIT provides objective information for physiotherapists to evaluate training results.

[0192] In a specific embodiment, the present invention experimentally verifies that, in terms of overall impedance, the ratio of inspiratory depth and expiratory time to inspiratory time during PLB is greater than that during QB, while the expiratory speed is less than that during QB, indicating that EIT can correctly capture the capacity and time characteristics of PLB and QB. In addition, there are significant differences in the inspiratory depth and expiratory time to inspiratory time ratio between the two groups of patients (e.g. Figure 6 (a) and 6(b)), which indicates that with the help of EIT, patients had a better understanding of the implementation of PLB. There was no significant difference in the expiratory speed between the two groups (e.g. Figure 6 (c)). The present invention believes that the patients in the conventional group not only have a shorter exhalation time (expressed as the ratio of exhalation to inhalation time), but also have shallower breathing (expressed as the depth of inhalation). Therefore, the exhalation speed (calculated as the ratio of inhalation volume to exhalation time) is maintained at a comparable level with the EIT-guided group. The use of candles in the conventional group may also be one of the reasons for the continuous and stable exhalation. In addition, the exhalation uniformity of the EIT-guided group is significantly less than that of the conventional group (e.g. Figure 6 (d), P < 0.01), indicating that by subjectively controlling the respiratory muscles, the inhaled gas was exhaled more evenly. This can be clearly observed from the overall impedance change. The impedance curve of the EIT-guided group decreased at an almost fixed slope during the exhalation phase (e.g. Figure 5 (b)), while the conventional group did not (e.g. Figure 5 (a)). In addition, the EIT-guided group had significantly less respiratory stability during PLB than the EIT-conventional group (P<0.01), indicating that the breathing depth of patients in the EIT-guided group was more stable with the help of EIT. In short, these results show that compared with the empirical PLB operation teaching method, EIT can provide patients with real-time responses during PLB training from the perspective of the impact of PLB on overall ventilation, thereby effectively guiding patients to master PLB skills.

[0193] In terms of local impedance distribution, the ratio of ventral to dorsal increased significantly and CoV also decreased significantly when PLB was implemented compared with QB. These results may be related to the breathing pattern of PLB. In the experiment, the present invention found that patients performed PLB in a thoracic breathing mode characterized by a significant bulge of the chest. During thoracic breathing, when the central tendon remains stable and the diaphragm contracts, the ribs are lifted and the chest expands forward and laterally, allowing more air to enter the ventral side. However, PLB did not lead to a significant difference in the ratio of the left and right lungs, indicating that the contraction and relaxation of the respiratory muscles on both sides are balanced. In addition, the expiratory time constant of local ventilation during PLB is greater than that during QB, which may indirectly indicate that PLB avoids the rapid collapse of local small airways. Therefore, EIT can reveal local respiratory muscle contraction from the perspective of the effect of PLB on local ventilation.

[0194] In a specific embodiment, the Bland-Altman plot analysis showed that the subjective scores of the conventional group and the EIT-guided group were highly consistent with the scores performed with the help of EIT, such as Figure 8 As shown, this indicates that the scoring with the help of EIT is reliable. However, the subjective scores of both groups were lower than the scores after observing the EIT parameters. These results may be due to the fact that subjective observation can only roughly evaluate the general situation of PLB operation through some physical appearances, such as estimating the depth of inspiration by the degree of chest relaxation, but cannot accurately judge the details of PLB operation, such as the accurate depth of inspiration (the ratio of inspired volume to vital capacity), which even experienced physical therapists cannot accurately judge. However, EIT can quantify the technical details of PLB and provide recommended global and local ventilation indicators during PLB operation. In addition, the score decrease of the conventional group before and after reviewing the EIT data was significantly lower than that of the EIT-guided group, which further proves the objective validity of the proposed global and local ventilation indicators in evaluating PLB.

[0195] In one specific embodiment, analysis of EIT in guided teaching. PLB is a special breathing technique that generates a preparatory pressure in the airway so that the isobaric point in the airway moves toward the alveoli. During exhalation, the small airways remain expanded, which is conducive to the full discharge of residual gas in the lungs and the increase of tidal volume. Therefore, the respiratory rate slows down, which is conducive to the full diffusion of gas in the alveoli, thereby improving hypoxia and carbon dioxide retention, and relaxing the patient's body. In addition, studies have also found that PLB training has a certain effect on relieving diaphragm fatigue. Therefore, the patient's dyspnea can be alleviated, thereby improving exercise tolerance. Although some patients with COPD often perform PLB training spontaneously, teaching patients to perform PLB has been shown to enhance exercise capacity and lung function.

[0196] In addition, previous studies have shown that teaching PLB to patients can lead to significant positive changes in respiratory and cardiac parameters in COPD patients. In order to enable patients to correctly master PLB operation as quickly as possible, this paper explores the feasibility of using EIT to assist physical therapists in teaching PLB to COPD patients, and finds that EIT can dynamically capture the details of PLB operation, thereby improving the efficiency of teaching PLB.

[0197] Compared with the traditional PLB (verbal communication and subjective judgment) teaching method, EIT can provide patients and physical therapists with real-time feedback on respiratory status, including overall ventilation changes (overall chest impedance) and local ventilation distribution (time series EIT images). On the one hand, the response information enables patients to visually observe their breathing and quickly understand how they should actively control their respiratory muscles to meet the requirements of the PLB maneuver. On the other hand, the response information enables physical therapists to intuitively see the patient's PLB performance and quickly understand the patient's problems in controlling breathing, so as to give corresponding guidance. In short, EIT builds a visual communication bridge between patients and physical therapists when teaching patients PLB operations.

[0198] In a specific embodiment, according to the characteristics of PLB operation, five parameters of overall ventilation are proposed to quantitatively evaluate the details of PLB operation, including the inhalation depth corresponding to "deep inhalation", the expiratory to inhalation time ratio and the expiratory speed corresponding to "slow exhalation", the expiratory uniformity corresponding to "uniform exhalation", and the respiratory stability corresponding to "stable end-expiratory lung capacity". In addition, four parameters of local ventilation are proposed to quantitatively evaluate the respiratory muscles during the implementation of PLB, including the ventral-dorsal ratio and ventilation center corresponding to the "respiratory muscle force mode", and the "respiratory muscle force balance" corresponding to the left and right ventilation ratio. And the respiratory muscle expiratory time constant corresponding to the "force duration of the respiratory muscle". The results of the present invention show that there are significant differences in these indicators between QB and PLB or between the conventional group and the EIT-guided group. The results prove the scientific rationality and objective practicality of these indicators.

[0199] In a specific embodiment, an objective method that can help physical therapists teach PLB operation to COPD patients is highly needed in clinical practice. In this study, the present invention explored the possibility of evaluating PLB operation by monitoring the ventilation status of patients during the implementation of PLB in 32 COPD patients. The results showed that there were significant differences in the overall and local ventilation between QB and PLB, and between the EIT-guided group and the conventional group. These results show that EIT can capture the details of PLB operation, which may be a potential tool for quantitatively evaluating PLB performance, thereby helping physical therapists teach PLB operation to COPD patients.

[0200] Figure 2 A schematic diagram of a system for guiding pulmonary rehabilitation based on EIT provided by an embodiment of the present invention specifically includes:

[0201] Acquisition unit: acquires ventilation signal data of pulmonary rehabilitation patients;

[0202] Reconstruction unit: performing image reconstruction on the ventilation signal data to obtain an EIT image;

[0203] Evaluation unit: guiding the patient to perform pulmonary rehabilitation breathing based on the EIT image.

[0204] Figure 3 A schematic diagram of a device for EIT-guided pulmonary rehabilitation provided by an embodiment of the present invention specifically includes:

[0205] A memory and a processor; the memory is used to store program instructions; the processor is used to call program instructions, and when the program instructions are executed, any one of the above-mentioned methods for EIT-guided pulmonary rehabilitation is performed.

[0206] In one embodiment, the device uses an electrode belt to collect patient ventilation signal data;

[0207] Preferably, the electrode belt is worn in the intercostal space between the sternum and the patient, and the electrode belt is transversely fixed on the chest;

[0208] Preferably, the length of the electrode belt is set based on the chest circumference of the patient, n electrodes are evenly distributed on the electrode belt, n is a natural number greater than 4, and the electrodes are conductive rubber electrodes;

[0209] Preferably, the electrode belt has 16 electrodes equidistantly distributed, including 12 fixed electrodes;

[0210] Preferably, m buttons are provided on the electrode belt, where m is a natural number greater than 2, and the buttons are located on both sides of the patient's spine and sternum.

[0211] In a specific embodiment, EIT data measurement: Use medical alcohol to clean the chest skin between the 4th and 5th intercostal spaces to reduce the influence of the stratum corneum on the electrode-skin conductivity. Secondly, considering the large breathing amplitude during the implementation of PLB, a specially designed electrode belt with a suitable length is selected by measuring the patient's chest circumference to enhance the stability of the electrode-skin interface. The electrode belt has 16 electrodes equidistantly distributed, including 12 fixed conductive rubber electrodes and 4 buttons located on both sides of the spine and sternum for connecting disposable electrocardiogram electrodes, such as Fig. 9 As shown in (a), finally, the electrode belt is fixed horizontally on the chest at the level of the 4th-5th intercostal space beside the sternum and connected to the EIT system through the electrode wire, as shown in Fig. 9 (b) shown.

[0212] The original EIT data were collected by a commercial EIT system (VenTom-100, MidasMED Biomedical technology, Suzhou, China) with an acquisition rate of 20 frames / s, an operating frequency of 50 kHz, and a signal-to-noise ratio greater than 70 dB. In order to improve the sensitivity of the central part of the chest, the data acquisition mode of opposite excitation-adjacent measurement was selected, and a current of 1 mArms was injected through a pair of opposite electrodes, and the voltage on the other adjacent electrodes was measured.

[0213] A computer-readable storage medium stores a computer program, wherein the computer program is executed by a processor to perform any one of the above-mentioned methods for EIT-guided pulmonary rehabilitation.

[0214] A method for evaluating pulmonary rehabilitation based on EIT, the method comprising:

[0215] Using any of the EIT-guided pulmonary rehabilitation methods to obtain data on pursed-lip breathing in COPD patients;

[0216] scoring the pursed lip breathing action based on the pursed lip breathing data;

[0217] Preferably, the score is compared with a historical score to obtain the degree of lung rehabilitation.

[0218] In a specific embodiment, an experienced physical therapist, without knowing which group the patient belongs to, rates the PLB performance based on his own subjective evaluation according to the items used in clinical practice listed in Table 2 (i.e., without the help of EIT). Then, he rates the PLB performance again (i.e., with the help of EIT) after carefully reviewing the results of EIT.

[0219] In a specific embodiment, based on the overall ventilation situation, the physical therapist scores the performance of the PLB according to the clinical practice items listed in Table 2.

[0220] Table 2 Evaluation score sheet for pursed lip breathing

[0221]

[0222]

[0223] The verification results of this verification embodiment show that assigning inherent weights to indications can improve the performance of the method relative to the default setting. Those skilled in the art can clearly understand that for the convenience and simplicity 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. In the several embodiments provided in this 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, and 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 coupling or direct coupling or communication connection between each other shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment. 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. A person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above-mentioned embodiments may be completed by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc.

[0224] A person skilled in the art can understand that all or part of the steps in the above-mentioned embodiment method can be implemented by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned medium storage can be a read-only memory, a disk or an optical disk, etc.

[0225] 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 guiding pulmonary rehabilitation based on EIT, characterized in that: The method comprises: Obtain ventilation signal data of pulmonary rehabilitation patients; Performing image reconstruction on the ventilation signal data to obtain an EIT image; Based on the EIT image, the patient is guided to perform pulmonary rehabilitation breathing. The guidance is performed by quantifying the EIT image, and the quantification includes overall ventilation assessment; the overall ventilation assessment is to first sum the pixel values ​​of the EIT image at time t to obtain the pixel sum, use the pixel sum as the overall impedance at time t, and then evaluate the overall ventilation based on the overall impedance; the indicators used in the overall ventilation assessment include one or more of the following: inhalation depth, ratio of expiratory time to inhalation time, exhalation speed, breathing uniformity, and breathing stability; the inhalation depth represents the magnitude of the inhalation force, which is obtained by calculating the percentage of the inhalation volume of pulmonary rehabilitation breathing to the inhalation volume of deep breathing; The ratio of the exhalation time to the inhalation time is obtained by calculating the percentage of the exhalation time to the inhalation time; The exhalation speed is obtained by calculating the ratio of the tidal impedance change to the exhalation time; The breathing uniformity is obtained by calculating the change of the exhaled volume in the whole breathing phase per unit time; The respiratory stability is obtained by calculating the change in total impedance at the end of breathing.

2. The method for guiding pulmonary rehabilitation based on EIT according to claim 1, characterized in that: A functional EIT image is constructed based on the EIT image, and local ventilation characteristics are quantified by the functional EIT image, and local ventilation volume is evaluated by the local ventilation characteristics.

3. The method for guiding pulmonary rehabilitation based on EIT according to claim 2, characterized in that: The functional EIT image is calculated by linear regression and is expressed as: Among them, Δρ i (t) represents the impedance change of the i-th pixel in the original time series EIT image over time; α i and β i represents the regression coefficient of the i-th pixel, χ i represents the fitting error of the i-th pixel, represents the i-th pixel value at time t, ρ t Represents the overall impedance.

4. The method for guiding pulmonary rehabilitation based on EIT according to claim 1, characterized in that: The quantification includes global ventilation assessment is replaced by: the quantification includes local ventilation assessment.

5. The method for guiding pulmonary rehabilitation based on EIT according to claim 2 or 4, characterized in that: The indicators used in the evaluation of local ventilation include one or more of the following: ventral-dorsal ventilation ratio, left-right ventilation ratio, ventilation center, and local respiratory time constant.

6. The method for guiding pulmonary rehabilitation based on EIT according to claim 5, characterized in that: The ventral-dorsal ventilation ratio is obtained by calculating the ratio of the sum of ventral pixels to the sum of dorsal pixels.

7. The method for guiding pulmonary rehabilitation based on EIT according to claim 5, characterized in that: The left-right ventilation ratio is obtained by calculating the ratio of the sum of the right pixel values ​​to the sum of the left pixel values. The calculation of the left-right ventilation ratio RtoL is expressed as: in, and Represents the sum of the pixel values ​​on the right and the sum of the pixel values ​​on the left, respectively. Z i is the value of the i-th pixel of the functional EIT image.

8. The method for guiding pulmonary rehabilitation based on EIT according to claim 5, characterized in that: The ventilation center is obtained by weighting the pixel value of each pixel of the functional EIT image and its coordinate position; The ventilation center is represented by: CoV=∑(Z i ·y i ) / ∑Z i ·100% Among them, CoV represents the ventilation center, y i Represents the height of the i-th pixel after scaling, Z i is the value of the i-th pixel of the functional EIT image.

9. The method for guiding pulmonary rehabilitation based on EIT according to claim 5, characterized in that: The local respiratory time constant is obtained by fitting the expiratory resistance signal with an exponential curve and then calculating the time constant of each pixel; The local breathing time constant is expressed as: Among them, τ i represents the time constant of the i-th pixel, Δρ i represents the value of the i-th pixel, C i represents the end-expiratory impedance of the ith pixel, represents the initial local breathing time constant.

10. The method for guiding pulmonary rehabilitation based on EIT according to claim 1, characterized in that: The image reconstruction algorithm includes one or more of the following: discrete Fourier transform, fast Fourier transform, nearest neighbor interpolation algorithm, bilinear interpolation algorithm, singular value decomposition, GREIT algorithm.

11. The method for guiding pulmonary rehabilitation based on EIT according to claim 10, characterized in that: The GREIT algorithm uses the relative change of the boundary voltage to calculate the optimal distribution of the relative change of the patient's chest impedance Δρ to obtain the impedance distribution, and grids the optimal distribution into an EIT image.

12. The method for guiding pulmonary rehabilitation based on EIT according to claim 11, characterized in that: The optimization is performed by training a set of distributions to minimize the following error of the impedance distribution.

13. The method for guiding pulmonary rehabilitation based on EIT according to claim 12, characterized in that: The following error is expressed as: Among them, ε 2 (R) represents the following error, represents the training target distribution, and the boundary change ΔV corresponds to the required impedance change W represents the weight of each target, and R represents the reconstruction matrix.

14. The method for guiding pulmonary rehabilitation based on EIT according to claim 1, characterized in that: The method further includes data preprocessing, using a filter to filter the patient ventilation signal data to obtain filtered signal data.

15. The method for guiding pulmonary rehabilitation based on EIT according to claim 14, characterized in that: The passband frequency range of the filter setting is 0.05 Hz to 0.65 Hz.

16. A system for guiding pulmonary rehabilitation based on EIT, characterized in that: include: Acquisition unit: acquires ventilation signal data of pulmonary rehabilitation patients; Reconstruction unit: performing image reconstruction on the ventilation signal data to obtain an EIT image; Evaluation unit: guiding the patient to perform pulmonary rehabilitation breathing based on the EIT image; The guidance is performed by quantifying the EIT image, and the quantification includes overall ventilation assessment; the overall ventilation assessment is to first sum the pixel values ​​of the EIT image at time t to obtain the pixel sum, use the pixel sum as the overall impedance at time t, and then evaluate the overall ventilation based on the overall impedance; the indicators used in the overall ventilation assessment include one or more of the following: inhalation depth, ratio of expiratory time to inhalation time, exhalation speed, breathing uniformity, and breathing stability; the inhalation depth represents the magnitude of the inhalation force, which is obtained by calculating the percentage of the inhalation volume of pulmonary rehabilitation breathing to the inhalation volume of deep breathing; The ratio of the exhalation time to the inhalation time is obtained by calculating the percentage of the exhalation time to the inhalation time; The exhalation speed is obtained by calculating the ratio of the tidal impedance change to the exhalation time; The breathing uniformity is obtained by calculating the change of the exhaled volume in the whole breathing phase per unit time; The respiratory stability is obtained by calculating the change in total impedance at the end of breathing.

17. A device for guiding pulmonary rehabilitation based on EIT, characterized in that: include: A memory and a processor, wherein the memory is used to store program instructions; the processor is used to call the program instructions, and when the program instructions are executed, the EIT-guided pulmonary rehabilitation method according to any one of claims 1 to 15 is implemented.

18. The device for EIT-guided pulmonary rehabilitation according to claim 17, characterized in that: The device uses an electrode belt to collect patient ventilation signal data.

19. The device for EIT-guided pulmonary rehabilitation according to claim 18, characterized in that: The electrode belt is worn at the patient's sternal intercostal space and is laterally fixed on the chest.

20. The device for EIT-guided pulmonary rehabilitation according to claim 18, characterized in that: The length of the electrode belt is set based on the chest circumference of the patient. N electrodes are evenly distributed on the electrode belt, where n is a natural number greater than 4. The electrodes are conductive rubber electrodes.

21. The device for EIT-guided pulmonary rehabilitation according to claim 20, characterized in that: The electrode belt has 16 electrodes distributed at equal intervals, including 12 fixed electrodes.

22. The device for EIT-guided pulmonary rehabilitation according to claim 18, characterized in that: The electrode belt is provided with m buttons, where m is a natural number greater than 2, and the buttons are located on both sides of the spine and sternum of the patient.

23. A computer-readable storage medium having a computer program thereon, characterized in that: include: When the computer program is executed by a processor, the method for EIT-guided pulmonary rehabilitation according to any one of claims 1 to 15 is implemented.

24. A method for evaluating pulmonary rehabilitation based on EIT, characterized in that: The method comprises: The method for guiding pulmonary rehabilitation based on EIT according to any one of claims 1 to 15 is used to obtain data of pursed lip breathing of COPD patients; The pursed lip breathing action is scored based on the pursed lip breathing data.

25. The method for evaluating pulmonary rehabilitation based on EIT according to claim 24, characterized in that: The score was compared with the historical score to obtain the degree of pulmonary rehabilitation.

Images