Four-dimensional EIT respiration monitoring method based on digital twinning assistance

Abstract

The invention discloses a four-dimensional EIT respiration monitoring method based on digital twinborn assistance, which comprises the following steps: firstly, constructing an individualized digital twinborn model which comprises an accurate three-dimensional geometric structure and electrical characteristic parameters and covers thoracic cavity whole organ systems including double lungs, a heart, a central axis skeleton, a main bronchus, an esophagus and the like on the basis of a chest medical image CT of a patient; the method comprises the steps that firstly, a stable and standardized theoretical reference voltage is generated on a model through electromagnetic field simulation, then, virtual-real fusion is conducted on the theoretical reference voltage, a clinically-collected voltage signal in real time and a clinically-actually-measured reference voltage sequence, and finally, a four-dimensional conductivity change image is reconstructed based on the fused dynamic voltage difference. According to the method, reference drift is effectively inhibited, individualized anatomical information is fused, and semi-absolute quantitative evaluation of the pulmonary ventilation function is achieved.

Description

Technical Field

[0001] The present invention belongs to the fields of biomedical engineering and intelligent medical technology, and specifically relates to a four-dimensional electrical impedance tomography (4D-EIT) respiratory monitoring method based on digital twin assistance. The method aims to achieve high-precision visualization and pathological quantitative analysis of the entire respiratory function cycle by integrating dynamic time series data with an individualized digital twin model. Background Art

[0002] Four-dimensional electrical impedance tomography (4D-EIT), a noninvasive, real-time medical imaging technology, has important applications in critical care and pulmonary function assessment. Currently, differential imaging is a core technology widely used in EIT respiratory monitoring. This method uses the body surface voltage signal at the end of expiration as a reference and calculates the difference between the voltage and other points in the respiratory cycle to reconstruct an image of lung ventilation changes.

[0003] Although differential imaging has core advantages in eliminating baseline interference and suppressing noise, it still has the following inherent and significant limitations, which seriously restrict the depth and breadth of its clinical application: 1) Reference drift problem: The end-expiratory voltage, which serves as the reference, is easily affected by fluctuations in the patient's breathing pattern, such as shortness of breath and changes in tidal volume, and pathological factors such as pleural effusion and atelectasis. This can lead to instability in the reference itself, thereby reducing imaging accuracy and reliability.

[0004] 2) Lack of individualization: Traditional methods do not take into account patient-specific anatomical structures, such as chest deformity, cardiac deviation, or postoperative organ displacement. These individual differences can significantly affect the electric field distribution in EIT measurements, thereby limiting the accuracy of imaging.

[0005] 3) Lack of absolute reference and loss of static information: Differential imaging generates images that represent only relative impedance changes, completely losing static anatomical information that reflects individual thoracic geometry, organ position, and resting tissue conductivity distribution. This not only makes it impossible to perform absolute or semi-absolute quantitative assessments of pulmonary ventilation function, but also significantly reduces the interpretability of the images.

[0006] Therefore, this field urgently needs a new four-dimensional EIT respiratory monitoring method that can effectively supplement key static anatomical information, correct the deviation of the measured reference frame, and improve the quantitative capability of imaging while retaining the core advantages of the differential imaging method. Summary of the Invention

[0007] The technical problem to be solved by the present invention is to overcome the defects of the existing EIT respiratory monitoring technology based on differential imaging, such as inaccurate imaging, unreliable imaging and lack of quantitative capability caused by baseline drift, insufficient individualization and loss of static information.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: The present invention provides a four-dimensional EIT respiratory monitoring method based on digital twin assistance. The core idea of ​​this method is to generate a stable and accurate theoretical voltage reference ( ), and integrate it with the dynamic data collected in real time in the clinic to form an enhanced reference that combines anatomical stability and dynamic physiological adaptability.

[0009] A four-dimensional EIT respiratory monitoring method based on digital twin assistance includes the following steps: Step S1, constructing a personalized digital twin: Based on the chest medical imaging data of the target object, constructing a personalized digital twin model including the three-dimensional geometric structure and electrical characteristic parameters of the main organs in the chest cavity of the target object; Step S2, generating theoretical reference voltage: on the individualized digital twin model, simulating the electromagnetic field distribution of the target object in the end-expiratory hypoventilation steady state, and solving to obtain the standardized theoretical reference voltage ( ); Step S3, clinical data acquisition: using an electrode array arranged on the surface of the target object, real-time acquisition of the target object's surface voltage signal during the respiratory cycle, the surface voltage signal includes a real-time voltage signal ( ) and the clinically measured reference voltage sequence that varies with the respiratory cycle ( ); Step S4, virtual-real fusion calculation: the theoretical reference voltage ( ), the clinically measured reference voltage sequence ( ) and the real-time voltage signal ( ) for dynamic fusion to calculate the dynamic voltage difference of virtual and real fusion ( ), the calculation formula is: in, is the virtual-real fusion proportional factor, and its value is determined according to the theoretical reference voltage ( ) and the clinically measured reference voltage sequence ( ) to adaptively adjust the peak-to-peak difference between them; Step S5, four-dimensional inversion and imaging: Based on the dynamic voltage difference ( ), by solving an optimization problem to reconstruct a four-dimensional conductivity change image reflecting the dynamic changes of lung ventilation ( ).

[0010] Preferably, the steps of constructing the personalized digital twin specifically include: Data input: obtaining chest CT image or MRI image data of the target object; Geometric modeling: using medical image processing tools to segment the image data, extract the organ contours of the lungs, heart, axial skeleton, main bronchi, and esophagus, and construct a three-dimensional geometric model, where the axial skeleton includes the sternum, ribs, and thoracic vertebrae; Electrical characteristic assignment: assigning electrical characteristic parameters at a preset EIT operating frequency to each organ in the three-dimensional geometric model; Sensor integration: An EIT electrode array model including a plurality of electrodes is integrated at a corresponding position on the body surface of the three-dimensional geometric model.

[0011] Preferably, the electrical characteristic assignment step further includes: A dynamic movement model of the organ during the respiratory cycle is established, and time-varying electrical characteristic parameters such as the electrical conductivity of the lung tissue are dynamically adjusted according to the inhalation phase and the exhalation phase during the respiratory cycle.

[0012] Preferably, the clinically measured reference voltage sequence ( ) is a sequence of body surface voltage signals collected at the end of exhalation in each respiratory cycle.

[0013] Preferably, the scaling factor The adaptive adjustment logic includes: Calculate the theoretical reference voltage ( ) and the clinically measured reference voltage sequence ( ) Peak-to-peak difference within one or more respiratory cycles ; When the peak-to-peak difference When the threshold is greater than the preset pathological state, the The value of the theoretical reference voltage is enhanced ( ) is the modified weight, at this time The value range of is 0.8 to 1.0; When the peak-to-peak difference When it is not greater than the preset pathological state threshold, the value of k is reduced to give priority to the clinical measured data. At this time, the value range of k is 0.3 to 0.5.

[0014] Preferably, in the four-dimensional inversion and imaging step, the mathematical expression of the optimization problem is: in, for The system's three-dimensional sensitive field matrix, is the regularization parameter, is a priori constraint term used to ensure the stability and smoothness of the solution.

[0015] A four-dimensional EIT respiratory monitoring system based on digital twin assistance, including: A model construction module is used to construct an individualized digital twin model containing the three-dimensional geometric structure and electrical characteristic parameters of the main organs in the chest cavity of the target subject, including at least the lungs, heart, axial skeleton, main bronchi, and esophagus, based on the chest medical imaging data of the target subject; The theoretical reference generation module is used to simulate the electromagnetic field distribution of the target object in the end-expiratory hypoventilation steady state on the individualized digital twin model, and solve to obtain the standardized theoretical reference voltage ( ); The data acquisition module is used to collect the real-time voltage signal of the target object during the respiratory cycle through the electrode array ( ) and clinically measured reference voltage series ( ); Fusion calculation module, used to convert the theoretical reference voltage ( ), the clinically measured reference voltage sequence ( ) and the real-time voltage signal ( ) for dynamic fusion to calculate the dynamic voltage difference of virtual and real fusion ( ), the calculation formula is ,in A proportional factor that is adaptively adjusted according to the peak-to-peak difference between the theoretical reference voltage and the clinically measured reference voltage sequence; imaging module for use based on the dynamic voltage difference ( ), by solving an optimization problem to reconstruct a four-dimensional conductivity change image reflecting the dynamic changes of lung ventilation ( ).

[0016] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention uses a digital twin model built based on the patient's CT / MRI data to accurately match the patient's chest geometry and organ distribution, breaking through the limitation of traditional EIT's insensitivity to anatomical differences.

[0017] 2. The present invention uses adaptive adjustment of the proportional factor , dynamically integrating the stable theoretical benchmark with the real-time clinical benchmark, effectively compensating for the measured benchmark deviation caused by respiratory instability or pathological interference, and significantly improving the imaging robustness.

[0018] 3. Based on the individualized conductance a priori information provided by digital twins, the present invention has for the first time realized the semi-absolute quantitative assessment of pulmonary ventilation function, such as the calculation of regional ventilation percentage, breaking through the limitation of traditional methods that only rely on relative changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for describing the embodiments.

[0020] Figure 1 Schematic diagram of the process of establishing the digital twin geometric model in the present invention; Figure 2 Schematic diagram of the overall process of the four-dimensional EIT respiratory monitoring method based on digital twin assistance in the present invention; Figure 3 This is a detailed principle analysis diagram of the virtual-real fusion calculation method in the present invention, in which the 'virtual space' on the left shows the simulated normalized global impedance waveform and the stable theoretical reference voltage ( ); The 'physical space' on the right shows the normalized global impedance waveform and real-time voltage signal measured in clinical practice ( ) and clinically measured reference voltage sequence ( ); the 'virtual-real fusion' arrow in the middle indicates the process of fusion calculation of the three; Figure 4 This is a schematic diagram of the four-dimensional EIT respiratory monitoring results assisted by the digital twin in the present invention, showing the process from CT images to the digital twin system, and finally generating a series of reconstructed conductivity change distribution maps at different breathing moments. DETAILED DESCRIPTION

[0021] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0022] This embodiment specifically monitors the respiratory function of patients with chronic obstructive pulmonary disease (COPD). This embodiment is intended to illustrate the specific application of the present invention in a clinical scenario.

[0023] Step S1: Construction of personalized digital twin See also Figure 1 As shown, the first step of the present invention is the construction of an individualized digital twin. The process begins with obtaining the patient's chest CT image data, as shown in Figure 1As shown in the upper left corner; then, the CT image is segmented using medical image processing software to accurately extract the contours of key organs such as the lungs, heart, axial skeleton, main bronchi and esophagus. The axial skeleton includes the sternum, ribs and thoracic vertebrae; at the same time, the information of the double-layer 32-electrode EIT sensor array model is integrated; finally, all the segmented organ models are integrated with the sensor model in three-dimensional space to complete the establishment of a high-fidelity geometric model, as shown in the figure below. Figure 1 As shown in the lower right corner, the model accurately reproduces the patient's individual chest anatomy.

[0024] Based on the geometric model, electrical characteristic parameters are assigned to each organ in the model at a specific operating frequency, such as 125 kHz. The key parameters can be set as follows: the conductivity of lung tissue in the inflated state at the end of inspiration is 0.109 S / m; the conductivity of lung tissue in the hypoventilated state at the end of expiration is 0.275 S / m.

[0025] In order to accurately simulate the dynamic deformation of the lungs during breathing, the present invention constructs a biomechanical model based on multi-physics field coupling, which specifically includes the following mechanical models and electrical-mechanical coupling models: (1) Mechanical model During normal breathing, the lungs reach their maximum inflation state at the end of inspiration, when the alveoli are fully expanded, the lung tissue tension is high, and the chest cavity volume is high. With the start of exhalation, the diaphragm gradually rises, the intrathoracic pressure rises, the lung tissue elastically shrinks, and the alveoli gradually collapse until the end of exhalation, when the lung volume is reduced to the minimum. During the entire process from the end of inspiration to the end of exhalation, the lung tissue undergoes significant three-dimensional deformation, accompanied by regional ventilation differences and changes in tissue density, which directly affect its conductivity distribution.

[0026] In order to accurately simulate the dynamic deformation process of the lungs during a complete respiratory cycle, the present invention constructs a biomechanical model based on finite element analysis and uses solid mechanics methods to describe the mechanical response of lung tissue under periodic respiratory drive.

[0027] In the modeling, we assume that the lung tissue obeys the isotropic linear elastic material model, and its stress-strain relationship satisfies Hooke's Law: in is the Cauchy stress tensor; is the linear strain tensor; , is the Lame parameter, which is calculated from Young's modulus E and Poisson's ratio v. The calculation formula is: Considering the large deformation characteristics of lung tissue during breathing, geometric nonlinear analysis is enabled in the model, using a more general deformation description variable - the deformation gradient tensor: And define the Green-Lagrange strain tensor: In this framework, stress can be expressed using the second Piola-Kirchhoff stress tensor Express: In terms of mechanical equilibrium, the momentum conservation equation under quasi-static conditions is: In nonlinear configuration, it is converted into the equilibrium equation under the reference configuration: Combining the anatomical structure and physiological characteristics of the lungs, the driving mechanism is set up with the periodic active contraction of the diaphragm and the dynamic changes in intrathoracic pressure as the dominant factors, simulating the expansion and deformation of lung tissue during inhalation and the passive retraction during exhalation.

[0028] Specifically, during inspiration, the lung base is adjacent to the diaphragm region (denoted as ) Apply preset boundary pressure loads along the xyz directions to simulate the mechanical compression of the lungs caused by the upward movement of the diaphragm: At the same time, on the surface of the lungs (denoted as ) surface is subjected to gradually increasing negative pressure load conditions , simulating the stretching effect caused by the reduction of intrathoracic pressure: This combined load induces nonlinear deformation of the lung tissue, resulting in an increase in the overall volume, which approximately reflects the alveolar expansion process under physiological conditions. The volume of the lung changes with time: During the exhalation phase, the model applies reverse mechanical boundary conditions to reproduce the deformation process of the lung from the inflated state to the end of exhalation. Specifically, the upward displacement load applied by the diaphragm region is gradually reduced until it is eliminated ( →0), and the external negative pressure load is also released synchronously ( → 0), simulating the process of intrathoracic pressure recovery and diaphragm relaxation and upward movement.

[0029] During this phase, the lung tissue spontaneously retracts under the action of the elastic potential energy accumulated after the previous expansion, showing obvious nonlinear elastic recovery behavior. Its dynamic performance is as follows: During this process, the alveolar volume gradually decreases, tissue tension decreases, and the overall volume decreases, which approximately reflects the passive rebound mechanism of lung tissue during real exhalation.

[0030] (2) Electrical and mechanical coupling model In terms of material property settings, lung tissue is considered a flexible, biomechanically responsive elastic body, exhibiting a certain degree of compressibility. To accurately reflect its actual mechanical properties, this study set the Poisson's ratio of lung tissue to 0.1. This indicates that lung tissue exhibits minimal lateral deformation during compression or extension, exhibiting significant volumetric compression, and better reflects changes in lung density and geometric changes caused by gas exchange during respiration.

[0031] During the entire simulation process, a multi-moment transient analysis method is used to dynamically model the complete respiratory cycle.

[0032] At each time point, the model outputs the three-dimensional displacement field, volume change rate, and stress distribution information of the lung tissue, reflecting the continuous deformation characteristics and compressible response of the lungs from the end of inspiration to the end of expiration. The calculation results of this mechanical model can intuitively obtain the dynamic geometric change characteristics of the lungs during the breathing process. This deformation information not only reflects the actual movement patterns of the lungs, but also provides important input parameters for the EIT simulation module.

[0033] Specifically, based on the changes in the local volume of lung tissue at each time point, the changing trend of its conductivity over time can be further deduced, thereby realizing the dynamic update and regulation of electrical parameters in EIT images.

[0034] Lung tissue deforms under the influence of respiration, resulting in local volume changes and readjustment of gas distribution. These mechanical deformations directly lead to dynamic distribution changes in lung conductivity in space and time, thereby affecting the distribution of the electric field and the measurement results.

[0035] Therefore, in electrical impedance tomography (EIT) of the lung, in order to accurately describe the dynamic changes of the electrical properties of the lung during breathing, it is necessary to construct a coupled model of electrical and mechanical properties.

[0036] The mechanical deformation of the lungs during breathing can be expressed as a displacement field The corresponding local volume strain is defined as: The deformation of the lungs satisfies the dynamic equilibrium equation: in, is the stress tensor, For external driving force, is the tissue density; by solving the above equation, the deformation state of the lung tissue at different breathing moments can be obtained.

[0037] The electrical conductivity of lung tissue can be defined as a function of deformation, meaning that the conductivity adjusts dynamically with changes in lung volume: in, is the static conductivity at the end of exhalation in the reference state, function Describes the sensitivity of conductivity to deformation; the commonly used linear equation is approximated as: The parameters >0 indicates the degree to which the conductivity decreases with volume expansion.

[0038] The electrical field is solved by satisfying the steady-state current continuity equation: in, represents the electric field potential distribution.

[0039] This coupling mechanism ensures that the electrical response is driven by the actual deformation of the lungs, significantly improving the physical consistency and predictive ability of the simulation model for the real breathing process.

[0040] Steps S2 to S4: Virtual-reality fusion monitoring based on digital twins See also Figure 2 ,The core monitoring process of the present invention integrates the advantages of ,physical space and virtual space.

[0041] See also Figure 3 ,First, in step S2, theoretical reference voltage generation, we use the digital twin constructed in step S1, ,to perform multi-physics field coupling simulation in virtual space.,Through this simulation, we can calculate the sensor output voltage,signal generated by virtual EIT excitation in the end-expiratory steady state; Figure 3 As shown in the 'virtual space' on the left, the voltage signal obtained by this simulation is a stable and standardized theoretical reference voltage. .

[0042] Secondly, in step S3 clinical data collection, we use EIT equipment in physical space at the patient's bedside to continuously monitor the patient's breathing through a double-layer 32-electrode array. Two data series are collected in real time: one is the real-time voltage signal of each sampling point during the respiratory cycle; the other is the real-time voltage signal of each sampling point during the respiratory cycle. , and the second is the clinically measured reference voltage sequence at the end of exhalation in each respiratory cycle ;like Figure 3 As shown in the 'physical space' on the right, the measured global impedance waveform may experience baseline drift due to unstable patient breathing.

[0043] Then, in the key step S4 virtual-real fusion dynamic voltage difference calculation, we perform Figure 3 The 'virtual-real fusion' calculation shown in the center. The processing unit performs the following operations: Differential Computing: Real-Time Computing Theoretical Benchmarks and clinical benchmarks In this example, due to the unstable breathing of COPD patients, δ was detected to be 15%, which exceeded the preset pathological state threshold of 10%.

[0044] Adaptive adjustment of k value: Based on the judgment result of δ>10%, the virtual-real fusion scale factor k is dynamically adjusted to 0.8 to enhance the theoretical benchmark correction effect.

[0045] Fusion computing: Applying core formulas , calculate the corrected dynamic voltage difference , the fusion process uses To calibrate drift, thus obtaining a corrected dynamic voltage difference that retains the true dynamic information and eliminates the baseline drift. , laying a solid foundation for subsequent high-precision imaging.

[0046] Step S5: 4D conductivity image reconstruction and analysis The calculated As input, it is substituted into the reconstruction algorithm, such as Figure 2 As shown in FIG, the reconstruction process needs to be combined with the pre-calculated three-dimensional EIT sensitivity field, that is, the sensitivity field matrix, and finally realize the three-dimensional image reconstruction by solving the inverse problem.

[0047] The final imaging result is Figure 4 As shown in the figure, the figure shows a series of three-dimensional images arranged in time sequence, corresponding to key moments in the respiratory cycle such as the end of exhalation, the midpoint of inspiration, and the end of inspiration, which strongly verifies the effective suppression of baseline drift and the visualization ability of the dynamic ventilation process of this method.

[0048] By post-processing the reconstructed four-dimensional images, specifically, the four-dimensional images, which are a time series of three-dimensional images, can quantitatively analyze that the patient's left lung ventilation accounts for 62.3% of the total ventilation, while the right lung accounts for only 37.7%, showing obvious ventilation heterogeneity. This quantitative result can provide an accurate basis for clinicians to formulate personalized postural treatment or ventilator parameter settings.

[0049] It can be seen from this example that the method of the present invention effectively overcomes the shortcomings of traditional EIT and provides more accurate, more robust and more clinically valuable quantitative monitoring results.

[0050] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A four-dimensional EIT respiratory monitoring method based on digital twin assistance, characterized in that: The following steps are involved: Step S1, constructing a personalized digital twin: based on the chest medical imaging data of the target subject, constructing a personalized digital twin model including the three-dimensional geometric structure and electrical characteristic parameters of the main organs in the chest cavity of the target subject; Step S2, generating theoretical reference voltage: simulating the electromagnetic field distribution of the target object in the end-expiratory hypoventilation steady state on the individualized digital twin model, and solving to obtain the standardized theoretical reference voltage ( ); Step S3, clinical data acquisition: using an electrode array arranged on the body surface of the target object, real-time acquisition of the body surface voltage signal of the target object during the respiratory cycle, the body surface voltage signal includes a real-time voltage signal ( ) and the clinically measured reference voltage sequence that varies with the respiratory cycle ( ); Step S4, virtual-real fusion calculation: the theoretical reference voltage ( ), the clinically measured reference voltage sequence ( ) and the real-time voltage signal ( ) for dynamic fusion to calculate the dynamic voltage difference of virtual and real fusion ( ), the calculation formula is: in, is the virtual-real fusion proportional factor, and its value is determined according to the theoretical reference voltage ( ) and the clinically measured reference voltage sequence ( ) to adaptively adjust the peak-to-peak difference between them; Step S5, four-dimensional inversion and imaging: Based on the dynamic voltage difference ( ), by solving an optimization problem to reconstruct a four-dimensional conductivity change image reflecting the dynamic changes of lung ventilation ( ).

2. A four-dimensional EIT respiratory monitoring method based on digital twin assistance according to claim 1, characterized in that: The steps of constructing the personalized digital twin specifically include: Data input: obtaining chest CT image or MRI image data of the target object; Geometric modeling: using medical image processing tools to segment the image data, extract the organ contours of the lungs, heart, axial skeleton, main bronchi, and esophagus, and construct a three-dimensional geometric model, where the axial skeleton includes the sternum, ribs, and thoracic vertebrae; Electrical characteristic assignment: assigning electrical characteristic parameters at a preset EIT operating frequency to each organ in the three-dimensional geometric model; Sensor integration: An EIT electrode array model including a plurality of electrodes is integrated at corresponding positions on the body surface of the three-dimensional geometric model.

3. A four-dimensional EIT respiratory monitoring method based on digital twin assistance according to claim 2, characterized in that: The electrical characteristic assignment step further includes: A dynamic movement model of the organ during the respiratory cycle is established, and time-varying electrical characteristic parameters such as the electrical conductivity of the lung tissue are dynamically adjusted according to the inhalation phase and the exhalation phase during the respiratory cycle.

4. A four-dimensional EIT respiratory monitoring method based on digital twin assistance according to claim 1, characterized in that: The clinically measured reference voltage sequence ( ) is a sequence of body surface voltage signals collected at the end of exhalation in each respiratory cycle.

5. A four-dimensional EIT respiratory monitoring method based on digital twin assistance according to claim 1, characterized in that: The scaling factor The adaptive adjustment logic includes: Calculate the theoretical reference voltage ( ) and the clinically measured reference voltage sequence ( ) Peak-to-peak difference within one or more respiratory cycles ; When the peak-to-peak difference When the threshold is greater than the preset pathological state, the The value of the theoretical reference voltage is enhanced ( ) is the modified weight, at this time The value range of is 0.8 to 1.0; When the peak-to-peak difference When it is not greater than the preset pathological state threshold, the value of k is reduced to give priority to the clinical measured data. At this time, the value range of k is 0.3 to 0.

5.

6. A four-dimensional EIT respiratory monitoring method based on digital twin assistance according to claim 1, characterized in that: In the four-dimensional inversion and imaging step, the mathematical expression of the optimization problem is: in, for The system's three-dimensional sensitive field matrix, is the regularization parameter, is a priori constraint term used to ensure the stability and smoothness of the solution.

7. A four-dimensional EIT respiratory monitoring system based on digital twin assistance, characterized in that: include: A model construction module is used to construct an individualized digital twin model containing the three-dimensional geometric structure and electrical characteristic parameters of the main organs in the chest cavity of the target subject, including at least the lungs, heart, axial skeleton, main bronchi, and esophagus, based on the chest medical imaging data of the target subject; The theoretical reference generation module is used to simulate the electromagnetic field distribution of the target object in the end-expiratory hypoventilation steady state on the individualized digital twin model, and solve to obtain the standardized theoretical reference voltage ( ); The data acquisition module is used to collect the real-time voltage signal of the target object during the respiratory cycle through the electrode array ( ) and clinically measured reference voltage series ( ); Fusion calculation module, used to convert the theoretical reference voltage ( ), the clinically measured reference voltage sequence ( ) and the real-time voltage signal ( ) for dynamic fusion to calculate the dynamic voltage difference of virtual and real fusion ( ), the calculation formula is ,in A proportional factor that is adaptively adjusted according to the peak-to-peak difference between the theoretical reference voltage and the clinically measured reference voltage sequence; imaging module for use based on the dynamic voltage difference ( ), by solving an optimization problem to reconstruct a four-dimensional conductivity change image reflecting the dynamic changes of lung ventilation ( ).

Images