170 results about "Electrical impedance imaging" patented technology

The invention relates to a lung region electrical impedance tomography (EIT) image reconstruction method based on a graph structure, and establishes an EIT depth imaging model in which double branch channels of a high-frequency channel graph attention network and a low-frequency channel graph attention network are parallel, and the model is named as HLGAT. The method comprises the following steps: injecting current excitation into a finite element simulation model of a lung region to obtain boundary voltage data required by EIT image reconstruction, and performing non-uniform mesh generation on the lung region needing image reconstruction to obtain nodes required by a graph neural network and an adjacency relationship between the nodes, so as to obtain a lung region model; storing the data in a graph structure form suitable for network input; the HLGAT aggregates the low-frequency characteristic information and the high-frequency characteristic information through the two channels, node output characteristic information of the two channels is fused in a learnable mode, a new adjacency matrix is reconstructed according to the node characteristic information output by the network, then a new Laplace matrix is constructed, more accurate conductivity distribution can be obtained, and the accuracy of the conductivity distribution is improved. And the physical process of electrical impedance imaging can be described more accurately, so that the accuracy of model imaging is improved.

The invention relates to an electrical impedance detection method and device, an electronic device and a storage medium, which are applied to the field of electrical impedance imaging, and the electrical impedance detection method comprises the following steps: obtaining an electrode signal of a target electrode in a measurement area; a plurality of preset electrodes are attached to the measurement area; the target electrode comprises any one of a plurality of preset electrodes; the electrode signal carries excitation electrode data and measurement electrode data generated by the target electrode; determining a fluctuation value of the target electrode according to the excitation electrode data and the measurement electrode data; when the fluctuation value is within a preset fluctuation threshold range, based on a preset electrode measurement method, electrode contact impedance of the measurement area is obtained; and generating an electrode adjustment result based on the electrode contact impedance and sending the electrode adjustment result to the client. According to the method and the device, the problem that the efficiency of electrical impedance measurement is relatively low due to the fact that whether the electrode falls off or is in poor contact cannot be quickly judged during bioelectrical impedance imaging is solved.

The invention relates to a visual airway clearance device with an intelligent airway internal and external oscillation control function. The visual airway clearance device comprises an electrical impedance imaging device, a controller, an airway internal oscillation device and an airway external oscillation device. The electrical impedance imaging device is used for evaluating the lung ventilation function condition of a patient and transmitting measured lung ventilation function index parameters of the patient to the controller; the controller receives the pulmonary ventilation function index parameters of the electrical impedance imaging device, processes the pulmonary ventilation function index parameters and outputs a control signal; and after receiving the control signal, the air passage internal and external oscillation devices adjust the operation modes and parameters of the air passage internal and external oscillation devices in real time. The system has the advantages that a four-dimensional integrated structure of electrical impedance imaging visual evaluation, intelligent mode selection, double-oscillation cooperation and closed-loop feedback is created for the first time, the problem that the traditional technology cannot dynamically adapt to the heterogeneity of patients is solved, and personalized airway clearance modes and optimal adjustment parameters are provided for different patients; and the effect of removing airway deposited secretions is obvious.

The invention discloses a head space positioning method, device and system based on electrical impedance tomography, and the method comprises the steps: constructing a corresponding three-dimensional model according to the basic parameters of a flexible electrode cap, and carrying out the finite element meshing, and obtaining a three-dimensional mesh model; performing electric field distribution calculation on sampling points of the three-dimensional grid model according to a preset calculation rule to obtain corresponding touch electrode response information; generating a sensitive field matrix corresponding to the sampling points and the electrode pairs in the flexible electrode cap according to the touch electrode response information; performing projection matching according to the initial voltage data of the electrode pair and the sensitive field matrix to obtain projection matching information; and performing model training according to the projection matching information and the tensile deformation data of the flexible electrode cap to obtain a voltage feature-space coordinate mapping relation, and analyzing the induced voltage data of the electrode pair to obtain corresponding target coordinate information. According to the method, the voltage change of the flexible electrode cap is obtained and analyzed to obtain the coordinate information, and the positioning accuracy and stability are improved.

The invention discloses a muscle imaging method based on a conditional diffusion model and electrical impedance, a medium and equipment, and belongs to the technical field of image processing. The method comprises the following steps: for a measured target, acquiring physical electrical impedance data by using electrical impedance equipment to obtain a boundary electrical impedance value; and inputting the boundary electrical impedance value into an image reconstruction model to obtain an electrical impedance imaging result. Wherein the image reconstruction model is obtained according to the following steps: constructing a data set which reflects a corresponding relation between electrical impedance data and a standard image; gradually adding noise to the standard image through conditional diffusion to obtain a noise image, and processing the electrical impedance data into an edge electrical impedance characteristic mapping graph; inputting the noise image and the edge electrical impedance characteristic mapping graph into a denoising network for training so as to learn a mapping relation between the boundary electrical impedance data and a real image; and taking the trained denoising network as the image reconstruction model. According to the invention, the image reconstruction effect and generalization ability are improved.

The invention relates to a petroleum polluted soil polycyclic aromatic hydrocarbon migration path simulation experiment system, which comprises a main reaction cabin, a mechanical arm collaborative operation module, a multi-mode sensing module, a whole natural environment regulation and control module and an edge intelligent decision-making platform, an annular magnetic suspension track is arranged at the top of the main reaction cabin, and a soil sample chamber is arranged at the bottom of the main reaction cabin; the multi-modal sensing module comprises an EIT (electrical impedance tomography) module, an LIBS (laser-induced breakdown spectroscopy) module and a terahertz time-domain spectroscopy module and is used for measuring global conductivity distribution of soil in a soil sample chamber, inverting the porosity of the soil sample and a pollutant concentration field in pore water, analyzing the concentration of carbon, hydrogen and oxygen elements of pollutants and specifically detecting polycyclic aromatic hydrocarbon molecules; the edge intelligent decision-making platform interacts with the multi-mode sensing module, the full-natural-environment regulation and control module and the mechanical arm collaborative operation module to actively adjust system parameters, and repair intervention is carried out on soil body degradation. And automatic preparation of the polluted soil can be realized, and migration monitoring under different practical engineering application working conditions can be realized.

The invention relates to a functional residual gas amount measuring method and device, equipment and a storage medium. The method comprises the following steps: recording lung electrical impedance change values of a user under a plurality of tidal volumes based on an electrical impedance imaging device to obtain a plurality of tidal volume-lung electrical impedance change value pairs; generating a lung electrical impedance change curve based on the plurality of tidal volume-lung electrical impedance change value pairs, and performing fitting processing on the lung electrical impedance change curve to obtain a fitted lung electrical impedance change curve; acquiring a real-time lung electrical impedance distribution value, and calculating a functional residual gas amount corresponding to the real-time lung electrical impedance distribution value based on the fitted lung electrical impedance change curve; compared with the prior art, the technical scheme of the invention can improve the efficiency and applicability of functional residual gas measurement, so that the method is more suitable for clinical and practical application scenes.

The invention discloses a reverse osmosis membrane concentration polarization layer thickness prediction method and device based on electrical impedance tomography, and relates to the technical field of membrane process nondestructive monitoring, and the method comprises the following steps: constructing a simulation model based on an electrode array membrane filtration sensor; virtual media with different conductivities are arranged on the surface of the membrane, a simulation conductivity image is reconstructed through a conjugate gradient least square algorithm and a sensitivity matrix, and a neural network is improved through known conductivity training; and reconstructing an actually measured conductivity image by an actually measured boundary voltage data set, predicting a membrane surface conductivity estimated value by using the trained improved neural network, and performing concentration polarization layer thickness mapping. A conductivity image with a conductivity label is generated through numerical simulation, so that the problem that the thickness of the concentration polarization layer is difficult to calibrate is solved, then a neural network is improved through training so that the truth value of the conductivity can be predicted according to the conductivity image, and interpretable mapping of the thickness of the concentration polarization layer is carried out in combination with a membrane mass transfer theory. The thickness of the concentration polarization layer can be subjected to online lossless quantitative detection.

The invention relates to the technical field of intelligent nursing, in particular to an electrical impedance tomography-based pressure sore risk perception and prevention control system, which comprises an EIT signal acquisition module, an impedance trend grading module, a risk area judgment module, a bed body intervention control module and an intervention feedback regulation module. According to the invention, through an electrical impedance imaging principle, fine distinguishing of body surface and superficial tissue physiological states of a patient is realized, multi-region impedance signals are continuously collected and dynamically integrated, local tissue perfusion changes and abnormal stress trends are accurately mapped, high-risk regions are automatically identified and classified, bed body action intervention is triggered in real time, and an intervention effect is dynamically tracked; according to the method, intervention parameters are cooperatively adjusted, the response logic and the intervention rhythm of each region are gradually improved, intelligent risk judgment and closed-loop adaptive intervention are completed, individuation, initialization and process data traceability in a nursing scene are promoted, and adaptive response aiming at complex illness conditions and variable nursing requirements is supported.

The invention relates to the field of intelligent medical treatment, in particular to an electrical impedance imaging method and device based on mixed excitation and a program product. Comprising the steps that an initial current vector and an initial boundary voltage vector of mixed excitation are obtained, the mixed excitation comprises L kinds of excitation, and L is a natural number larger than 1; performing weighted fusion on the L excitation initial current vectors to obtain a mixed excitation current vector, and performing weighted fusion on the L excitation initial boundary voltages to obtain a mixed excitation voltage; performing electrical impedance imaging optimization function calculation based on the mixed excitation current vector and the mixed excitation voltage to obtain conductivity change; the optimization function is used for carrying out regularization calculation on regional potential distribution and conductivity variation based on the mixed excitation current vector and the mixed excitation voltage; an electrical impedance distribution image is generated based on the conductivity change. According to the invention, the resolution of EIT imaging is improved, and the method has good clinical value.

The invention discloses a motion posture recognition detection method based on transfer learning, belongs to the field of biomedical signal processing and machine learning, and aims at improving the robustness of a model under the condition of electrode position change by constructing an adversarial training mechanism and aligning data distribution before and after electrode offset in a feature space. The problem of data distortion caused by electrode displacement in the electrical impedance tomography EIT technology is solved, and the accuracy of posture recognition is improved.

The invention discloses an electrical impedance tomography method, which integrates a physical model and deep learning to construct a deep learning framework with physical constraints so as to improve physical consistency and reconstruction precision. According to the method, a neural network based on an encoder-decoder structure is adopted, and measured boundary voltage is used as input to predict conductivity distribution of a target object; in order to improve the performance of the neural network, a physical Jacobian matrix is introduced, and the sensitivity of boundary voltage to conductivity is described; and constructing a physical regularization loss function, comparing a physically calculated Jacobi matrix with a neural network predicted Jacobi matrix, and combining a final total loss function with data error loss and physical consistency loss. According to the method, data driving model training is guided through physical constraints, combination of physical information and deep learning is achieved, the precision of electrical impedance reconstruction and the generalization ability of the model are remarkably improved, and a new solution thought is provided for the fields of medicine, flexible electronics, environment monitoring and the like.

The invention discloses an electrical impedance cancer detection method based on frequency domain information enhancement. The method comprises the following steps: S1, acquiring an electrical impedance signal in the body of a patient through an electrical impedance imaging technology; s2, converting the signal into frequency domain representation by using discrete cosine transform, and performing frequency domain enhancement; s3, inputting the features subjected to frequency domain enhancement into the model, and processing the features subjected to frequency domain enhancement in combination with frequency domain information and a global dependency relationship to obtain a global feature matrix; and S4, inputting the global feature matrix into a classifier for cancer detection, and giving a corresponding detection result. According to the method, the time domain signals are subjected to frequency domain conversion, the features subjected to frequency domain enhancement are input into the network model, the global matrix features are obtained by combining the frequency domain information and the global dependency relationship, the global matrix features are input into the classifier for cancer detection, the robustness of the frequency domain data is improved, and the application effect of the electrical impedance signals in cancer detection is enhanced.

The invention discloses a diaphragm monitoring method and device based on electrical impedance change and a storage medium, and relates to the technical field of medical monitoring, and the method comprises the steps: obtaining an electrical impedance imaging signal collected around the chest of a subject in real time; generating an electrical impedance state image according to the electrical impedance imaging signal; generating a diaphragm interest region corresponding to the diaphragm part of the subject according to the electrical impedance state image; and shielding a lung respiration signal in the electrical impedance imaging signal by using the diaphragm interest region, and updating the electrical impedance state image to obtain an electrical impedance change image only displaying the diaphragm region. Through the content of the application, the diaphragm activity condition of the subject can be monitored in real time, so that the diaphragm function condition can be known, and accurate diagnosis and treatment can be realized.

The invention discloses an electrical impedance tomography method based on a multi-layer full-connection neural network. The method comprises the following steps: acquiring voltage measurement data of a to-be-measured area of a human thoracic cavity; performing triangle subdivision on the to-be-measured region by using a finite element method to obtain a finite element model; establishing a multi-layer full-connection neural network imaging model according to the finite element model, inputting the voltage measurement data into the neural network imaging model to obtain an initial conductivity distribution sequence of the to-be-measured region, and performing normalization to obtain a training set; training a neural network imaging model by using an early stop method according to the training set to obtain an optimal solution of a network connection weight; therefore, an optimized neural network imaging model is obtained, and a reconstructed image of impedance distribution of the to-be-measured region is obtained according to the optimized neural network imaging model. According to the method, the nonlinear mapping relation between the electrical impedance imaging input quantity and the electrical impedance imaging output quantity can be better represented, and the quality and the robustness of electrical impedance imaging are improved.

The invention provides a method for extracting motion characteristic data. The method comprises the following steps: acquiring kinematics data of a muscle to be detected; establishing a finite element model of the to-be-measured muscle according to the electrical impedance imaging differential voltage signal value of the to-be-measured muscle and the anatomical prior information of the section of the to-be-measured muscle; extracting respective time domain information and frequency domain information in the conductivity data of the plurality of signal nodes from the finite element model; correlation calculation is carried out based on the time domain information, the frequency domain information and the kinematics data, the motion participation degree of each signal node is obtained, and the motion participation degree is used for representing the muscle motion participation degree of each signal node; according to the motion participation degree of each signal node, the finite element model and the conductivity data, motion feature data are obtained, the motion feature data are used for representing spatial position distribution of multiple key muscle units in the to-be-detected muscle, and therefore the morphological features of the to-be-detected muscle can be determined based on the spatial position distribution.

The invention discloses an individual head tissue conductivity model construction method and system. According to the method, a non-uniform intracranial tissue conductivity value is obtained by adopting a conductivity model construction method based on the water content, and meanwhile, the conductivity of the scalp and the skull is measured through an improved electrical impedance imaging technology, so that the defects of the conductivity model construction method based on the water content during measurement of the conductivity of the scalp and the skull are overcome. According to the method, the difference of individual tissue conductivity is fully considered, the conductivity distribution of the head tissue of each patient can be measured independently, and a more accurate simulation modeling and optimization scheme can be provided in the fields of electrical stimulation of nerve regulation, tumor electric field treatment and the like.

The present invention discloses a method for detecting cancer by bioelectrical impedance based on deep learning, comprising the following steps: S1: obtaining the electrical signal data of benign and malignant samples of cancer tissues by using an electrical impedance imaging system and combining it with physiological data; S2: extracting global features of the electrical signals by using a matrix decomposition module; S3: taking the result of global feature extraction and the original electrical signal data together as new inputs and further extracting signal features by using data dependency; S4: integrating the extracted feature maps into a final classification result. The present invention uses an electrical impedance imaging system to obtain the electrical signal data of cancer tissues, performs global feature extraction through a matrix decomposition module, and at the same time takes the result of global feature extraction and the original electrical signal data together as new inputs, and further extracts signal features by using data dependency, which can improve the utilization rate of data and further enhance the accuracy and reliability of cancer detection.

A physical neural network high-resolution electrical impedance tomography optimization method belongs to the field of electrical impedance tomography and comprises the following steps: firstly, acquiring an initial image of a to-be-tested part of a human body by using an electrical impedance tomography (EIT) technology; secondly, performing preliminary denoising processing on the initial image through a three-dimensional block matching algorithm BM3D; and finally, on the basis of the non-local similarity in the prior information of the natural image, introducing the prior information of the CT image as a constraint condition, adding the prior information into the physical neural network PINNs, and continuously iterating and optimizing to realize high-resolution reconstruction of the image, thereby achieving the purpose of improving the image quality. The EIT imaging resolution is high, and the imaging result is more reliable.

The invention discloses a thoracic cavity three-dimensional electrical impedance tomography method and thoracic cavity three-dimensional electrical impedance tomography equipment. The method comprises the following steps: acquiring a three-dimensional point cloud of the appearance of a chest area of a testee to establish a three-dimensional chest model; carrying out equipment self-inspection and checking the bonding condition of the electrode; generating a determined excitation signal and injecting the excitation signal into the testee; acquiring a voltage signal of each electrode; separating EIT and ECG signals and filtering the EIT and ECG signals; according to a three-dimensional thoracic cavity model of the testee, performing positive problem calculation on the voltage signal to obtain the potential of each electrode of the three-dimensional thoracic cavity model; and performing three-dimensional reconstruction by adopting a single-step Gaussian Newton method to obtain a lung ventilation change electrical impedance imaging graph. According to the method, the three-dimensional thoracic cavity model of the testee is constructed, the positive problem solution is performed on the voltage signal, and the image reconstruction is further performed, so that the real-time high-precision three-dimensional dynamic imaging of the thoracic cavity of the testee can be completed, and the imaging accuracy is high.

The invention relates to an electrical impedance tomography data processing method and device and a storage medium. The impedance imaging data processing method comprises the following steps: acquiring a plurality of channel data of a plurality of electrodes in a measurement area; calculating a signal disturbance comprehensive index based on the channel data; under the condition that the data state is determined to be an abnormal state based on the signal disturbance comprehensive index, filtering and baseline correction are carried out on the channel data based on the signal disturbance comprehensive index to obtain optimized data; obtaining tissue transmission impedance based on the channel data; on the basis of tissue transmission impedance, respiratory impedance physiological characteristic indexes are obtained; determining a mutation frame in the optimization data based on the respiratory impedance physiological characteristic index; and obtaining valid data based on the mutation frame. According to the invention, the problem of low data validity in the electrical impedance imaging system is solved.

The present application relates to a kind of electrode belt and electrode assembly for electrical impedance imaging, it is related to biomedical electrical impedance imaging technical field.The electrode belt for electrical impedance imaging of the present application, including band body, the band body includes multiple electrode segments arranged along length, and elastic segment between adjacent electrode segments, the electrode segment can be used to set electrode assembly, the thickness of the electrode segment is greater than the thickness of the elastic segment, so that the elastic segment is more likely to occur elastic deformation compared with the electrode segment.Band body can be more conveniently fixed around the body of the object to be measured, and the fixing mode is simple, can make electrode and the surface of the object to be measured always keep good contact.

The invention discloses a bioelectrical impedance cancer detection method based on deep learning, and the method comprises the following steps: S1, obtaining electrical signal data of a benign sample and a malignant sample of a cancer tissue through an electrical impedance imaging system, and combining the electrical signal data with physiological data; s2, performing global feature extraction on the electric signal by using a matrix decomposition module; s3, taking a global feature extraction result and original electric signal data as new input, and further extracting signal features by using a data dependency relationship; and S4, mapping and integrating the extracted features into a final classification result. The electrical signal data of the cancer tissue is acquired by using the electrical impedance imaging system, global feature extraction is performed through the matrix decomposition module, the result of global feature extraction and the original electrical signal data are used as new input, and the signal features are further extracted by using the data dependency relationship, so that the utilization rate of the data can be improved; and the accuracy and reliability of cancer detection are further improved.

The utility model relates to the technical field of electrical impedance imaging, in particular to an electrical impedance imaging signal acquisition circuit and an acquisition device, the electrical impedance imaging signal acquisition circuit comprises an excitation signal generation circuit and a measurement signal detection circuit, a first voltage follower circuit is arranged in the measurement signal detection circuit in series, and a second voltage follower circuit is arranged in the measurement signal detection circuit. The first voltage following circuit can increase the input impedance of the measurement signal detection circuit, so that the measurement signal detection circuit is equivalent to an ideal voltmeter, and almost does not draw current from a motor of the excitation signal generation circuit, thereby enabling the voltage of a motor signal not to be remarkably changed, reducing the influence on the motor signal, and improving the reliability of the motor. And the authenticity and integrity of the measurement signal are ensured.

The invention discloses an extensible three-dimensional electrical impedance imaging electrode array device, and belongs to the technical field of biomedical measurement. The device comprises a two-dimensional electrode interface module which is connected with original two-dimensional equipment through a series input and expansion interface; the three-dimensional common electrode array comprises a plurality of groups of electrodes at different horizontal layers; the input end of the three-dimensional electrode control module is connected to the two-dimensional electrode interface module, and the output end of the three-dimensional electrode control module is connected to the three-dimensional common electrode array. The control module comprises an electrode array control connector which is connected in parallel and an isolation type analog switch unit of a multi-stage series analog switch structure. By sending a control signal to the control connector, all electrode channels on a certain layer in the three-dimensional electrode array are uniformly gated, and original two-dimensional measurement is mapped to a three-dimensional space. According to the invention, three-dimensional measurement can be realized without changing the original equipment, the number of vertical layers expanded by serial connection of interfaces is supported, the number of horizontal electrodes expanded by parallel connection is controlled, and high compatibility, high expansibility and excellent signal isolation capability are realized.

The application discloses an electrode ring and an electrical impedance imaging system for electrical impedance imaging. The electrode ring comprises a metal ring, a filler, an elastic fabric, a plurality of electrodes and a plurality of electrode lines, wherein the metal ring can adjust its diameter in a circular structure; the filler is arranged between the metal ring and the elastic fabric; the elastic fabric covers the metal ring, the filler and the plurality of electrodes; the plurality of electrode lines are wrapped between the filler and are led out as an electrode belt after being gathered together and are connected with an external electrical impedance imaging system; the plurality of electrodes are fixed on the surface of the elastic fabric in an equidistance manner, each electrode is connected by a corresponding electrode line, and the electrodes are not connected with each other. The electrode ring designed in the application can freely stretch and shrink in different limb diameter ranges, solves the problem of unfixed electrode spacing in the existing electrical impedance tomography electrode technology, and improves the wearing comfort and the stability of signal acquisition.

The application discloses a brain injury identification method and an identification system. The identification system identifies the injury of a patient according to the identification method. The identification method comprises the following steps: firstly, the electrical impedance tomography (EIT) of the brain of the patient is performed to obtain the EIT image of the brain of the patient; then, the region with abnormal resistivity distribution in the EIT image of the brain is taken as a reference for scanning of a near-infrared spectrometer, and a scanning path of the near-infrared spectrometer is planned; finally, the near-infrared spectrometer is scanned along the scanning path, and the lesion range and the lesion type are determined according to the obtained near-infrared spectral data. The electrodes need not be arranged on the whole head of the patient, and the automatic and rapid identification of the lesion range and the nature of the brain injury is realized.

The invention relates to the technical field of biology, in particular to a cell monitoring and electric field intervention device which can overcome technical challenges of an existing cell monitoring and electric field intervention device to a certain extent and solve the problems that a traditional impedance spectrum is insufficient in spatial resolution in cell culture monitoring, low in electric field intervention space setting flexibility and the like. The device comprises a main control unit, an electric field intervention unit, an electrical impedance scanning unit, a temperature monitoring and adjusting unit, an energy supply unit, a communication unit and a monitoring and intervention integrated electrode. Through multiplexing of the electrical impedance measuring electrode and the electric field intervention electrode, the three-dimensional electrical impedance imaging precision of cells can be improved, meanwhile, flexible electric field intervention mode setting is provided, and the device further integrates cell electrical impedance monitoring and electric field intervention functions and temperature monitoring and control functions; the growth state of cells under the intervention of the electric field and the temperature change of the device can be monitored and adjusted in real time, and the safety is ensured.

The invention relates to the technical field of focused ultrasound treatment, in particular to a real-time feedback phased array focused ultrasound treatment system, which comprises the following steps of: 1, fixing integrated equipment of ultrasonic transducers and EIT electrodes which are alternately and annularly arranged on a head, acquiring a three-dimensional image of the head by using imaging technologies such as CT or MRI and the like, and marking the spatial positions of the electrode, the ultrasonic array and the treatment target spot on the image. According to the invention, brain region real-time three-dimensional electrical impedance imaging is used as feedback, the excitation time sequence, intensity and phase of the ultrasonic array are adaptively adjusted, the influence of skull structure difference on ultrasonic focusing can be effectively overcome, the system calculates the phase shift of the ultrasonic array in real time, it is ensured that an ultrasonic beam is accurately focused at a treatment target, and the treatment accuracy is improved. The device is particularly suitable for a patient with a complex skull structure, the treatment accuracy is improved, it is ensured that ultrasonic energy accurately acts on a lesion area, and damage to surrounding healthy tissue is avoided.

The present application relates to the technical field of image processing, and more particularly to a method and system for evaluating electrical impedance state by fusing CT features. The method comprises the following steps: CT scanning of a subject to obtain CT scan data; generating an anatomical mask according to the CT scan data to obtain anatomical mask data; collecting three-dimensional impedance data by an electrical impedance scanning device; extracting multi-scale decomposition features according to the three-dimensional impedance data to obtain decomposition feature data; mapping an elastic harmonics network according to the decomposition feature data and the anatomical mask data to obtain a shape-calibrated impedance map data; extracting regional impedance features from the shape-calibrated impedance map data according to the anatomical mask data to obtain regional impedance feature data; and obtaining regional anomaly probability value data according to the regional impedance feature data. The present application fuses CT anatomical information and multi-scale electrical impedance features, realizes shape accurate alignment and regional anomaly recognition, and improves the spatial resolution of electrical impedance imaging.