Electrical Impedance Tomography Research Articles

Shape analysis of training data for neural networks in Electrical Impedance Tomography.

Electrical Impedance Tomography (EIT) is a cost-effective and fast way to visualize dielectric properties of the human body, through the injection of alternating currents and measurement of the resulting potential on the bodies surface. However, this comes at the cost of low resolution as EIT is a non-linear ill-posed inverse problem. Recently Deep Learning methods have gained the interest in this field, as they provide a way to mimic non-linear functions. Most of the approaches focus on the structure of the Artificial Neural Networks (ANNs), while only glancing over the used training data. However, the structure of the training data is of great importance, as it needs to be simulated. In this work, we analyze the effect of basic shapes to be included as targets in the training data set. We compared inclusions of ellipsoids, cubes and octahedra as training data for ANNs in terms of reconstruction quality. For that, we used the well-established GREIT figures of merit on laboratory tank measurements. We found that ellipsoids resulted in the best reconstruction quality of EIT images. This shows that the choice of simulation data has an impact on the ANN reconstruction quality.Clinical relevance- This work helps to improve time independent EIT reconstruction, which in turn allows for extraction of time independent features of e.g., the lung.

Electric impedance tomography enables portable and non-invasive approach to screen and monitor chronic kidney disease.

Chronic kidney disease (CKD) is an escalating global health concern, and non-invasive means for early CKD detection is eagerly awaited. Here, we explore the potential of using home-based frequency-difference electrical impedance tomography (fdEIT) to evaluate CKD based on bio-conductivity characteristics. We performed bio-conductivity measurement in vivo paired with standard estimated glomerular filtration rate (eGFR) measurements on a N=126 CKD patients by EIT and traditional blood and urine tests, respectively. We developed an EIT processing pipeline that extracts the kidney regions from EIT images. We further developed a regression model and a CKD classification scheme. Our results showed a significant correlation between EIT-features and eGFR, and the classification scheme shows sensitivity and specificity of 76.2% and 74.6% respectively considering stages 1 and 2 CKD versus stages 3, 4 and 5 CKD. These results suggest the feasibility of EIT to be used as a portable, self-administrated and home-based approach for CKD early diagnostic screening and longitudinal monitoring.Clinical Relevance-The results presented here demonstrates a cost-effective, home-based and self-administrative screening process on chronic kidney disease patients, thereby enhancing the quality and area of possible application of telemedicine. By achieving this, the process presented here can relieve the burden of public health system.

Mechanical insufflation-exsufflation to promote extubation success in critically ill adults on intensive care: protocol for a randomised controlled feasibility trial

BackgroundExtubation failure, defined as reintubation within 48 h, is associated with increased intensive care unit (ICU) length of stay and higher mortality risk. One cause of extubation failure is secretion retention, resulting from an inability to cough effectively. Mechanical insufflation-exsufflation (MI-E) simulates a cough aiding secretion clearance. However, MI-E is not routinely used in the ICU for invasively ventilated patients. This study aims to determine feasibility and acceptability of a randomised controlled trial (RCT) examining MI-E use to promote extubation success in intubated, ventilated adults.MethodsIt is a single-centre, feasibility RCT with semi-structured interviews, economic scoping, and exploratory physiology study.The feasibility RCT (n = 50) will compare standard care to a MI-E protocol including a minimum of two MI-E sessions via the endotracheal tube prior to extubation. Post-extubation, MI-E will be delivered via facemask or mouthpiece up to two times/day for 48 h. MI-E settings will be individualised. All patients will receive standard care (no MI-E) in relation to mechanical ventilation, weaning, rehabilitation, physiotherapy techniques such as positioning, manual airway clearance techniques, manual/ventilator hyperinflation, endotracheal suctioning, and nebulisation. Clinical data collection will occur before, on completion, and 5-min post-physiotherapy sessions (intervention/control arms). Resource use will be calculated for each 24-h period. Analyses will be descriptive and address feasibility outcomes including participant recruitment and attrition, proportion of MI-E treatment sessions completed, dataset completeness, and frequency of adverse events and acceptability.Semi-structured online interviews informed by the Theoretical Framework of Acceptability (TFA) with patients, clinicians, and family members will explore the acceptability of the MI-E intervention and study processes.Interview data will be analysed using reflexive thematic analysis based on TFA domains through first-level coding.The embedded physiology study will use electrical impedance tomography and lung ultrasound to explore lung recruitment and de-recruitment during MI-E in a subset of 5–10 patients.DiscussionThis study will examine feasibility and acceptability of a RCT protocol of MI-E to promote extubation success. Study findings will inform design modification and conduct of a future adequately powered trial. Furthermore, the study will contribute and advance the understanding of MI-E use in critically ill intubated adults.Trial registrationISRCTN 24603037; IRAS 303674

Towards intraoperative surgical margin assessment: Validation of an electrical impedance-based probe with ex vivo bovine tissue.

Radical prostatectomy (RP) is a common surgical therapy to treat prostate cancer. The procedure has a high positive surgical margin (PSM) rate ranging from 4-48%. Patients with PSMs have a higher rate of cancer recurrence and often undergo noxious adjuvant therapy. Intraoperative surgical margin assessment (SMA) with an electrical impedance-based probe can potentially identify PSMs in real-time. This would enable surgeons to make data-based decisions in the operating room to improve patient outcomes. This paper focuses on characterizing an impedance sensing SMA probe with specialized electrodes to improve speed and bandwidth while maintaining accuracy. 3D electrical impedance tomography (EIT) reconstructions were generated from ex vivo bovine tissue to characterize probe imaging and to determine an optimal applied pressure range (15 Pa to 38 Pa). Classification accuracy of adipose and muscle tissue was evaluated by comparing the experimental data set to simulated data based on a ground truth binary map of the tissue. Experimental AUCs ≥0.83 were maintained up to 50 kHz. The developed impedance sensing probe successfully classified between muscle and adipose tissue in an ex vivo bovine model. Future work includes improving performance of the SMA probe with custom hardware and collecting data from ex vivo and in vivo prostatic tissues.Clinical Relevance-This technology is expected to reduce the rate of PSMs in RP and decrease the use of post-surgical adjuvant therapies. It is also anticipated that intraoperative impedance measurements will increase efficacy of nerve sparing procedures and reduce complications such as incontinence and erectile dysfunction.

Deep learning based reconstruction enables high-resolution electrical impedance tomography for lung function assessment.

Recently, deep learning based methods have shown potential as alternative approaches for lung time difference electrical impedance tomography (tdEIT) reconstruction other than traditional regularized least square methods, that have inherent severe ill-posedness and low spatial resolution posing challenges for further interpretation. However, the validation of deep learning reconstruction quality is mainly focused on simulated data rather than in vivo human chest data, and on image quality rather than clinical indicator accuracy. In this study, a variational autoencoder is trained on high-resolution human chest simulations, and inference results on an EIT dataset collected from 22 healthy subjects performing various breathing paradigms are benchmarked with simultaneous spirometry measurements. The deep learning reconstructed global conductivity is significantly correlated with measured volume-time curves with correlation > 0.9. EIT lung function indicators from the reconstruction are also highly correlated with standard spirometry indicators with correlation > 0.75.Clinical Relevance- Our deep learning reconstruction method of lung tdEIT can predict lung volume and spirometry indicators while generating high-resolution EIT images, revealing potential of being a competitive approach in clinical settings.

Tumor location on electroporation therapies by means of multi-electrode structures and machine learning

Electroporation is a phenomenon produced in the cell membrane when it is exposed to high pulsed electric fields that increases its permeability. Among other application fields, this phenomenon can be exploited in a clinical environment for tumor ablation therapies. In this context to achieve optimum results, it is convenient to focus the treatment on the tumor tissue to minimize side effects. In this work, a pre-treatment tumor location method is developed, with the purpose of being able to precisely target the therapy. This is done by taking different impedance measurements with a multi-output electroporation generator in conjunction with a multi-electrode structure. Data are processed by means of a vector of independent artificial neural networks, trained and tested with simulation data, and validated with phantom gels. This algorithm proved to provide suitable accuracy in spite of the low electrode count compared to the number of electrodes of a standard electrical impedance tomography device.

The Influence of Breathing Exercises on Regional Ventilation in Healthy and Patients with Chronic Obstructive Pulmonary Disease

We hypothesized that the respiratory exercises have uniform effects on ventilation in healthy subjects but the effects varied in patients with chronic obstructive pulmonary disease (COPD). In this study, a total of 30 healthy volunteers and 9 patients with COPD were included. Data were recorded continuously during (1) diaphragmatic breathing; (2) pursed lip breathing with full inhalation; (3) pursed lip combining diaphragmatic breathing. The sequence of the three breathing exercises was randomized using machine generated random permutation. Spatial and temporal ventilation distributions were evaluated with electrical impedance tomography. Results showed that, tidal volume was significantly larger during various breathing exercises compared to quiet tidal breathing, in both healthy and COPD (p < 0.01). However, for other EIT-based parameters, statistical significances were only observed in healthy volunteers, not in patients. Diaphragmatic breathing alone might not be able to decrease functional residual capacity in COPD and the effect varied largely from patient to patient (6:3, decrease vs. increase). Ventilation distribution moved toward ventral regions in healthy during breathing exercises (p < 0.0001). Although this trend was observed in the COPD, the differences were not significant. Ventilation became more homogeneous when diaphragmatic breathing technique was implemented (p < 0.0001). Again, the improvements were not significant in COPD. Regional ventilation delay was relatively high in COPD and comparable in various breathing periods. In conclusions, the impact of pursed lip and diaphragmatic breathing varied in different patients with COPD. Breathing exercise may need to be individualized to maximize the training efficacy with help of EIT.

Setting the optimal positive end-expiratory pressure: a narrative review.

The primary goals of positive end-expiratory pressure (PEEP) are to restore functional residual capacity through recruitment and prevention of alveolar collapse. Through these mechanisms, PEEP improves arterial oxygenation and may reduce the risk of ventilator-induced lung injury (VILI). Because of the many potential negative effects associated with the use of PEEP, much research has concentrated on determining the optimal PEEP setting. Arterial oxygenation targets and pressure-volume loops have been utilized to set the optimal PEEP for decades. Several other techniques have been suggested, including the use of PEEP tables, compliance, driving pressure (DP), stress index (SI), transpulmonary pressures, imaging, and electrical impedance tomography. Each of these techniques has its own benefits and limitations and there is currently not one technique that is recommended above all others.

Bedside electrical impedance tomography (EIT) for early assessment of lung function in liver transplantation.

Early extubation after liver transplantation is recommended by the Enhanced Recovery After Surgery Society (ERAS guideline 2022) as the benefit to avoid prolonged mechanical ventilation and associated complications. The timing of extubation is challenged by early postoperative hypoxia due to both preoperative and surgical status. Timely identifying the cause of hypoxia, typically including hepatopulmonary syndrome (HPS), pulmonary edema, atelectasis, and effusion is critical to prevent delayed extubation, especially in cases with HPS. As a radiation-free bedside approach, electrical impedance tomography (EIT) facilitates real-time lung ventilation and perfusion(V/Q) monitoring, however, the applicability of EIT V/Q monitoring for the assessment of HPS and its value for the management of hypoxia after liver transplantation has never been reported. Under this context, we took the lead in monitoring V/Q with EIT for a 12-year-old girl diagnosed with HPS who suffered intra and post liver transplantation hypoxia at the bedside. Our image raises key points for physicians that: 1) V/Q measurement of intrapulmonary shunts with bedside EIT holds the potential to identify HPS, a novel application that requires clinical validation. 2) EIT helps timely identify hypoxia after liver transplantation to support early individualized respiratory interventions. To our knowledge, V/Q monitoring by EIT is increasingly used in respiratory therapy, especially for ARDS PEEP titration, pulmonary embolism detection and lung transplantation assessment. However, The potential of EIT in liver transplant patients has been rarely studied. Our images might provide a novel and convenient approach to diagnosis HPS at bedside and offer new clinical applications for EIT imaging techniques.

Physiological-induced conductive response evaluation in specific muscle compartments under hybrid of electrical muscle stimulation and voluntary resistance training by electrical impedance tomography.

Objective: The physiological-induced conductive response has been visualised for evaluation in specific muscle compartments under hybrid (hybridEMS) of electrical muscle stimulation (EMS) and voluntary resistance training (VRT) by electrical impedance tomography (EIT). Methods: In the experiments, tendency of conductivity distribution images σ over time was clearly detected for three specific muscle compartments, which are called AM 1 compartment composed of biceps brachii muscle, AM 2 compartment composed of triceps brachii muscle, and AM 3 compartment composed of brachialis muscle, under three training modalities. Results: From the experimental results, the tendency of physiological-induced conductive response are increased in all three training modalities with increasing training time. Correspondingly, the spatial-mean conductivity <σ>AM1,AM2,AM3 increased with the conductance value G and extracellular water ratio β of right arm by bio-impedance analysis (BIA) method. In addition, hybridEMS has the greatest effect on physiological-induced conductive response in AM 1, AM 2, and AM 3. Under hybridEMS, the spatial-mean conductivity increased from <σ pre > AM1 = 0.154 to <σ 23mins > AM1 = 0.810 in AM 1 muscle compartment (n = 8, p < 0.001); <σ pre > AM2 = 0.040 to <σ 23mins > AM2 = 0.254 in AM 2 muscle compartment (n = 8, p < 0.05); <σ pre > AM3 = 0.078 to <σ 23mins > AM3 = 0.497 in AM 3 muscle compartment (n = 8, p < 0.05). Conclusion: The paired-samples t-test results of <σ>AM1,AM2,AM3 under all three training modalities suggest hybridEMS has the most efficient elicitation on physiological induced conductive response compared to VRT and EMS. The effect of EMS on deep muscle compartment (AM 3) is slower compared to VRT and hybridEMS, with a significant difference after 15min of training.

A fully connected neural Network-based voltage compensation method for accurate reconstruction in brain electrical impedance tomography

Acute cerebral ischemia is commonly accompanied by cerebral edema. With brain electrical impedance tomography (EIT), it is possible to monitor conductivity variation during dehydration treatment of the cerebral edema. However, the scalp is also dehydrated when dehydrating brain tissue which exerts a large impact on boundary measurement. Consequently, reconstruction quality of cerebral edema is seriously affected. To reduce the influence of scalp dehydration, a voltage data compensation method based on a fully connected neural network (FCNN) is proposed in this work. With this method, the voltage measured when brain tissue and scalp are simultaneously dehydrated can be compensated. To evaluate the performance of the proposed method, reconstruction of simulated cerebral ischemia in a three-layer head model is conducted. Images reconstructed with the compensated voltage data are compared with the results when there is no compensation. Besides, quantitative comparison is performed. The results indicate that it is almost impossible to identify the simulated cerebral ischemia without voltage compensation. In contrast, cerebral ischemia can be much more accurately reconstructed when the measured voltage is compensated with the proposed method.

BRACETS: Bimodal repository of auscultation coupled with electrical impedance thoracic signals

Background and Objective: Respiratory diseases are among the most significant causes of morbidity and mortality worldwide, causing substantial strain on society and health systems. Over the last few decades, there has been increasing interest in the automatic analysis of respiratory sounds and electrical impedance tomography (EIT). Nevertheless, no publicly available databases with both respiratory sound and EIT data are available. Methods: In this work, we have assembled the first open-access bimodal database focusing on the differential diagnosis of respiratory diseases (BRACETS: Bimodal Repository of Auscultation Coupled with Electrical Impedance Thoracic Signals). It includes simultaneous recordings of single and multi-channel respiratory sounds and EIT. Furthermore, we have proposed several machine learning-based baseline systems for automatically classifying respiratory diseases in six distinct evaluation tasks using respiratory sound and EIT (A1, A2, A3, B1, B2, B3). These tasks included classifying respiratory diseases at sample and subject levels. The performance of the classification models was evaluated using a 5-fold cross-validation scheme (with subject isolation between folds). Results: The resulting database consists of 1097 respiratory sounds and 795 EIT recordings acquired from 78 adult subjects in two countries (Portugal and Greece). In the task of automatically classifying respiratory diseases, the baseline classification models have achieved the following average balanced accuracy: Task A1 - 77.9±13.1%; Task A2 - 51.6±9.7%; Task A3 - 38.6±13.1%; Task B1 - 90.0±22.4%; Task B2 - 61.4±11.8%; Task B3 - 50.8±10.6%. Conclusion: The creation of this database and its public release will aid the research community in developing automated methodologies to assess and monitor respiratory function, and it might serve as a benchmark in the field of digital medicine for managing respiratory diseases. Moreover, it could pave the way for creating multi-modal robust approaches for that same purpose.

A Positive Data Extraction Method for Electrical Impedance Tomography (EIT) Based on the Novel MSA-Net

The nonlinear and ill-posed Electrical Impedance Tomography (EIT) inverse problem leads to reconstructed images with distortion and low resolution. A positive data extraction method based on the deep learning is proposed in this study. This method realizes the accurate classification of the positive data and the general data in voltage measurements through a deep learning network called Multi Scale Attention Network (MSA-Net). The positive data is used for image reconstruction to improve the imaging quality. Multi scale feature extraction, residual learning and attention mechanism are introduced in the MSA-Net to improve classification accuracy. The Linear Back Projection (LBP) algorithm and the Tikhonov Regularization (TR) algorithm are used to verify the effectiveness of the proposed method. Both simulation and experiment are conducted around imaging of bubble flow. The simulation results indicate that there are fewer artifacts in the reconstructed images using the positive data of MSA-Net, and the shape and position of the bubbles can be better described. Moreover, the imaging quality of experimental samples can also be effectively improved. The existing test results preliminarily confirm that the distribution of the positive data and the general data in voltage measurements is related to the position of bubbles in the measurement domain.

Regional lung perfusion using different indicators in electrical impedance tomography.

Management of acute respiratory distress syndrome (ARDS) is classically guided by protecting the injured lung and mitigating damage from mechanical ventilation. Yet the natural history of ARDS is also dictated by disruption in lung perfusion. Unfortunately, diagnosis and treatment are hampered by the lack of bedside perfusion monitoring. Electrical impedance tomography is a portable imaging technique that can estimate regional lung perfusion in experimental settings from the kinetic analysis of a bolus of an indicator with high conductivity. Hypertonic sodium chloride has been the standard indicator. However, hypertonic sodium chloride is often inaccessible in the hospital, limiting practical adoption. We investigated whether regional lung perfusion measured using electrical impedance tomography is comparable between indicators. Using a swine lung injury model, we determined regional lung perfusion (% of total perfusion) in five pigs, comparing 12% sodium chloride to 8.4% sodium bicarbonate across stages of lung injury and experimental conditions (body position, positive end-expiratory pressure). Regional lung perfusion for four lung regions was determined from maximum slope analysis of the indicator-based impedance signal. Estimates of regional lung perfusion between indicators were compared in the lung overall and within four lung regions. Regional lung perfusion estimated with a sodium bicarbonate indicator agreed with a hypertonic sodium chloride indicator overall (mean bias 0%, limits of agreement -8.43%, 8.43%) and within lung quadrants. The difference in regional lung perfusion between indicators did not change across experimental conditions. Sodium bicarbonate may be a comparable indicator to estimate regional lung perfusion using electrical impedance tomography.NEW & NOTEWORTHY Electrical impedance tomography is an emerging tool to measure regional lung perfusion using kinetic analysis of a conductive indicator. Hypertonic sodium chloride is the standard agent used. We measured regional lung perfusion using another indicator, comparing hypertonic sodium chloride to sodium bicarbonate in an experimental swine lung injury model. We found strong agreement between the two indicators. Sodium bicarbonate may be a comparable indicator to measure regional lung perfusion with electrical impedance tomography.

The application of a wavelet filtering method in magneto-acousto-electrical tomography

Magneto-acousto-electrical tomography (MAET), which couples ultrasound imaging with electrical impedance tomography, is an electrical property imaging method which is expected to have a wide range of clinical applications, including the early detection of breast and liver cancers. Obviously, as a coupled imaging method, how to improve the signal-to-noise ratio (SNR) is a key issue in the imaging process. In this paper, a wavelet filtering method is introduced into MAET, which includes the filtering effect of the db6 wavelet, and its filtering effect at different decomposition levels. At the same time, based on the Lorentz reciprocity theorem, the wave equation satisfied by the detected voltage obtained by electrode was deduced. We also built an experimental platform to acquire signals by keeping the position of the target unchanged and moving the ultrasound transducer along the trajectory of a circular arc. The experimental results show that the wavelet filtering scheme proposed in this paper improves the SNR of the detected signal of 15.1 dB, and the images of electrical properties of the phantom and pork from isolated tissues were realized by the filtered signal of the db6 wavelet and time reversal method, which reflects the interface of electrical conductivity change of tissues. This scanning method, of fixing the target body and rotating the transducer, can effectively reduce the error and noise caused by the movement of the detection electrodes in the experiment. The filtering technique and imaging algorithm proposed in this paper have improved the SNR and contrast of the images. Thus, the images of the low conductivity phantom with 0.2 S m−1 and isolated tissue were obtained, which indicates that the MAET has good prospects in clinical applications.

Comparison of electrical impedance tomography and spirometry-based measures of airflow in healthy adult horses.

Electrical impedance tomography (EIT) is a non-invasive diagnostic tool for evaluating lung function. The objective of this study was to compare respiratory flow variables calculated from thoracic EIT measurements with corresponding spirometry variables. Ten healthy research horses were sedated and instrumented with spirometry via facemask and a single-plane EIT electrode belt around the thorax. Horses were exposed to sequentially increasing volumes of apparatus dead space between 1,000 and 8,500mL, in 5-7 steps, to induce carbon dioxide rebreathing, until clinical hyperpnea or a tidal volume of 150% baseline was reached. A 2-min stabilization period followed by 2minutes of data collection occurred at each timepoint. Peak inspiratory and expiratory flow, inspiratory and expiratory time, and expiratory nadir flow, defined as the lowest expiratory flow between the deceleration of flow of the first passive phase of expiration and the acceleration of flow of the second active phase of expiration were evaluated with EIT and spirometry. Breathing pattern was assessed based on the total impedance curve. Bland-Altman analysis was used to evaluate the agreement where perfect agreement was indicated by a ratio of EIT:spirometry of 1.0. The mean ratio (bias; expressed as a percentage difference from perfect agreement) and the 95% confidence interval of the bias are reported. There was good agreement between EIT-derived and spirometry-derived peak inspiratory [-15% (-46-32)] and expiratory [10% (-32-20)] flows and inspiratory [-6% (-25-18)] and expiratory [5% (-9-20)] times. Agreement for nadir flows was poor [-22% (-87-369)]. Sedated horses intermittently exhibited Cheyne-Stokes variant respiration, and a breath pattern with incomplete expiration in between breaths (crown-like breaths). Electrical impedance tomography can quantify airflow changes over increasing tidal volumes and changing breathing pattern when compared with spirometry in standing sedated horses.

Lung Imaging Acquisition with Electrical Impedance Tomography: Tackling Common Pitfalls.

Electrical impedance tomography is a powerful tool for lung imaging that can be employed at the bedside in multiple clinical scenarios. Diagnosing and preventing interpretation pitfalls will ensure reliable data and allow for appropriate clinical decision-making.

A modified Levenberg–Marquardt scheme for solving a class of parameter identification problems

Parameter identification problems in PDEs are special class of nonlinear inverse problems which has many applications in science and technology. One such application is the Electrical Impedance Tomography (EIT) problem. Although many methods are available in literature to tackle nonlinear problems, the computation of Fréchet derivative is often a bottle neck for deriving the solution. Moreover, many assumptions are required to establish the convergence of such methods. In this paper, we propose a modified form of Levenberg–Marquardt scheme which does not require the knowledge of exact Fréchet derivative, instead, uses an approximate form of it and at the same time, no additional assumptions are required to establish the convergence of the scheme. We illustrate the theoretical result through numerical examples. In order to ensure that the proposed scheme can be applied to practical problems, we have applied the scheme to EIT problem and the reconstruction process clearly demonstrates that the method can be successfully applied to practical problems.

Image reconstruction method for electrical impedance tomography based on RBF and attention mechanism

Electrical impedance tomography (EIT) is an imaging technology for estimating the conductivity change for the measured field of the human body. However, because EIT image reconstruction is severely ill-posed and nonlinear inverse problem, the reconstructed image based on traditional algorithm is lower accurate with obscure boundaries and lots of artifacts. In order to improve the accuracy of reconstructed image, an EIT image reconstruction method based on RBF and attention mechanism is proposed in this paper. The proposed RCU-Net network architecture consists of two sub-networks: RBF and CBAM-UNet. The RBF neural network accomplishes the nonlinear mapping between the boundary voltages and conductivity distribution values. The CBAM-UNet combining attention mechanism CBAM with U-Net makes further processing for the resulting images to obtain more sharp and explicit images. RCU-Net was trained and tested on the simulated dataset created by EIDORS platform. The experiment reveals that the proposed method outperforms the traditional methods in distinguishing multi-target, generalization ability and anti-interference, and it has improved the reconstructed image quality which has an average reduction of 55.09% and 26.23% on RE (Relative Error) and an increase of 14.19% and 3.08% on CC (Correlation Coefficient) respectively compared with RBF-EIT and RBF-UNet methods. In addition, the experimental data from KIT4 system can be applied to the trained network. This successful transition also demonstrates the proposed method can reconstruct more explicit images with high fidelity.

A fast approach to determine excitation eigenfrequencies for TD-EIT and FD-EIT

Electrical impedance tomography can reconstruct the complex conductivity distribution by injecting a current or voltage at a specific frequency into the target domain. The complex conductivity spectroscopy of numerous biological tissues is frequency-dependent. A suitable excitation frequency is vital to high-quality imaging over a wide frequency range. This paper investigates the relationship between the parameters of the biological tissue impedance model and the impedance spectroscopy. A frequency selection method based on the impedance spectroscopy is proposed, in which the impedance spectroscopy on a specific electrode at the domain boundary to be measured is first scanned. In TD-EIT, the difference between the target’s impedance spectroscopy and the null field is calculated, and the frequency corresponding to its extreme value is used as the excitation signal for TD-EIT. The excitation frequency in FD-EIT is the frequency corresponding to the extreme point in the target impedance spectroscopy, and we have also used this method to image the interior of the maize ear. This study provides a quick and efficient method for determining the excitation frequency for EIT, allowing researchers to find the best excitation frequency for high-quality imaging during actual measurements.