Jiafeng Yao

Melanoma is a highly malignant skin tumor, and early detection with accurate boundary delineation is critical for improving patient survival. Electrical impedance tomography (EIT) is a promising technique for melanoma detection due to its noninvasiveness, low cost, and portability. However, current EIT reconstruction methods are prone to boundary blurring, structural distortion, and missing details owing to the highly ill‐posed nature of the inverse problem. To address this issue, this paper develops an Adaptive Dynamic Window SwinUNet (ADW‐SwinUNet) for EIT‐based melanoma imaging. The acquired 16 × 13 boundary voltage vector is transformed into a 128 × 128 feature map and then fed into the network. By introducing an ADW mechanism, the network enables hierarchical multi‐scale feature modeling, thereby improving the balance between global conductivity representation and local boundary recovery. In addition, a 16‐electrode honeycomb‐structured handheld sensor is designed to improve the sensitivity distribution within the sensing domain. Compared with the conventional ring‐shaped configuration, the proposed planar electrode configuration enhances the sensitivity in the central and transition regions, thereby improving the response to internal abnormalities. Simulation results demonstrate that ADW‐SwinUNet outperforms Tikhonov regularization, convolutional neural network‐based methods, and DHU‐Net, a high‐capacity network based on an improved U‐Net architecture, achieving an average root mean square error (RMSE) of 0.044 and an intraclass correlation coefficient of 0.98. Experimental results validate that the proposed method exhibits high robustness, with RMSE values ranging from 0.06 to 0.10. These results indicate the potential of the proposed method for noninvasive and portable EIT‐based skin melanoma imaging.

A dynamic analysis method for medaka embryo membrane during organ development stage using dielectric relaxation model functions is proposed. The membrane’s bioimpedance curves are extracted from lower-frequency part of the measured differential Nyquist plot, and it is fitted by the membrane’s relaxation model functions. Not only the permeability, integrity, uniformity and symmetry of membrane are analyzed according to the fitted relaxation models and parameters, but also the microdamage, directional features of the membrane and the action of hatching enzymes are analyzed. To establish the correlation between physiological characteristics of membrane and its relaxation models and parameters, the physiological dynamics of embryo membrane are introduced firstly, then its relaxation model functions and parameters during organogenesis are studied. The proposed method is evaluated in experiment. The physiological dynamics of membrane during organ development stage are analyzed by the experiment results. Firstly, the membrane is intact and symmetrical, then some micropores and micro protrusions are formed, afterwards some directional features like the oriented pores and invaginations are appearing, finally, the chorion and gelatinous layer of the membrane are separated due to the action of hatching enzymes. The proposed method provides a reliable way to analyze physiological changes of medaka embryo membrane during organogenesis.

Diabetic foot ulcer (DFU) progression is associated with abnormal plantar loading and pathological tissue changes. Conventional plantar pressure systems provide mechanical information only, while electrical impedance tomography (EIT) can provide tissue conductivity information but is affected by pressure-related impedance changes at the electrode–tissue interface. This study proposes a physics-constrained three-dimensional pressure-decoupled EIT (3D-pdEIT) framework to estimate pressure-dependent electrode–tissue contact impedance and incorporate it into the EIT forward model, thereby reducing the propagation of pressure-induced boundary perturbations into reconstructed tissue conductivity. Pork tissue phantoms with agar inclusions were constructed to mimic ulcer-like regions. Boundary impedance collected under loads of 1.96–49.03 N applied at 16 electrode positions. Hertz contact mechanics and Holm’s electrical contact theory were integrated to establish a pressure-dependent contact impedance model, which was embedded into the complete electrode model through Robin boundary conditions to achieve pressure decoupling in the EIT forward problem. In addition, a Gaussian mixture model (GMM) prior was introduced to improve the contrast and boundary definition of reconstructed inclusions. The multi-frequency measurements revealed a pronounced nonlinear and load-dependent boundary impedance response, with a pressure-sensitive spectral feature identified around 1.18 M Hz. The proposed framework achieved a spatial load-localization RMSE of 1.44 mm on the independent phantom test dataset, while the load-magnitude estimation achieved an average R2 > 0.938 across the electrode array. Compared with conventional Tikhonov noser EIT reconstruction, the proposed 3D-pdEIT framework reduced pressure-induced errors and improved inclusion localization. The framework provides a physics-guided approach for estimating plantar pressure distribution and characterizing tissue conductivity abnormalities.

During robotic cell manipulation tasks, micro-force sensors play an important role to provide real-time force feedback for precise interaction between the robotic manipulator and the environmental cells. In order to accommodate a larger cross-scale range of forces, this paper presents an active micro-force sensing strategy based on a macro-fiber composite (MFC) enabled piezoelectric cantilever operating in a closed-loop force-balancing mode. Unlike conventional passive piezoelectric sensors whose usable range is limited by structural nonlinearity and stiffness, the proposed sensor employs a symmetric MFC sandwich beam, in which one MFC layer performs force sensing while the other provides counteracting actuation under a robust model predictive control scheme. By actively maintaining near-zero tip deflection, the applied micro-force is inferred directly from the balancing actuation voltage rather than from the structural deflection. A distributed-parameter dynamic model of the composite beam is derived using modal superposition, enabling precise controller synthesis and state estimation via a Kalman observer. Calibration experiments demonstrate a sensing resolution of 10.12 μN over a measurement range of 21.53 mN, resulting in a range-to-resolution ratio of 2127.5, significantly exceeding that of existing piezoelectric micro-force sensors. After that, the effectiveness of the developed sensor is further validated in robotic manipulation of zebrafish embryos and onion cells. The results confirm that the active MFC enabled force sensor provides a practical route to wide-range, high-resolution force sensing for delicate biological micromanipulation tasks.

Objective. The objective of this study was to assess the feasibility and accuracy of computed tomography (CT)-guided electrical impedance tomography (CT-guided EIT) in the quantitative detection of the spatial distribution and location of pneumothorax, hemothorax, and hemopneumothorax lesions and effective ventilation regions in pig models. Approach . Five Bama miniature pigs were used to establish models of pneumothorax, hemothorax, and hemopneumothorax by incrementally injecting air or Ringer’s solution in 100 ml steps up to a total volume of 500 ml into the right pleural cavity. Synchronous EIT data and CT images were acquired at each experimental stage. EIT images were reconstructed using the GREIT algorithm with anatomical constraints derived from CT-based lung contours. Mean total boundary voltage (mTBV), pneumothorax pixel area (PPA), hemothorax pixel area (HPA), center of ventilation (CoV), Dice similarity coefficient (Dice), and centroid distance ( d _c ) were used for quantitative assessment. PPA, HPA, and CoV are statistically compared between EIT and CT using Spearman correlation and Bland–Altman agreement analysis. Main results. mTBV showed a strong linear correlation with injected air volume ( R ² = 0.968–0.994) and fluid volume ( R ² = 0.712–0.994). In pneumothorax models, Dice = 0.828–0.884 and d _c = 2.80–3.33. In hemothorax models, Dice = 0.850–0.874 and d _c = 2.64–3.34. PPA, HPA, and CoV derived from CT-guided EIT images correlated significantly with CT findings (Spearman r = 0.63–0.92, p < 0.001). Ventilation distribution patterns in EIT were consistent with CT, with dorsal shifts during pneumothorax and ventral shifts during hemothorax. Bland–Altman plots showed good agreement between EIT and CT measurements. Significance. This study demonstrates the feasibility of CT-guided EIT for dynamic monitoring and quantitative evaluation of pneumothorax, hemothorax, and hemopneumothorax in pig models. Its noninvasive, radiation-free, and bedside monitoring nature makes it a promising tool for detecting pulmonary pathological accumulation during mechanical ventilation and postoperative care.

This study proposes a microscale electrochemical impedance spectroscopy tomography (EIST) method for identifying bacterial antibiotic resistance. An 8-electrode array microfluidic electrical impedance sensor chip is designed to enable this approach. Firstly, the influence of electrode pair configuration on the sensor's impedance measurement performance is investigated through numerical simulations, leading to the optimization of the sensor's design. Secondly, polystyrene (PS) beads coated with different metal films are used to simulate bacteria cells at various resistance stages in experimental trials. The proposed method is validated both through numerical simulations and experimental data, demonstrating successful localization of target with a diameter of 20 µm, Furthermore, PS beads coated with different metal films, representing varying bacterial antibiotic resistance states, were effectively identified. The results highlight the significant potential of this approach for the rapid, real-time diagnosis of bacterial antibiotic resistance.

Electrical Impedance Tomography (EIT) image reconstruction frequently encounters significant artifacts due to the inherent high nonlinearity and ill-posed nature of the inverse problem. In this study, we propose an Efficient Multi-Scale Attention Convolutional Neural Network-Transformer (ECNN-Transformer) method specifically designed for EIT lung imaging. Building upon the Visual Geometry Group (VGG) model, we adjust both the depth of the network and the step size of the pooling layer. Additionally, we incorporate an Efficient Multi-Scale Attention Mechanism Module (EMA) along with a Transformer neural network. These enhancements contribute to creating lightweight network models that improve reconstruction accuracy and robustness while effectively mitigating artifacts. The proposed network was trained using 28000 EIT simulation models generated from chest CT images of patients. During model generation, various conditions such as lung tumors, lung hyperexpansion, and lung collapse were randomly simulated. The efficacy of our method was evaluated through a series of simulation data and static experiments. To quantitatively assess reconstruction quality, we calculated metrics including root mean square error (RMSE), peak signal-to-noise ratio (PSNR), and the structural similarity index (SSIM). Experimental results demonstrate that our proposed method achieves an average RMSE of 0.024, a PSNR value of 21.16, and an SSIM exceeding 0.893. This approach facilitates high-resolution reconstruction in EIT lung imaging while accurately restoring conductivity characteristics associated with pathological tissues—particularly in scenarios involving measurement noise. We anticipate that this methodology will yield reliable interference-free images suitable for potential clinical applications such as imaging human lung tumors.