Multi-frequency electrical impedance tomography (mfEIT) offers a nondestructive imaging technology that reconstructs the distribution of electrical characteristics within a subject based on the impedance spectral differences among biological tissues. However, the technology faces challenges in imaging multi-class lesion targets when the conductivity of background tissues is frequency-dependent. To address these issues, we propose a spatial-frequency cross-fusion network (SFCF-Net) imaging algorithm, built on a multi-path fusion structure. This algorithm uses multi-path structures and hyper-dense connections to capture both spatial and frequency correlations between multi-frequency conductivity images, which achieves differential imaging for lesion targets of multiple categories through cross-fusion of information. According to both simulation and physical experiment results, the proposed SFCF-Net algorithm shows an excellent performance in terms of lesion imaging and category discrimination compared to the weighted frequency-difference, U-Net, and MMV-Net algorithms. The proposed algorithm enhances the ability of mfEIT to simultaneously obtain both structural and spectral information from the tissue being examined and improves the accuracy and reliability of mfEIT, opening new avenues for its application in clinical diagnostics and treatment monitoring.

Electrical impedance tomography (EIT) is a noninvasive and radiation-free imaging method. As a “soft-field” imaging technique, in EIT, the target signal in the center of the measured field is frequently swamped by the target signal at the edge, which restricts its further application. To alleviate this problem, this study presents an enhanced encoder–decoder (EED) method with an atrous spatial pyramid pooling (ASPP) module. The proposed method enhances the ability to detect central weak targets by constructing an ASPP module that integrates multiscale information in the encoder. The multilevel semantic features are fused in the decoder to improve the boundary reconstruction accuracy of the center target. The average absolute error of the imaging results by the EED method reduced by 82.0%, 83.6%, and 36.5% in simulation experiments and 83.0%, 83.2%, and 36.1% in physical experiments compared with the errors of the damped least-squares algorithm, Kalman filtering method, and U-Net-based imaging method, respectively. The average structural similarity improved by 37.3%, 42.9%, and 3.6%, and 39.2%, 45.2%, and 3.8% in the simulation and physical experiments, respectively. The proposed method provides a practical and reliable means of extending the application of EIT by solving the problem of weak central target reconstruction under the effect of strong edge targets in EIT.

Magnetic induction tomography (MIT) is viewed as a promising method for brain imaging. Most MIT studies are based on time-difference imaging, which cannot be used for detecting hemorrhagic stroke. However, for many years, multifrequency MIT (mfMIT) has been proposed for the early detection of hemorrhagic stroke, but the focus has primarily been on theoretical analysis and simulations. mfMIT has not been applied in clinical research due to issues such as inadequate imaging algorithms and mfMIT systems. A weighted frequency difference adaptive thresholding split Bregman (WFD–ATSB) algorithm is proposed here and is validated for the first time using a 16-channel mfMIT system developed by our group. The imaging results of a single-hemorrhagic model were evaluated using the total image reconstruction error [as the sum of the position error, area error, and image noise (IN)], and the imaging results of a double-hemorrhagic model were evaluated by calculating the correlation coefficient (CC). Simulation results showed that WFD–ATSB can reduce the overall image reconstruction error by 52% and improve the CC by 35% compared with that of the traditional algorithm. In phantom experiments, the total image reconstruction error was reduced by 27% and the CC was improved by 15%. The results confirmed that WFD–ATSB is a more practical and stable algorithm for mfMIT compared with traditional methods, which is promising for the rapid detection of cerebral hemorrhage.

Electrical impedance tomography (EIT) is low-cost and noninvasive and has the potential for real-time imaging and bedside monitoring of brain injury. However, brain injury monitoring by EIT imaging suffers from image noise (IN) and resolution problems, causing blurred reconstructions. To address these problems, a least absolute shrinkage and selection operator model is built, and a fast iterative shrinkage-thresholding algorithm with continuation (FISTA-C) is proposed. Results of numerical simulations and head phantom experiments indicate that FISTA-C reduces IN by 63.2%, 47.2%, and 29.9% and 54.4%, 44.7%, and 22.7%, respectively, when compared with the damped least-squares algorithm, the split Bergman, and the FISTA algorithms. When the signal-to-noise ratio of the measurements is 80–50 dB, FISTA-C can reduce IN by 83.3%, 72.3%, and 68.7% on average when compared with the three algorithms, respectively. Both simulation and phantom experiments suggest that FISTA-C produces the best image resolution and can identify the two closest targets. Moreover, FISTA-C is more practical for clinical application because it does not require excessive parameter adjustments. This technology can provide better reconstruction performance and significantly outperforms the traditional algorithms in terms of IN and resolution and is expected to offer a general algorithm for brain injury monitoring imaging via EIT.

Electrical impedance tomography (EIT) can be used for real-time bedside monitoring of pathological changes in human brain tissue and dynamic imaging. However, EIT measurement signals are easily disturbed by noise, tremor in stroke patients, and other factors in clinical practice, which result in significant artifacts in the reconstructed images. These artifacts degrade the image quality and affect the detection of focal targets. To address this problem, we propose a multiscale one-dimensional residual convolutional network (MS-1DResCNN) to remove chaotic noise and interference from the conductivity distribution data and retain the target feature data, thereby improving the robustness of the reconstruction algorithm to noise and interference. The structural similarity (SSIM) and normalized mean square error (NMSE) were used to evaluate the performance of the proposed method in suppressing image reconstruction artifacts under noise-free conditions, different noise simulation levels, and varying vibration interference frequencies. The results of physical experiments showed that, under 10 Hz vibration interference, the reconstructed images using the MS-1DResCNN method improved the SSIM by 40.4%, 22.0%, 17.4%, and 11.7% and reduced the NMSE by 74.3%, 72.4%, 65.2%, and 29.5%, compared to the damped least squares, artificial neural network, Ec-Net, and U-Net methods, respectively. This method effectively improves the anti-interference ability of conditional algorithms, significantly reduces artifacts in EIT images, and makes the perturbation target clearer and more precise, thereby providing stable and reliable algorithmic support for the clinical application of EIT.