As magneto-acoustic-electrical tomography (MAET) combines the merits of high contrast and high imaging resolution, and is extremely useful for electrical conductivity measurement, so it is expected to be a promising medical imaging modalities for diagnosis of early-stage cancer. Based on the Verasonics system and the MC600 displacement platform, we designed and implemented a MAET system with a chirp pulse stimulation (MAET-CPS) method and a focal probe was utilized for stepscan focus excitation to enhance the imaging resolution. The relevant experiments were conducted to explore the influence of excitation positions of the single-focus point, and the effect of the excitation position on the amplitudes of the conductivity variation was clearly demonstrated. In order to take advantage of the merits of multifocus imaging, we firstly proposed a single focus MAET system with a chirp pulse stimulation (sfMAET-CPS) method and a multifocus MAET system with a chirp pulse stimulation (mfMAET-CPS) method for high-resolution conductivity imaging, and a homogenous gelatin phantom with a cuboid-shaped hole was used to investigate the accuracy of mfMAET-CPS. Comparative experiments were carried out on the same uniform phantom by the sfMAET-CPS and the mfMAET-CPS, respectively. The results showed that: (1) the electrical conductivity distributions of the homogenous phantom with a cuboid-shaped hole were detected by the sfMAET-CPS but were easily affected by the focal point, which demonstrated that the sfMAET-CPS had a low imaging resolution. (2) Compared with the sfMAET-CPS, the imaging effect of the mfMAET-CPS was much better than that of the sfMAET-CPS. (3) A linear interpolation algorithm was used to process the 2D conductivity distribution; it increased the smoothness of the conductivity distribution and improved the imaging effect. The stepscan focus excitation and the linearly frequency-modulated theory provide an alternative scheme for the clinical application of MAET.
Based on the Hall effect, a magneto-acousto-electrical tomography (MAET) has been indicated to have a good ability for distinguishing the conductivity variations along the acoustic propagation direction, and B-scan imaging of the MAET is expected to obtain pathological information of the tissue. For achieving a clear B-scan image, in this paper, we designed and implemented a MAET system with a planar transducer and conducted a series of experiments to explore the characteristics of the magneto-acoustic-electrical (MAE) signal and electromagnetic interference (EMI) signal. The influence of the EMI signal on the MAE voltage signal was demonstrated experimentally, and the generation mechanism of the EMI signal was explained. Concurrently, several effective methods were proposed for reducing the EMI signal and improving the imaging resolution of the B-scan image. Additionally, for obtaining a B-scan image with high resolution, the detection front end was redesigned and algorithms applying the characteristics of the MAE signal were proposed. The accuracy, feasibility, and effectiveness of the improved methods were verified. Finally, a B-scan image was reconstructed with the relative amplitude of the conductivity. The results showed that: 1) the MAE signal obtained by the redesigned platform could be well separated from the EMI signal and had a higher SNR than that obtained by the previous detection system; 2) the proposed imaging algorithms had a high detection accuracy and achieved an axis resolution of 1 mm on the z-axis; and 3) the interfaces of the conductivity changes of homogeneous phantoms with 0.5% salinity were clearly presented by measuring the MAE wave packets, and the measured thicknesses of the phantoms were highly consistent with the actual thicknesses. This paper provides a theoretical and experimental basis for detecting the interface positions of conductivity variation, and the presented MAET technology is expected to become an alternative medical imaging modality for the early diagnosis and detection of biological cancerous tissues.
The assessment of liver fibrosis is usually required in the diagnostic and treatment procedures for chronic liver disease. In this paper, we propose a deep convolutional neural network (DCNN) with multi-feature fusion (DCNN-MFF) to extract and integrate features from ultrasound (US) B-mode image and Nakagami parametric map for significant liver fibrosis recognition. The DCNN-MFF model mainly consists of three branches, among which the first two branches are used for extracting deep features respectively from the US B-mode image and the Nakagami parametric map, while the remaining branch is designed for extracting quantitative US features from the Nakagami parametric map. At the backend of the DCNN model, the extracted deep and quantitative features are fused together for final decision making. The performance of the DCNN-MFF model was evaluated on an animal dataset collected from 84 rats with 168 liver lobes under various fibrosis stages. Across five-fold cross-validation, the accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) achieved by the proposed DCNN-MFF model for significant liver fibrosis recognition were respectively 0.827 (95% confidence interval [CI] 0.762-0.881), 0.821 (95% CI 0.729-0.892), 0.836 (95% CI 0.731-0.912), 0.869 (95% CI 0.809-0.916), which are significantly better than those provided by the comparative methods.
As a non-invasive and hybrid imaging modality, magneto-acoustic-electrical tomography (MAET) is extremely useful for the electrical conductivity measurement in vivo. Based on the Verasonics system and the MC600 displacement platform, we designed and implemented a novel MAET system with a chirp pulse stimulation (MAET-CPS) method for electrical conductivity measurement. In the system, a 2–3 MHz chirp signal was exploited for stimulating ultrasound power probe. Then, the interface positions of conductivity variation were obtained by digital demodulation of the excitation signal and the received voltage signal. Finally, five different homogeneous phantoms with same size were used to investigate the feasibility, accuracy and repeatability of MAET-CPS. The results showed that: 1) When a chirp signal with pulse duration of 1000 μs was used to stimulate a homogeneous phantom with 0.5% NaCl, the reconstructed B-scan image of the conductivity distribution was highly consistent with the ultrasound B-scan imaging and physical size. 2) The signal-to-noise ratio of the system and the detection resolution of the interface of conductivity variations could be influenced by the linear frequency modulation period. The resolution obtained by using chirp signal with pulse duration of 1000 μs was better than that of 500 μs and 1500 μs. 3) The interfaces of conductivity variations of homogeneous phantoms with five different concentrations (0.4%, 0.5%, 0.6%, 0.7%, and 0.8%) were clearly presented and the measured thicknesses of each phantom showed good agreement with the thickness of the target sample. This paper has laid the foundation for the MAET-CPS modality in the phantom sample, and MAET-CPS is expected to become an alternative imaging method for early diagnosis and detection of biological cancerous tissues.
The surface electromyographic (sEMG) signals reflect human motor intention and can be utilized for human-machine interfaces (HMI). Comparing to the sparse multi-channel (SMC) electrodes, the high-density (HD) electrodes have a large number of electrodes and compact space between electrodes, which can achieve more sEMG information and have the potential to achieve higher performance in myocontrol. However, when the HD electrodes grid shift or damage, it will affect gesture recognition and reduce recognition accuracy. To minimize the impact resulting from the electrodes shift and damage, we proposed an attention deep fast convolutional neural network (attention-DFCNN) model by utilizing the temporary and spatial characteristics of high-density surface electromyography (HD-sEMG) signals. Contrary to the previous methods, which are mostly base on sEMG temporal features, the attention-DFCNN model can improve the robustness and stability by combining the spatial and temporary features. The performance of the proposed model was compared with other classical method and deep learning methods. We used the dataset provided by The University Medical Center Göttingen. Seven able-bodied subjects and one amputee involved in this work. Each subject executed nine gestures under the electrodes shift (10 mm) and damage (6 channels). As for the electrodes shift 10 mm in four directions (inwards; onwards; upwards; downwards) on seven able-bodied subjects, without any pre-training, the average accuracy of attention-DFCNN (0.942 0.04) is significantly higher than LSDA (0.910 0.04, p < 0.01), CNN (0.920 0.05, p < 0.01), TCN (0.840 0.07, p < 0.01), LSTM (0.864 0.08, p < 0.01), attention-BiLSTM (0.852 0.07, p < 0.01), Transformer (0.903 0.07, p < 0.01) and Swin-Transformer (0.908 0.09, p < 0.01). The proposed attention-DFCNN algorithm and the way of combining the spatial and temporary features of sEMG signals can significantly improve the recognition rate when the HD electrodes grid shift or damage during wear.
In this paper, an optically reconfigurable coded metasurface based on photosensitive silicon material for generating multi-channel, multi-mode vortex beams in the terahertz band is proposed. The top layer of the proposed metasurface is a skeletonized metal ring with eight photosensitive silicon patches equidistantly filled in the middle; the bottom structure is a metal plate for reflecting electromagnetic waves. The coding process of the eight photosensitive silicon patches and the use of a spatially structured light source for aligned irradiation can realize the reflection phase reconstruction and form a 3-bit reconfigurable metasurface. Based on the principle of coded metasurface convolution and the principle of superposition, the phase distributions of 3-bit metasurface arrays for single-channel and multi-channel vortex beams are calculated. Under the excitation of a right circularly polarized plane wave, a vertically reflected +1 order vortex wave, a +2 order vortex wave reflected in the tilted direction, +2 and +3 order vortex waves in two directions, and vortex beams carrying orbital angular momentum of orders −2, +1, +2, and +3 in four different directions, respectively, are generated. Our work provides a new way to design a programmable and reconfigurable metasurface, and the designed novel optically controlled reconfigurable metasurface is potentially valuable in the fields of dynamic imaging, terahertz communication, and so on.