A Deep Learning Framework for Evaluating the Over-the-Air Performance of the Antenna in Mobile Terminals.

This study introduces RTEEMF (Real-Time Evaluation Electromagnetic Field)-PhoneAnts, a novel Deep Learning (DL) framework for the efficient evaluation of mobile phone antenna performance, addressing the time-consuming nature of traditional full-wave numerical simulations. The DL model, built on convolutional neural networks, uses the Near-field Electromagnetic Field (NEMF) distribution of a mobile phone antenna in free space to predict the Effective Isotropic Radiated Power (EIRP), Total Radiated Power (TRP), and Specific Absorption Rate (SAR) across various configurations. By converting antenna features and internal mobile phone components into near-field EMF distributions within a Huygens' box, the model simplifies its input. A dataset of 7000 mobile phone models was used for training and evaluation. The model's accuracy is validated using the Wilcoxon Signed Rank Test (WSR) for SAR and TRP, and the Feature Selection Validation Method (FSV) for EIRP. The proposed model achieves remarkable computational efficiency, approximately 2000-fold faster than full-wave simulations, and demonstrates generalization capabilities for different antenna types, various frequencies, and antenna positions. This makes it a valuable tool for practical research and development (R&D), offering a promising alternative to traditional electromagnetic field simulations. The study is publicly available on GitHub for further development and customization. Engineers can customize the model using their own datasets.

Attention Mask R-CNN with edge refinement algorithm for identifying circulating genetically abnormal cells.

Recent studies have suggested that circulating tumor cells with abnormalities in gene copy numbers in mononuclear cell-enriched peripheral blood samples, such as circulating genetically abnormal cells (CACs), can be used as a non-invasive tool to detect patients with benign pulmonary nodules. These cells are identified through fluorescence signals counting by using 4-color fluorescence in situ hybridization (FISH) technology that exhibits high stability, sensitivity, and specificity. When FISH data are analyzed, the overlapping cells and fluorescence noise is a great challenge for identifying of CACs, thereby seriously affecting the efficiency of clinical diagnosis. To address this problem, in this study, we proposed an end-to-end FISH-based method (CACNET) for CAC identification. CACNET achieved nuclear segmentation and counted 4-color staining signals through improved Mask region-based convolutional neural network (R-CNN), followed by cell category (normal cell, deletion cell, gain cell, or CAC) according to pathological criteria. Firstly, the segmentation accuracy of overlapping nuclei was improved by adding an edge constraint head during training. Then, the interference of fluorescence noise was reduced by fusing non-local module to reconstruct the feature extraction network of Mask R-CNN. We trained and tested the proposed model on a dataset comprising 700 frames with 58,083 nuclei. The Accuracy, Sensitivity, and Specificity (overall performance metric for the algorithm) of CAC identification with CACNET were 94.06%, 92.1%, and 99.8%, respectively. Moreover, the developed method exhibited approximately identification speed of approximately 0.22 s per frames. The results showed that the proposed method outperformed the existing CAC identification methods, making it a promising approach for early screening of lung cancer.

Dynamic Gesture Recognition Based on FMCW Millimeter Wave Radar: Review of Methodologies and Results.

As a convenient and natural way of human-computer interaction, gesture recognition technology has broad research and application prospects in many fields, such as intelligent perception and virtual reality. This paper summarized the relevant literature on gesture recognition using Frequency Modulated Continuous Wave (FMCW) millimeter-wave radar from January 2015 to June 2023. In the manuscript, the widely used methods involved in data acquisition, data processing, and classification in gesture recognition were systematically investigated. This paper counts the information related to FMCW millimeter wave radar, gestures, data sets, and the methods and results in feature extraction and classification. Based on the statistical data, we provided analysis and recommendations for other researchers. Key issues in the studies of current gesture recognition, including feature fusion, classification algorithms, and generalization, were summarized and discussed. Finally, this paper discussed the incapability of the current gesture recognition technologies in complex practical scenes and their real-time performance for future development.

A Lightweight and Robust Framework for Circulating Genetically Abnormal Cells (CACs) Identification Using 4-Color Fluorescence In Situ Hybridization (FISH) Image and Deep Refined Learning.

Circulating genetically abnormal cells (CACs) constitute an important biomarker for cancer diagnosis and prognosis. This biomarker offers high safety, low cost, and high repeatability, which can serve as a key reference in clinical diagnosis. These cells are identified by counting fluorescence signals using 4-color fluorescence in situ hybridization (FISH) technology, which has a high level of stability, sensitivity, and specificity. However, there are some challenges in CACs identification, due to the difference in the morphology and intensity of staining signals. In this concern, we developed a deep learning network (FISH-Net) based on 4-color FISH image for CACs identification. Firstly, a lightweight object detection network based on the statistical information of signal size was designed to improve the clinical detection rate. Secondly, the rotated Gaussian heatmap with a covariance matrix was defined to standardize the staining signals with different morphologies. Then, the heatmap refinement model was proposed to solve the fluorescent noise interference of 4-color FISH image. Finally, an online repetitive training strategy was used to improve the model's feature extraction ability for hard samples (i.e., fracture signal, weak signal, and adjacent signals). The results showed that the precision was superior to 96%, and the sensitivity was higher than 98%, for fluorescent signal detection. Additionally, validation was performed using the clinical samples of 853 patients from 10 centers. The sensitivity was 97.18% (CI 96.72-97.64%) for CACs identification. The number of parameters of FISH-Net was 2.24 M, compared to 36.9 M for the popularly used lightweight network (YOLO-V7s). The detection speed was about 800 times greater than that of a pathologist. In summary, the proposed network was lightweight and robust for CACs identification. It could greatly increase the review accuracy, enhance the efficiency of reviewers, and reduce the review turnaround time during CACs identification.

Assessment of Twin Fetal Exposure to Environmental Magnetic and Electromagnetic Fields.

Fetal development is vital in the human lifespan. Therefore, it is essential to characterize exposure by a series of typical environmental magnetic and electromagnetic fields. In particular, there has recently been a sharp increase in the twin birth rate. However, lack of appropriate models has prohibited dosimetric evaluation, restricting characterization of the impact of these environmental factors on twins. The present study developed two whole-body pregnant models of 31 and 32 weeks of gestation with twin fetuses and explored several typical exposure scenarios, including 50-Hz uniform magnetic field exposure, local 125-kHz magnetic field (MF), and 13.56-MHz electromagnetic field exposure, as well as wideband planewave radiofrequency (RF) exposure from 20 to 6000 MHz. Finally, dosimetric results were derived. Compared to the singleton pregnancy with similar weeks of gestation, twin fetuses were overexposed at 50-Hz uniform MF, but they were probably underexposed in the RF scenarios with frequencies for wireless communications. Furthermore, the twin fetuses manifested large dosimetric variability compared to the singleton, which was attributed to the incident direction and fetal position. Based on the analysis, the dosimetric results over the entire gestation period were estimated. The results can be helpful to estimate the risk of twin-fetal exposure to electromagnetic fields and examine the conservativeness of the international guidelines.© 2022 Bioelectromagnetics Society.

Deformable torso phantoms of Chinese adults for personalized anatomy modelling.

In recent years, there has been increasing demand for personalized anatomy modelling for medical and industrial applications, such as ergonomics device development, clinical radiological exposure simulation, biomechanics analysis, and 3D animation character design. In this study, we constructed deformable torso phantoms that can be deformed to match the personal anatomy of Chinese male and female adults. The phantoms were created based on a training set of 79 trunk computed tomography (CT) images (41 males and 38 females) from normal Chinese subjects. Major torso organs were segmented from the CT images, and the statistical shape model (SSM) approach was used to learn the inter-subject anatomical variations. To match the personal anatomy, the phantoms were registered to individual body surface scans or medical images using the active shape model method. The constructed SSM demonstrated anatomical variations in body height, fat quantity, respiratory status, organ geometry, male muscle size, and female breast size. The masses of the deformed phantom organs were consistent with Chinese population organ mass ranges. To validate the performance of personal anatomy modelling, the phantoms were registered to the body surface scan and CT images. The registration accuracy measured from 22 test CT images showed a median Dice coefficient over 0.85, a median volume recovery coefficient (RCvlm ) between 0.85 and 1.1, and a median averaged surface distance (ASD) < 1.5 mm. We hope these phantoms can serve as computational tools for personalized anatomy modelling for the research community.

A reverberation chamber for rodents' exposure to wideband radiofrequency electromagnetic fields with different small-scale fading distributions.

A reverberation chamber (RC) is realized for the rodents' in vivo exposure to electromagnetic fields (EMFs) with various small-scale fading characteristics. Its performance is evaluated to ensure the exposure experiments from 0.85 to 2.60 GHz. By different configurations, line-of-sight and non-line-of-sight exposures can be established. The measured electric field in the RC is analyzed to determine its statistical distribution. We accordingly reconstruct the EMF environment by numerical methods. Simulations are carried to compare the dosimetric variability due to different small-scale fading characteristics. It demonstrates that the surveyed fading distribution will not change the specific absorption rate in the rats. The possibility to reproduce the realistic multi-reflective EMF environment by adjusting the structures of the RC is discussed. It is the first reported in vivo exposure system aiming to provide the EMF exposure with different small-scale fading distributions.

Dosimetry of infant exposure to power-frequency magnetic fields: variation of 99th percentile induced electric field value by posture and skin-to-skin contact.

Infant exposure to 50 Hz magnetic fields from power lines was numerically analyzed in this study. Dosimetric variability due to posture and skin-to-skin contact was evaluated using human anatomical models including a recently developed model of a 12-months-old infant. As proposed by the International Commission on Non-Ionizing Radiation Protection, the induced E-field strength (99th percentile value, E99 ) for the central nerve systems (E99_CNS ) and peripheral nerve system (E99_PNS ), were used as metrics. Results showed that the single (free of contact with others) infant model has lower E99 (E99_CNS and E99_PNS inclusive) compared with single adult and child models when exposed to the same power-frequency magnetic field. Also, studied postures of sitting, standing, or arm-up, would not change E99 _PNS . However, skin-to-skin contact with other models could significantly raise induced E-field strength in the infant (e.g., contact on 0.93% of the infant's total surface increased E99_PNS by 213%). Simulations with canonical models were conducted to assess different factors contributing to the E99 enhancement. Results indicated the importance of thoroughly investigating the conservativeness of current safety guidelines in the case of skin-to-skin contact, especially with infants.

Dosimetry for infant exposures to electronic article surveillance system: posture, physical dimension and anatomy.

The use of electronic article surveillance (EAS) systems has become popular in many public sites. As a consequence, concern has risen about infant exposure to magnetic fields (MFs) from this kind of device. To evaluate infant exposure to MFs of an EAS system (operating at 125 kHz and 13.56 MHz), we numerically compared dosimetric results among adult, child and infant models. Results revealed that postures insignificantly influenced dosimetric results if there was a similar cross-sectional area under exposure. Although safety limits are unlikely to be exceeded, the infant has higher SAR values for brain and central nervous system tissues compared with adult (1.5x at 125 kHz and 112x at 13.56 MHz), which deserve further investigation. Infant's specific anatomy (e.g., non-proportionally large head and high fat content) did not induce higher SAR values. The numerical models developed in the study (stroller and postured infant models) could be freely used for nonprofit academic research.

Generation of infant anatomical models for evaluating electromagnetic field exposures.

Realistic anatomical modeling is essential in analyzing human exposure to electromagnetic fields. Infants have significant physical and anatomical differences compared with other age groups. However, few realistic infant models are available. In this work, we developed one 12-month-old male whole body model and one 17-month-old male head model from magnetic resonance images. The whole body and head models contained 28 and 30 tissues, respectively, at spatial resolution of 1 mm × 1 mm × 1 mm. Fewer identified tissues in the whole body model were a result of the low original image quality induced by the fast imaging sequence. The anatomical and physical parameters of the models were validated against findings in published literature (e.g., a maximum deviation as 18% in tissue mass was observed compared with the data from International Commission on Radiological Protection). Several typical exposure scenarios were realized for numerical simulation. Dosimetric comparison with various adult and child anatomical models was conducted. Significant differences in the physical and anatomical features between adult and child models demonstrated the importance of creating realistic infant models. Current safety guidelines for infant exposure to radiofrequency electromagnetic fields may not be conservative.

Dosimetric variability of the rats' exposure to electromagnetic pulses.

Rats' exposure to electromagnetic pulses (EMPs) has been conducted using an EMP simulator for various biological endpoints. In contrast, information about the EMP energy distribution and its variability in rats is lacking. EMPs are signals with spectrum concentrating in several hundred MHz, leading to EM absorption patterns different from those obtained at high frequencies. In this study, two anatomical models of rats (a male and a female) were reconstructed from magnetic resonance imaging. The models had the same posture as in the exposure experiments. Realistic EMPs were acquired directly from the EMP simulator and applied to the simulations. The interaction of the EMP with the rat was analyzed through the finite-difference time-domain method. Two approaches were utilized to calculate the energy absorption at the tissue and whole-body levels. Dosimetric variability due to incident directions, polarizations, exposure signals simplification, and rat separation was evaluated in this study. The variability result differed substantially from that of the non-constrained rats' exposure experiments. The result sensitivity to frequency and amplitude was discussed as well. The work can be used as a basis to determine the uncertainty and to formulate a standard experimental protocol for this type of experiment.

Dosimetric study on eye's exposure to wide band radio frequency electromagnetic fields: variability by the ocular axial length.

This paper evaluates the variability of specific absorption rate (SAR) in the human eye. This variability results from changes in ocular axial length (OAL), which is common in many ophthalmologic and vision abnormalities, including myopia. A generic eye model was reconstructed according to published data. The feasibility of using the generic model in numerical research of electromagnetic fields (EMF) was demonstrated by means of comparative simulations with eye models reconstructed from magnetic resonance (MR) scans. Free-form deformation (FFD) was used to deform the OAL of the generic eye model. Thus, 64 deformed eyes were created and were categorized according to the OAL increase. The finite-difference time-domain (FDTD) method was applied in the simulations. The results revealed that changing the OAL does not increase EMF absorption in the eyes or the eye tissues. No additional induced temperature rise was produced by the changes of OAL. The results also indicated that the non-pathological increment of the OAL, which is inevitable during the childhood, does not increase the SAR in the eyes.

Semi-supervised lung adenocarcinoma histopathology image classification based on multi-teacher knowledge distillation.

Objective.In this study, we propose a semi-supervised learning (SSL) scheme using a patch-based deep learning (DL) framework to tackle the challenge of high-precision classification of seven lung tumor growth patterns, despite having a small amount of labeled data in whole slide images (WSIs). This scheme aims to enhance generalization ability with limited data and reduce dependence on large amounts of labeled data. It effectively addresses the common challenge of high demand for labeled data in medical image analysis.Approach.To address these challenges, the study employs a SSL approach enhanced by a dynamic confidence threshold mechanism. This mechanism adjusts based on the quantity and quality of pseudo labels generated. This dynamic thresholding mechanism helps avoid the imbalance of pseudo-label categories and the low number of pseudo-labels that may result from a higher fixed threshold. Furthermore, the research introduces a multi-teacher knowledge distillation (MTKD) technique. This technique adaptively weights predictions from multiple teacher models to transfer reliable knowledge and safeguard student models from low-quality teacher predictions.Main results.The framework underwent rigorous training and evaluation using a dataset of 150 WSIs, each representing one of the seven growth patterns. The experimental results demonstrate that the framework is highly accurate in classifying lung tumor growth patterns in histopathology images. Notably, the performance of the framework is comparable to that of fully supervised models and human pathologists. In addition, the framework's evaluation metrics on a publicly available dataset are higher than those of previous studies, indicating good generalizability.Significance.This research demonstrates that a SSL approach can achieve results comparable to fully supervised models and expert pathologists, thus opening new possibilities for efficient and cost-effective medical images analysis. The implementation of dynamic confidence thresholding and MTKD techniques represents a significant advancement in applying DL to complex medical image analysis tasks. This advancement could lead to faster and more accurate diagnoses, ultimately improving patient outcomes and fostering the overall progress of healthcare technology.

Study of MI-BCI classification method based on the Riemannian transform of personalized EEG spatiotemporal features.

Motor imagery (MI) is a traditional paradigm of brain-computer interface (BCI) and can assist users in creating direct connections between their brains and external equipment. The common spatial patterns algorithm is the most popular spatial filtering technique for collecting EEG signal features in MI-based BCI systems. Due to the defect that it only considers the spatial information of EEG signals and is susceptible to noise interference and other issues, its performance is diminished. In this study, we developed a Riemannian transform feature extraction method based on filter bank fusion with a combination of multiple time windows. First, we proposed the multi-time window data segmentation and recombination method by combining it with a filter group to create new data samples. This approach could capture individual differences due to the variation in time-frequency patterns across different participants, thereby improving the model's generalization performance. Second, Riemannian geometry was used for feature extraction from non-Euclidean structured EEG data. Then, considering the non-Gaussian distribution of EEG signals, the neighborhood component analysis (NCA) algorithm was chosen for feature selection. Finally, to meet real-time requirements and a low complexity, we employed a Support Vector Machine (SVM) as the classification algorithm. The proposed model achieved improved accuracy and robustness. In this study, we proposed an algorithm with superior performance on the BCI Competition IV dataset 2a, achieving an accuracy of 89%, a kappa value of 0.73 and an AUC of 0.9, demonstrating advanced capabilities. Furthermore, we analyzed data collected in our laboratory, and the proposed method achieved an accuracy of 77.4%, surpassing other comparative models. This method not only significantly improved the classification accuracy of motor imagery EEG signals but also bore significant implications for applications in the fields of brain-computer interfaces and neural engineering.

Semi-automatic Framework for Voxel Human Deformation Modeling.

BACKGROUND: With the advancement of computer and medical imaging technologies, a number of high-resolution, voxel-based, full-body human anatomical models have been developed for medical education, industrial design, and physics simulation studies. However, these models are limited in many applications because they are often only in an upstanding posture. OBJECTIVE: To quickly develop multi-pose human models for different applications. A semi-automatic framework for voxel deformation is proposed in the study. METHODS: This paper describes a framework for human pose deformation based on three-dimensional (3D) medical images. The voxel model is first converted into a surface model using a surface reconstruction algorithm. Second, a deformation skeleton based on human bones is defined, and the surface model is bound to the skeleton. The bone Glow algorithm is used to assign weights to the surface vertices. Then, the model is deformed to the target posture by using the Smoothed Rotation Enhanced As-Rigid-As-Possible (SR-ARAP) algorithm. Finally, the volume-filling algorithm is applied to refill the tissues into the deformed surface model. RESULTS: The proposed framework is used to deform two standing human models, and the sitting and running models are developed. The results show that the framework can successfully develop the target pose. When compared to the results of the As-Rigid-As-Possible algorithm, SR-ARAP preserves local tissues better. CONCLUSION: The study proposes a frame for voxel human model deformation and improves the local tissue integrity during deformation.

Evaluation of Chinese populational exposure to environmental electromagnetic field based on stochastic dosimetry and parametric human modelling.

This study aimed to estimate the distribution of the whole-body averaged specific absorption rate (WBSAR) using several measurable physique parameters for Chinese adult population exposed to environmental electromagnetic fields (EMFs) of current wireless communication frequencies, and to discuss the effects of these physique parameters in the frequency-dependent dosimetric results. The physique distribution of Chinese adults was obtained from the National Physical Fitness and Health Database comprising 81,490 adult samples. The number of physique parameters used to construct the surrogate model was reduced to three via mutual information analysis. A stochastic method with 40 deterministic simulations was used to generate frequency-dependent and gender-specific surrogate models for WBSAR via polynomial chaos expansion. In the simulations, we constructed anatomically correct models conforming to the targeted physique parameters via deformable human modelling technique, which was based on deep learning from the image database including 767 Chinese adults. Thereafter, we analysed the sensitivity of the physique parameters to WBSAR by covariance-based Sobol decomposition. The results indicated that the generated models were consistent with the targeted physique parameters. The estimated dosimetric results were validated using finite-difference time-domain simulations (the error was < 6% across all the investigated frequencies for WBSAR). The novelty of the study included that it demonstrated the feasibility of estimating the individual WBSAR using a limited number of physique parameters with the aid of surrogate modelling. In addition, the population-based distribution of the WBSAR in Chinese adults was firstly presented in the manuscript. The results also indicated that the different combinations of physique parameter, dependent on genders and frequencies, significantly influenced the WBSAR, although the general conservativeness of the guidelines of the International Commission on Non-Ionizing Radiation and Protection can be confirmed in the surveyed population.

Modulation of Sleep Architecture by Whole-Body Static Magnetic Exposure: A Study Based on EEG-Based Automatic Sleep Staging.

A steady increase in sleep problems has been observed along with the development of society. Overnight exposure to a static magnetic field has been found to improve sleep quality; however, such studies were mainly based on subjective evaluation. Thus, the presented data cannot be used to infer sleep architecture in detail. In this study, the subjects slept on a magneto-static mattress for four nights, and self-reported scales and electroencephalogram (EEG) were used to determine the effect of static magnetic field exposure (SMFE) on sleep. Machine learning operators, i.e., decision tree and supporting vector machine, were trained and optimized with the open access sleep EEG dataset to automatically discriminate the individual sleep stages, determined experimentally. SMEF was found to decrease light sleep duration (N2%) by 3.51%, and sleep onset latency (SOL) by 15.83%, while it increased deep sleep duration (N3%) by 8.43%, compared with the sham SMFE group. Further, the overall sleep efficiency (SE) was also enhanced by SMFE. It is the first study, to the best of our knowledge, where the change in sleep architecture was explored by SMFE. Our findings will be useful in developing a non-invasive sleep-facilitating instrument.

Functional and network analyses of human exposure to long-term evolution signal.

Human exposure to the electromagnetic field emitted by wireless communication systems has raised public concerns. There were claims of the potential association of some neurophysiological disorders with the exposure, but the mechanism is yet to be established. The wireless networks, recently, experience a transition from the 4th generation (4G) to 5th generation (5G), while 4G long-term evolution (LTE) is still the frequently used signal in wireless communication. In the study, exposure experiments were conducted using the LTE signal. The subjects were divided into sham and real exposure groups. Before and after the exposure experiments, they underwent functional magnetic resonance imaging. Within-session and between-session comparisons have been executed for functional connectivity and network properties. Individual specific absorption rate (SAR) was also calculated. The results indicated that acute LTE exposure beneath the safety limits modulated both the functional connection and graph-based properties. To characterize the effect of functional activity, SAR averaged over a certain tissue mass was not an appropriate metric. The potential neurophysiological effect of 5G exposure has also been discussed in the study.