Preoperative prediction of hepatocellular carcinoma microvascular invasion based on magnetic resonance imaging feature extraction artificial neural network

BACKGROUND Hepatocellular carcinoma(HCC)recurrence is highly correlated with increased mortality.Microvascular invasion(MVI)is indicative of aggressive tumor biology in HCC.AIM To construct an artificial neural network(ANN)capable of accurately predicting MVI presence in HCC using magnetic resonance imaging.METHODS This study included 255 patients with HCC with tumors<3 cm.Radiologists annotated the tumors on the T1-weighted plain MR images.Subsequently,a three-layer ANN was constructed using image features as inputs to predict MVI status in patients with HCC.Postoperative pathological examination is considered the gold standard for determining MVI.Receiver operating characteristic analysis was used to evaluate the effectiveness of the algorithm.RESULTS Using the bagging strategy to vote for 50 classifier classification results,a prediction model yielded an area under the curve(AUC)of 0.79.Moreover,correlation analysis revealed that alpha-fetoprotein values and tumor volume were not significantly correlated with the occurrence of MVI,whereas tumor sphericity was significantly correlated with MVI(P<0.01).CONCLUSION Analysis of variable correlations regarding MVI in tumors with diameters<3 cm should prioritize tumor sphericity.The ANN model demonstrated strong predictive MVI for patients with HCC(AUC=0.79).

Numerical Analysis of the Magnetic Dipole Effect on a Radiative Ferromagnetic Liquid Flowing over a Porous Stretched Sheet

The effects of a magnetic dipole on a nonlinear thermally radiative ferromagnetic liquidflowing over a stretched surface in the presence of Brownian motion and thermophoresis are investigated.By means of a similarity transformation,ordinary differential equations are derived and solved afterwards using a numerical(the BVP4C)method.The impact of various parameters,namely the velocity,temperature,concentration,is presented graphically.It is shown that the nanoparticles properties,in conjunction with the magnetic dipole effect,can increase the thermal conductivity of the engineered nanofluid and,consequently,the heat transfer.Comparison with earlier studies indicates high accuracy and effectiveness of the numerical approach.An increase in the Brow-nian motion parameter and thermophoresis parameter enhances the concentration and the related boundary layer.The skin-friction rises when the viscosity parameter is increased.A larger value of the ferromagnetic para-meter results in a higher skin-friction and,vice versa,in a smaller Nusselt number.

Hierarchical Magnetic Network Constructed by CoFe Nanoparticles Suspended Within “Tubes on Rods” Matrix Toward Enhanced Microwave Absorption

Hierarchical magnetic-dielectric composites are promising functional materials with prospective applications in microwave absorption(MA)field.Herein,a three-dimension hierarchical“nanotubes on microrods,”core–shell magnetic metal–carbon composite is rationally constructed for the first time via a fast metal–organic frameworksbased ligand exchange strategy followed by a carbonization treatment with melamine.Abundant magnetic CoFe nanoparticles are embedded within one-dimensional graphitized carbon/carbon nanotubes supported on micro-scale Mo2N rod(Mo2N@CoFe@C/CNT),constructing a special multi-dimension hierarchical MA material.Ligand exchange reaction is found to determine the formation of hierarchical magnetic-dielectric composite,which is assembled by dielectric Mo2N as core and spatially dispersed CoFe nanoparticles within C/CNTs as shell.Mo2N@CoFe@C/CNT composites exhibit superior MA performance with maximum reflection loss of−53.5 dB at 2 mm thickness and show a broad effective absorption bandwidth of 5.0 GHz.The Mo2N@CoFe@C/CNT composites hold the following advantages:(1)hierarchical core–shell structure offers plentiful of heterojunction interfaces and triggers interfacial polarization,(2)unique electronic migration/hop paths in the graphitized C/CNTs and Mo2N rod facilitate conductive loss,(3)highly dispersed magnetic CoFe nanoparticles within“tubes on rods”matrix build multi-scale magnetic coupling network and reinforce magnetic response capability,confirmed by the off-axis electron holography.

Repetitive transcranial magnetic stimulation for lower extremity motor function in patients with stroke:a systematic review and network meta-analysis

Transcranial magnetic stimulation,a type of noninvasive brain stimulation,has become an ancillary therapy for motor function rehabilitation.Most previous studies have focused on the effects of repetitive transcranial magnetic stimulation(rTMS)on motor function in stroke patients.There have been relatively few studies on the effects of different modalities of rTMS on lower extremity motor function and corticospinal excitability in patients with stroke.The MEDLINE,Embase,Cochrane Library,ISI Science Citation Index,Physiotherapy Evidence Database,China National Knowledge Infrastructure Library,and ClinicalTrials.gov databases were searched.Parallel or crossover randomized controlled trials that addressed the effectiveness of rTMS in patients with stroke,published from inception to November 28,2019,were included.Standard pairwise meta-analysis was conducted using R version 3.6.1 with the“meta”package.Bayesian network analysis using the Markov chain Monte Carlo algorithm was conducted to investigate the effectiveness of different rTMS protocol interventions.Network meta-analysis results of 18 randomized controlled trials regarding lower extremity motor function recovery revealed that low-frequency rTMS had better efficacy in promoting lower extremity motor function recovery than sham stimulation.Network meta-analysis results of five randomized controlled trials demonstrated that highfrequency rTMS led to higher amplitudes of motor evoked potentials than low-frequency rTMS or sham stimulation.These findings suggest that rTMS can improve motor function in patients with stroke,and that low-frequency rTMS mainly affects motor function,whereas high-frequency rTMS increases the amplitudes of motor evoked potentials.More highquality randomized controlled trials are needed to validate this conclusion.The work was registered in PROSPERO(registration No.CRD42020147055)on April 28,2020.

Small-worldness of brain networks after brachial plexus injury: a resting-state functional magnetic resonance imaging study

Research on brain function after brachial plexus injury focuses on local cortical functional reorganization,and few studies have focused on brain networks after brachial plexus injury.Changes in brain networks may help understanding of brain plasticity at the global level.We hypothesized that topology of the global cerebral resting-state functional network changes after unilateral brachial plexus injury.Thus,in this cross-sectional study,we recruited eight male patients with unilateral brachial plexus injury（right handedness,mean age of 27.9±5.4years old）and eight male healthy controls（right handedness,mean age of 28.6±3.2）.After acquiring and preprocessing resting-state magnetic resonance imaging data,the cerebrum was divided into 90 regions and Pearson’s correlation coefficient calculated between regions.These correlation matrices were then converted into a binary matrix with affixed sparsity values of 0.1–0.46.Under sparsity conditions,both groups satisfied this small-world property.The clustering coefficient was markedly lower,while average shortest path remarkably higher in patients compared with healthy controls.These findings confirm that cerebral functional networks in patients still show smallworld characteristics,which are highly effective in information transmission in the brain,as well as normal controls.Alternatively,varied small-worldness suggests that capacity of information transmission and integration in different brain regions in brachial plexus injury patients is damaged.

GA-BASED PID NEURAL NETWORK CONTROL FOR MAGNETIC BEARING SYSTEMS

In order to overcome the system non-linearity and uncertainty inherent in magnetic bearing systems, a GA（genetic algnrithm）-based PID neural network controller is designed and trained tO emulate the operation of a complete system （magnetic bearing, controller, and power amplifiers）. The feasibility of using a neural network to control nonlinear magnetic bearing systems with unknown dynamics is demonstrated. The key concept of the control scheme is to use GA to evaluate the candidate solutions （chromosomes）, increase the generalization ability of PID neural network and avoid suffering from the local minima problem in network learning due to the use of gradient descent learning method. The simulation results show that the proposed architecture provides well robust performance and better reinforcement learning capability in controlling magnetic bearing systems.

Prediction of the undrained shear strength of remolded soil with non-linear regression,fuzzy logic,and artificial neural network

This study aims to predict the undrained shear strength of remolded soil samples using non-linear regression analyses,fuzzy logic,and artificial neural network modeling.A total of 1306 undrained shear strength results from 230 different remolded soil test settings reported in 21 publications were collected,utilizing six different measurement devices.Although water content,plastic limit,and liquid limit were used as input parameters for fuzzy logic and artificial neural network modeling,liquidity index or water content ratio was considered as an input parameter for non-linear regression analyses.In non-linear regression analyses,12 different regression equations were derived for the prediction of undrained shear strength of remolded soil.Feed-Forward backpropagation and the TANSIG transfer function were used for artificial neural network modeling,while the Mamdani inference system was preferred with trapezoidal and triangular membership functions for fuzzy logic modeling.The experimental results of 914 tests were used for training of the artificial neural network models,196 for validation and 196 for testing.It was observed that the accuracy of the artificial neural network and fuzzy logic modeling was higher than that of the non-linear regression analyses.Furthermore,a simple and reliable regression equation was proposed for assessments of undrained shear strength values with higher coefficients of determination.

Rectification of magnetic force tracker using neural network inaugmented reality system

Nonlinear errors always exist in data obtained from tracker in augmented reality （AR）, which badly influence the effect of AR. This paper proposes to rectify the errors using BP neural network. As BP neural network is prone to getting into local extrema and convergence is slow, genetic algorithm is employed to optimize the initial weights and threshold of neural network. This paper discusses how to set the crucial parameters in the algorithm. Experimental results show that the method ensures that the neural network achieves global convergence quickly and correctly. Tracking precision of AR system is improved after the tracker is rectified, and the third dimension of AR system is enhanced.

GliomaCNN: An Effective Lightweight CNN Model in Assessment of Classifying Brain Tumor from Magnetic Resonance Images Using Explainable AI

Brain tumors pose a significant threat to human lives and have gained increasing attention as the tenth leading cause of global mortality.This study addresses the pressing issue of brain tumor classification using Magnetic resonance imaging(MRI).It focuses on distinguishing between Low-Grade Gliomas(LGG)and High-Grade Gliomas(HGG).LGGs are benign and typically manageable with surgical resection,while HGGs are malignant and more aggressive.The research introduces an innovative custom convolutional neural network(CNN)model,Glioma-CNN.GliomaCNN stands out as a lightweight CNN model compared to its predecessors.The research utilized the BraTS 2020 dataset for its experiments.Integrated with the gradient-boosting algorithm,GliomaCNN has achieved an impressive accuracy of 99.1569%.The model’s interpretability is ensured through SHapley Additive exPlanations(SHAP)and Gradient-weighted Class Activation Mapping(Grad-CAM++).They provide insights into critical decision-making regions for classification outcomes.Despite challenges in identifying tumors in images without visible signs,the model demonstrates remarkable performance in this critical medical application,offering a promising tool for accurate brain tumor diagnosis which paves the way for enhanced early detection and treatment of brain tumors.

Breast Tumor Computer-Aided Detection System Based on Magnetic Resonance Imaging Using Convolutional Neural Network

Background:The main cause of breast cancer is the deterioration of malignant tumor cells in breast tissue.Early diagnosis of tumors has become the most effective way to prevent breast cancer.Method:For distinguishing between tumor and non-tumor in MRI,a new type of computer-aided detection CAD system for breast tumors is designed in this paper.The CAD system was constructed using three networks,namely,the VGG16,Inception V3,and ResNet50.Then,the influence of the convolutional neural network second migration on the experimental results was further explored in the VGG16 system.Result:CAD system built based on VGG16,Inception V3,and ResNet50 has higher performance than mainstream CAD systems.Among them,the system built based on VGG16 and ResNet50 has outstanding performance.We further explore the impact of the secondary migration on the experimental results in the VGG16 system,and these results show that the migration can improve system performance of the proposed framework.Conclusion:The accuracy of CNN represented by VGG16 is as high as 91.25%,which is more accurate than traditional machine learningmodels.The F1 score of the three basic networks that join the secondary migration is close to 1.0,and the performance of the VGG16-based breast tumor CAD system is higher than Inception V3,and ResNet50.

Chronic antiepileptic drug use and functional network efficiency: A functional magnetic resonance imaging study

AIM To increase our insight in the neuronal mechanisms underlying cognitive side-effects of antiepileptic drug(AED) treatment.METHODS The relation between functional magnetic resonance-acquired brain network measures, AED use, and cognitive function was investigated. Three groups of patients with epilepsy with a different risk profile for developing cognitive side effects were included: A "low risk" category(lamotrigine or levetiracetam, n=16), an "intermediate risk" category(carbamazepine, oxcarbazepine, phenytoin, or valproate, n=34) and a "high risk" category(topiramate, n=5). Brain connectivity was assessed using resting state functional magnetic resonance imaging and graph theoretical network analysis. The Computerized Visual Searching Task was used to measure central information processing speed, a common cognitive side effect of AED treatment. RESULTS Central information processing speed was lower in patients taking AEDs from the intermediate and high risk categories, compared with patients from the low risk category. The effect of risk category on global efficiency was significant(P < 0.05, ANCOVA), with a significantly higher global efficiency for patient from the low category compared with the high risk category(P < 0.05, post-hoc test). Risk category had no significant effect on the clustering coefficient(ANCOVA, P > 0.2). Also no significant associations between information processing speed and global efficiency or the clustering coefficient(linear regression analysis, P > 0.15) were observed. CONCLUSION Only the four patients taking topiramate show aberrant network measures, suggesting that alterations in functional brain network organization may be only subtle and measureable in patients with more severe cognitive side effects.

Ensembling Neural Networks for User’s Indoor Localization Using Magnetic Field Data from Smartphones

Predominantly the localization accuracy of the magnetic field-based localization approaches is severed by two limiting factors:Smartphone heterogeneity and smaller data lengths.The use of multifarioussmartphones cripples the performance of such approaches owing to the variability of the magnetic field data.In the same vein,smaller lengths of magnetic field data decrease the localization accuracy substantially.The current study proposes the use of multiple neural networks like deep neural network(DNN),long short term memory network(LSTM),and gated recurrent unit network(GRN)to perform indoor localization based on the embedded magnetic sensor of the smartphone.A voting scheme is introduced that takes predictions from neural networks into consideration to estimate the current location of the user.Contrary to conventional magnetic field-based localization approaches that rely on the magnetic field data intensity,this study utilizes the normalized magnetic field data for this purpose.Training of neural networks is carried out using Galaxy S8 data while the testing is performed with three devices,i.e.,LG G7,Galaxy S8,and LG Q6.Experiments are performed during different times of the day to analyze the impact of time variability.Results indicate that the proposed approach minimizes the impact of smartphone variability and elevates the localization accuracy.Performance comparison with three approaches reveals that the proposed approach outperforms them in mean,50%,and 75%error even using a lesser amount of magnetic field data than those of other approaches.

Application of New Type BP Neural Networks for Magnetic Measurement

Magnetic measurement is a typical inverse problem in Biomedical field. In this kind of problem we always need to locate the positions and moments of one or more magnetic dipoles. Although using the traditional methods to solve this kind of inverse problem has all kinds of shortcomings, BPNN (Back Propagation Neural Networks) method can be used to solve this typical inverse problem fast enough for real time measurement. In the traditional BPNN method, gradient descent search method is performed for error propagation. In this paper the authors propose a new algorithm that Newton method is performed for error propagation. For the cost function is highly nonconvex in the magnetic measurement problem, the new kind of BPNN can get convergent results quickly and precisely. A simulation result for this method is also presented.

Quantitative Interpretation for the Magnetic Flux Leakage Testing Data Based on Neural Network

In order to interpret the magnetic flux leakage (MFL) testing data quantitatively and size the defects accurately, some defect profiles inversion methods from the MFL signals are studied on the basis of the neural network.Because the wavelet ba- sis function neural network (WBFNN) has good accuracy in the forward calculation and the radial basis function neural network (RBFNN) has reliable precision in the inversion modeling respectively,a new neural network scheme combining WBFNN and RBFNN is presented to solve the nonlinear inversion problem for the MFL data and reconstruct the defect shapes.And such details as the choice of wavelet basis function,the initialization of the weight value and the input normalization are analyzed,the train- ing and testing algorithm for the network are also studied.The inversion results demonstrate that the proposed network scheme has good reliability to interpret the MFL data for some defects.

Pattern transition and regulation in a subthalamopallidal network under electromagnetic effect

Although the significant roles of magnetic induction and electromagnetic radiation in the neural system have been widely studied,their influence on Parkinson’s disease(PD)has yet to be well explored.By virtue of the magnetic flux variable,this paper studies the transition of firing patterns induced by magnetic induction and the regulation effect of external magnetic radiation on the firing activities of the subthalamopallidal network in basal ganglia.We find:(i)The network reproduces five typical waveforms corresponding to the severity of symptoms:weak cluster,episodic,continuous cluster,episodic,and continuous wave.(ii)Magnetic induction is a double-edged sword for the treatment of PD.Although the increase of magnetic coefficient may lead the physiological firing activity to transfer to pathological firing activity,it also can regulate the pathological intensity firing activity with excessiveβ-band power transferring to the physiological firing pattern with weakβ-band power.(iii)External magnetic radiation could inhibit continuous tremulous firing andβ-band power of subthalamic nucleus(STN),which means the severity of symptoms weakened.Especially,the bi-parameter plane of the regulation region shows that a short pulse period of magnetic radiation and a medium level of pulse percentage can well regulate pathological oscillation.This work helps to understand the firing activity of the subthalamopallidal network under electromagnetic effect.It may also provide insights into the mechanisms behind the electromagnetic therapy of PD-related firing activity.

Brain Functional Network Improved by Magnetic Stimulation at Acupoints during Mental Fatigue

To investigate the effects of magnetic stimulation at acupoints on brain functional network during mental fatigue, magnetic stimulation was applied to stimulate SHENMEN (HT7), HEGU (LI4) and LAOGONG (PC8) acupoint in this paper. The brain functional networks of normal state, mental fatigue state and stimulated state were constructed and the characteristic parameters were comparatively studied based on the complex network theory. The results showed that the connection of the network was enhanced by stimulating the HT7, LI4 and PC8 acupoint. In conclusion, magnetic stimulation at acupoints can effectively relieve mental fatigue.

Leveraging Quantum Computing for the Ising Model to Simulate Two Real Systems: Magnetic Materials and Biological Neural Networks (BNNs)

Quantum computing is a field with increasing relevance as quantum hardware improves and more applications of quantum computing are discovered. In this paper, we demonstrate the feasibility of modeling Ising Model Hamiltonians on the IBM quantum computer. We developed quantum circuits to simulate these systems more efficiently for both closed and open boundary Ising models, with and without perturbations. We tested these various geometries of systems in both 1-D and 2-D space to mimic two real systems: magnetic materials and biological neural networks (BNNs). Our quantum model is more efficient than classical computers, which can struggle to simulate large, complex systems of particles.

UNBALANCE RESPONSE AND TOUCH-RUBBING THRESHOLD SPEED OF ROTOR SUBJECTED TO NONLINEAR MAGNETIC FORCES

Because of the effect of unbalance excitation and nonlinear magnetic force, the large vibration of the rotor supported by active magnetic bearing（AMB） will go beyond the radial gap of the bearing, even causing mechanical touch-rubbing when the system works at an operational speed closer to the critical speed. In order to investigate this problem, the linear model and nonlinear model of the single mass symmetric rigid rotor system supported by AMB are established respectively and the corresponding transfer functions of close-loop system are given. To pass through the numerical calculation by using MATLAB/Simulink, the effect of both the unbalance response and threshold speed of touch-rubbing of the system subjected to nonlinear magnetic forces and nonlinear output current of power amplifier are studied. Furthermore, threshold speed of touch-rubbing of the rotor-bearing system is defined and the results of numerical simulation are presented. Finally, based on above studies, two methods of increasing the touch-rubbing threshold speed are discussed.

Application of neural networks for permanent magnet synchronous motor direct torque control

Neural networks require a lot of training to understand the model of a plant or a process. Issues such as learning speed, stability, and weight convergence remain as areas of research and comparison of many training algorithms. The application of neural networks to control interior permanent magnet synchronous motor using direct torque control （DTC） is discussed. A neural network is used to emulate the state selector of the DTC. The neural networks used are the back-propagation and radial basis function. To reduce the training patterns and increase the execution speed of the training process, the inputs of switching table are converted to digital signals, i.e., one bit represent the flux error, one bit the torque error, and three bits the region of stator flux. Computer simulations of the motor and neural-network system using the two approaches are presented and compared. Discussions about the back-propagation and radial basis function as the most promising training techniques are presented, giving its advantages and disadvantages. The system using back-propagation and radial basis function networks controller has quick parallel speed and high torque response.

Magnetic non-potentiality on the quiet Sun and the filigree

From the observed vector magnetic fields by the Solar Optical Telescope/ Spectro-Polarimeter aboard the satellite Hinode, we have examined whether or not the quiet Sun magnetic fields are non-potential, and how the G-band filigrees and Ca II network bright points （NBPs） are associated with the magnetic non-potentiality. A sizable quiet region in the disk center is selected for this study. The new findings by the study are as follows. （1） The magnetic fields of the quiet region are obviously non-potential. The region-average shear angle is 40°, the average vertical current is 0.016A m^-2, and the average free magnetic energy density, 2.7× 10^2erg cm^-3. The magnitude of these non-potential quantities is comparable to that in solar active regions. （2） There are overall correlations among current helicity, free magnetic energy and longitudinal fields. The magnetic non-potentiality is mostly concentrated in the close vicinity of network elements which have stronger longitudinal fields. （3） The filigrees and NBPs are magnetically characterized by strong longitudinal fields, large electric helicity, and high free energy density. Because the selected region is away from any enhanced network, these new results can generally be applied to the quiet Sun. The findings imply that stronger network elements play a role in high magnetic non-potentiality in heating the solar atmosphere and in conducting the solar wind.