An Integrated Multi-Channel Deep Neural Network for Mesial Temporal Lobe Epilepsy Identification Using Multi-Modal Medical Data.

Epilepsy is a chronic brain disease with recurrent seizures. Mesial temporal lobe epilepsy (MTLE) is the most common pathological cause of epilepsy. With the development of computer-aided diagnosis technology, there are many auxiliary diagnostic approaches based on deep learning algorithms. However, the causes of epilepsy are complex, and distinguishing different types of epilepsy accurately is challenging with a single mode of examination. In this study, our aim is to assess the combination of multi-modal epilepsy medical information from structural MRI, PET image, typical clinical symptoms and personal demographic and cognitive data (PDC) by adopting a multi-channel 3D deep convolutional neural network and pre-training PET images. The results show better diagnosis accuracy than using one single type of medical data alone. These findings reveal the potential of a deep neural network in multi-modal medical data fusion.

[Effect of electroconvulsive therapy on brain functional network in major depressive disorder].

Electroconvulsive therapy (ECT) is an interventional technique capable of highly effective neuromodulation in major depressive disorder (MDD), but its antidepressant mechanism remains unclear. By recording the resting-state electroencephalogram (RS-EEG) of 19 MDD patients before and after ECT, we analyzed the modulation effect of ECT on the resting-state brain functional network of MDD patients from multiple perspectives: estimating spontaneous EEG activity power spectral density (PSD) using Welch algorithm; constructing brain functional network based on imaginary part coherence (iCoh) and calculate functional connectivity; using minimum spanning tree theory to explore the topological characteristics of brain functional network. The results show that PSD, functional connectivity, and topology in multiple frequency bands were significantly changed after ECT in MDD patients. The results of this study reveal that ECT changes the brain activity of MDD patients, which provides an important reference in the clinical treatment and mechanism analysis of MDD.

Optimal Design of Array Coils for Multi-Target Adjustable Electromagnetic Brain Stimulation System.

Temporal interference magnetic stimulation is a novel noninvasive deep brain neuromodulation technology that can solve the problem of balance between focus area and stimulation depth. However, at present, the stimulation target of this technology is relatively single, and it is difficult to realize the coordinated stimulation of multiple brain regions, which limits its application in the modulation of multiple nodes in the brain network. This paper first proposes a multi-target temporal interference magnetic stimulation system with array coils. The array coils are composed of seven coil units with an outer radius of 25 mm, and the spacing between coil units is 2 mm. Secondly, models of human tissue fluid and the human brain sphere are established. Finally, the relationship between the movement of the focus area and the amplitude ratio of the difference frequency excitation sources under time interference is discussed. The results show that in the case of a ratio of 1:5, the peak position of the amplitude modulation intensity of the induced electric field has moved 45 mm; that is, the movement of the focus area is related to the amplitude ratio of the difference frequency excitation sources. The conclusion is that multi-target temporal interference magnetic stimulation with array coils can simultaneously stimulate multiple network nodes in the brain region; rough positioning can be performed by controlling the conduction of different coils, fine-tuning the position by changing the current ratio of the conduction coils, and realizing accurate stimulation of multiple targets in the brain area.

Application and evaluation of LID facilities in sponge airport, China.

Low Impact Development (LID) is an important approach for the construction of sponge airports. There are few researches on the application of LID facilities in airports. This study mainly analyzes the application of LID facilities in airports, and analyzes the reduction rate of LID facilities on the total runoff, peak present time and peaking volume by constructing EPA Storm Water Management Model (SWMM) in the eastern work area of an airport, which is located in a coastal city in northern China. This study selected three kinds of LID facilities: green roof, bio-detention facility and permeable pavement. Then three LID scenarios were formed according to different layout ratios of facilities (30%-90%), and the effects of different scenarios under different design rainstorms are simulated and analyzed. The results show that the control effect of LID scenario is enhanced with the increase of the proportion of LID facilities. The control effect of LID scenario gradually weakened with the increase of rainfall intensity. For high-frequency rainstorm, the maximum reduction rates of total runoff and peaking volume are 30.89% and 25.58% respectively, and the peak present time delay rate is up to 28.57%. For low-frequency rainstorm, the maximum reduction rates of total runoff and peaking volume are 17.96% and 14.95% respectively, and the peak present time delay rate is up to 6.12%. The flood control effect is more obvious when the LID facilities and pipe network are combined under the condition of low-frequency heavy rain. These conclusions present the effects under different combination ratio of LID facilities. It can provide the technical reference for the design and application of LID facilities for sponge airport construction in the future.

[Cross-subject electroencephalogram emotion recognition based on maximum classifier discrepancy].

Affective brain-computer interfaces (aBCIs) has important application value in the field of human-computer interaction. Electroencephalogram (EEG) has been widely concerned in the field of emotion recognition due to its advantages in time resolution, reliability and accuracy. However, the non-stationary characteristics and individual differences of EEG limit the generalization of emotion recognition model in different time and different subjects. In this paper, in order to realize the recognition of emotional states across different subjects and sessions, we proposed a new domain adaptation method, the maximum classifier difference for domain adversarial neural networks (MCD_DA). By establishing a neural network emotion recognition model, the shallow feature extractor was used to resist the domain classifier and the emotion classifier, respectively, so that the feature extractor could produce domain invariant expression, and train the decision boundary of classifier learning task specificity while realizing approximate joint distribution adaptation. The experimental results showed that the average classification accuracy of this method was 88.33% compared with 58.23% of the traditional general classifier. It improves the generalization ability of emotion brain-computer interface in practical application, and provides a new method for aBCIs to be used in practice.

Portable Aptasensor of Aflatoxin B1 in Bread Based on a Personal Glucose Meter and DNA Walking Machine.

Despite some recent developments on the portable on-site sensor of Aflatoxin B1 (AFB1), the complex and expensive preparation of recognition elements have still limited their wide applications. In this paper, using the fast, low-cost, and stable recognition of aptamer DNA-AFB1, a portable aptasensor was constructed for the on-site detection of AFB1 in food matrixes, with the readout of personal glucose meter (PGM) and DNA walking machine for signal probe separation. In such an assay protocol, the target could trigger the DNA walker to autonomously move on the electrode surface, propelled by unidirectional Pb2+-specific DNAzyme digestion, which could amplify the signal and separate the signal probe as well for further quantification by the PGM. Under optimized conditions, the increase of PGM signal was relative with the concentration of AFB1 ranging from 0.02 to 10 nM and the low limit of detection (LOD) was 10 pM (S/N = 3). With the features of portability, and cheapness, the presented user-friendly method could be extended to various other analytes for wide point-of-care applications.

A Simple Method of Electrospun Tungsten Trioxide Nanofibers with Enhanced Visible-Light Photocatalytic Activity.

The present study involves the fabrication of tungsten trioxide (WO3) nanofibers by an electrospinning technique using polyvinyl pyrrolidone (PVP)/citric acid/tungstic acid as precursor solution. It was found that the PVP concentration was one of the most crucial processing parameters determining the final properties of WO3 nanofibers. The optimum concentration of PVP was from 75 to 94 g L-1. The average diameter of the nanofibers increases with increasing the PVP concentration, whereas it is decreased after sintering and orthorhombic structure were formed at 500 °C. The photocatalytic properties of the as-synthesized nanofibers were also investigated by degrading methylene blue and twofold efficiency was obtained compared with that of commercial WO3 microparticles.

[Analysis of composite traditional Chinese medicine constitution: an investigation of 974 volunteers].

OBJECTIVE: To explore the analysis methods for composite traditional Chinese medicine (TCM) constitutions. METHODS: The epidemiological data of TCM constitutions were collected from 974 volunteers via a cross-sectional survey. The samples were classified into 9 constitution types according to the maximal standardized scores of imbalanced constitutions. The correlation matrix of 9 constitutions was computed. The standardized scores of 9 constitutions of all the volunteers were ranked respectively, and the composite status of every two constitutions was observed using cross tabulation. The constitution types of all the volunteers were transformed into ternary code of 9 digits, and the composite status of 3 or more than 3 kinds of constitution types was analyzed. RESULTS: According to the maximal standardized scores of imbalanced constitutions, of 974 volunteers, 227, 148, 218, 102, 31, 81, 44, 97 and 26 volunteers had balanced constitution, qi-deficiency constitution, yang-deficiency constitution, yin-deficiency constitution, phlegm-dampness constitution, heat-dampness constitution, blood stasis constitution, qi-stagnation constitution, and inherited special constitution, respectively. The standardized scores of balanced constitution were negatively correlated with those of imbalanced constitutions, while there was a positive correlation between the standardized scores of every two imbalanced constitutions. Among the 8 imbalanced constitutions, one kind of imbalanced constitutions was usually complicated with another kind of imbalanced constitutions. The number of qi-deficiency constitution complicated with yang-deficiency constitution, qi-deficiency constitution complicated with yin-deficiency constitution, and yin-deficiency constitution complicated with yang-deficiency constitution ranked the top three. The constitution types of 974 volunteers were transformed into a total of 465 ternary codes, showing a total of 465 kinds of constitution types; the simplex constitution, the approximately simplex constitution, and the composite constitution of two or more than two types were found in 259, 130, and 585 volunteers, respectively. CONCLUSION: Cross tabulation can show the composite status of every two constitutions, while the ternary code can show the composite status of three or more than three constitutions.

Primary anaplastic solitary fibrous tumor of the tentorium cerebelli.

Meningeal solitary fibrous tumors (MSFT) have been described in about 80 patients as benign spindle-cell neoplasms, with few anaplastic variants. We report a 57-year-old male patient with a 4-month history of progressive headache caused by a primary anaplastic MSFT arising from the tentorium cerebelli. MRI revealed a tentorium-based tumor that extended into the occipital lobe superiorly and into the cerebellum inferiorly on the left. Following gross total resection of the tumor and postoperative radiotherapy, the patient experienced symptomatic improvement with no recurrence at the 12-month follow-up. The final tumor pathology was consistent with an anaplastic MSFT, with a Ki-67 proliferative index of 25%.