Efficacy of various surgical methods in the treatment of allergic rhinitis: A network meta-analysis.

OBJECTIVE: We often use surgery to treat allergic rhinitis (AR) patients who have failed drug treatment, but there is currently no clear gold standard for the treatment of allergic rhinitis. Using network meta-analysis, we evaluated the efficacy of different surgical methods in the treatment of AR. METHODS: PubMed, Embase, The Cochrane Library, Web of Science, CBM, Wan Fang Data, and CNKI databases were searched to collect clinical randomized controlled trials of AR with different surgical methods that met the inclusion criteria. After two investigators independently screened literature, extracted data, and assessed the risk of bias of included studies, R software was used to evaluate inconsistency using the node splitting method, and Stata15.1 was used to estimate the ranking probability of treatment. RESULTS: A total of 47 randomized control studies involving 17 surgical schemes and 4144 participants were included. The results showed that after excluding surgical methods that did not form a closed loop, in AR patients without chronic rhinosinusitis and nasal polyps, surgical efficiency and symptom score ranked the same, which were posterior nasal neurectomy (PNN), Vidian neurectomy (VN), anterior ethmoid neurectomy (AEN), nasal septal reconstruction (NSR), and bilateral inferior turbinoplasty (BIT). In AR patients with chronic rhinosinusitis with nasal polyps, the effective rate (OR = 5.06; 95% CI = 2.75-9.32) and symptom and sign scores (MD = -3.80; 95% CI = -6.50-1.09) of PNN + FESS (functional endoscopic sinusitis surgery) were higher than FESS, and there was a significant difference. CONCLUSION: Our findings suggest that PNN is the best single operation for patients with AR and without chronic rhinosinusitis and nasal polyps, and the combination of multiple procedures may be better than a single operation. FESS + PNN is more effectual in AR patients with chronic rhinosinusitis with nasal polyps.

COVID-19 and risk spillovers of China's major financial markets: Evidence from time-varying variance decomposition and wavelet coherence analysis.

COVID-19 has influenced financial markets drastically; however, this influence has received little attention, particularly in China. This study investigates risk spillovers across China's financial and shipping markets through dynamic spillover measures based on time-varying parameter vector autoregression and generalized forecast error variance decompositions. Stock, fund, and futures markets are identified as major risk senders, whereas other markets are identified as major risk receivers. Surprisingly, bonds, gold, and shipping are safe havens that facilitate portfolio optimization. Furthermore, using wavelet coherence analysis, we find that the coherence between dynamic total spillover and COVID-19 varies across time and frequency domains.

Joint reconstruction of neuron and ultrastructure via connectivity consensus in electron microscope volumes.

BACKGROUND: Nanoscale connectomics, which aims to map the fine connections between neurons with synaptic-level detail, has attracted increasing attention in recent years. Currently, the automated reconstruction algorithms in electron microscope volumes are in great demand. Most existing reconstruction methodologies for cellular and subcellular structures are independent, and exploring the inter-relationships between structures will contribute to image analysis. The primary goal of this research is to construct a joint optimization framework to improve the accuracy and efficiency of neural structure reconstruction algorithms. RESULTS: In this investigation, we introduce the concept of connectivity consensus between cellular and subcellular structures based on biological domain knowledge for neural structure agglomeration problems. We propose a joint graph partitioning model for solving ultrastructural and neuronal connections to overcome the limitations of connectivity cues at different levels. The advantage of the optimization model is the simultaneous reconstruction of multiple structures in one optimization step. The experimental results on several public datasets demonstrate that the joint optimization model outperforms existing hierarchical agglomeration algorithms. CONCLUSIONS: We present a joint optimization model by connectivity consensus to solve the neural structure agglomeration problem and demonstrate its superiority to existing methods. The intention of introducing connectivity consensus between different structures is to build a suitable optimization model that makes the reconstruction goals more consistent with biological plausible and domain knowledge. This idea can inspire other researchers to optimize existing reconstruction algorithms and other areas of biological data analysis.

Water pollutant discharge permit allocation based on DEA and non-cooperative game theory.

Against the background of the ecological civilization system reform in the new era, the appropriate allocation of water pollutant discharge permits is an important policy for controlling the amount of wastewater discharge. Traditional allocation methods have disadvantages, such as high additional costs, an unfair allocation scheme, and market distortion. In the present study, a fixed-cost allocation model based on data envelopment analysis (DEA) and the Nash non-cooperative game theory is employed to allocate water pollutant discharge permits of totally 31 provinces in China from 2008 to 2017. The allocation scheme considers environmental efficiency. The results demonstrate regional differences in the allocation of water pollutant discharge permits. The eastern region has abundant allocations. The northeastern and central regions have insufficient allocations. Besides, the western region has a significant shortage of allocations. It indicates the higher the utilization efficiency of the water pollutant discharge permits, the higher the region's sustainable development is. Based on the analysis, we propose guidelines for industrial wastewater discharge reduction.

Development and validation of a novel diagnostic model for initially clinical diagnosed gastrointestinal stromal tumors using an extreme gradient-boosting machine.

INTRODUCTION: Gastrointestinal stromal tumor (GIST) is the most common gastrointestinal soft tissue tumor. Clinical diagnosis mainly relies on enhanced CT, endoscopy and endoscopic ultrasound (EUS), but the misdiagnosis rate is still high without fine needle aspiration biopsy. We aim to develop a novel diagnostic model by analyzing the preoperative data of the patients. METHODS: We used the data of patients who were initially diagnosed as gastric GIST and underwent partial gastrectomy. The patients were randomly divided into training dataset and test dataset at a ratio of 3 to 1. After pre-experimental screening, max depth = 2, eta = 0.1, gamma = 0.5, and nrounds = 200 were defined as the best parameters, and in this way we developed the initial extreme gradient-boosting (XGBoost) model. Based on the importance of the features in the initial model, we improved the model by excluding the hematological features. In this way we obtained the final XGBoost model and underwent validation using the test dataset. RESULTS: In the initial XGBoost model, we found that the hematological indicators (including inflammation and nutritional indicators) examined before the surgery had little effect on the outcome, so we subsequently excluded the hematological indicators. Similarly, we also screened the features from enhanced CT and ultrasound gastroscopy, and finally determined the 6 most important predictors for GIST diagnosis, including the ratio of long and short diameter under CT, the CT value of the tumor, the enhancement of the tumor in arterial period and venous period, existence of liquid area and calcific area inside the tumor under EUS. Round or round-like tumors with a CT value of around 30 (25-37) and delayed enhancement, as well as liquid but not calcific area inside the tumor best indicate the diagnosis of GIST. CONCLUSIONS: We developed a model to further differential diagnose GIST from other tumors in initially clinical diagnosed gastric GIST patients by analyzing the results of clinical examinations that most patients should have completed before surgical resection.

Efficacy and Safety of Complete Mesocolic Excision in Patients With Colon Cancer: Three-year Results From a Prospective, Nonrandomized, Double-blind, Controlled Trial.

OBJECTIVE: The aim of the study was to evaluate the oncological outcomes of complete mesocolic excision (CME) in colon cancer patients. SUMMARY BACKGROUND DATA: CME is considered a standard procedure for colon cancer patients. However, previous evidence regarding the effect of CME on prognosis has fundamental limitations that prevent it from being fully accepted. METHODS: Patients who underwent radical resection for colon cancer were enrolled between November 2012 and March 2016. According to the principles of CME, patients were stratified into 2 groups based on intraoperative surgical fields and specimen photographs. The primary outcome was local recurrence-free survival (LRFS). The clinicopathological data and follow-up information were collected and recorded. The final follow-up date was April 2016. The trial was registered in ClinicalTrials.gov (identifier: NCT01724775). RESULTS: There were 220 patients in the CME group and 110 patients in the noncomplete mesocolic excision (NCME) group. Baseline characteristics were well balanced. Compared with NCME, CME was associated with a greater number of total lymph nodes (24 vs 20, P = 0.002). Postoperative complications did not differ between the 2 groups. CME had a positive effect on LRFS compared with NCME (100.0% vs 90.2%, log-rank P < 0.001). Mesocolic dissection (100.0% vs 87.9%, log-rank P < 0.001) and nontumor deposits (97.2% vs 91.6%, log-rank P < 0.022) were also associated with improved LRFS. CONCLUSIONS: Our findings demonstrate that, compared with NCME, CME improves 3-year LRFS without increasing surgical risks.

An innovative method for screening and evaluating the degree of diabetic retinopathy and drug treatment based on artificial intelligence algorithms.

Current methods of evaluating the degree of diabetic retinopathy are highly subjective and have no quantitative standard. To objectively evaluate the slight changes in tissue structure during the early stage of retinal diseases, a subjective interpretation and qualitative analysis of the pathological sections of retinal HE in diabetic animals is required for screening and evaluating the degree of diabetic retinopathy and drug efficacy. To develop an innovative method for screening and evaluating the degree of diabetic retinopathy and drug treatment based on artificial intelligence algorithms. Based on the change law of the early nerve fiber layer and the ganglion cells, we get disparate characteristics of the microscopic image of diabetes animal retina HE slices. Using image recognition and deep learning methods on these HE slices, we can identify the changes in the ganglion cells and nerve fiber layer for diagnosing early retinopathy and evaluated the therapeutic effect of the potential drugs. We conduct quantitative calculation per unit length of the nerve fiber layer and total area of the nerve fiber layer to identify biology significance of edema. Additionally, we also perform quantitative calculation with the number of unit area ganglion cells to identify the section in biology cell hyperplasia. Finally, we get the significance of quantitative calculation on the unit cell area to identify ganglion cell shriveling in biology. In addition to the evaluation of the disease degree and changes, we also obtained retinal HE sections after different drug interventions and evaluated the therapeutic effect of the drugs. This study presents a novel quantitative method for screening and evaluating of diabetic retinopathy and drug efficacy.

Effective automated pipeline for 3D reconstruction of synapses based on deep learning.

BACKGROUND: The locations and shapes of synapses are important in reconstructing connectomes and analyzing synaptic plasticity. However, current synapse detection and segmentation methods are still not adequate for accurately acquiring the synaptic connectivity, and they cannot effectively alleviate the burden of synapse validation. RESULTS: We propose a fully automated method that relies on deep learning to realize the 3D reconstruction of synapses in electron microscopy (EM) images. The proposed method consists of three main parts: (1) training and employing the faster region convolutional neural networks (R-CNN) algorithm to detect synapses, (2) using the z-continuity of synapses to reduce false positives, and (3) combining the Dijkstra algorithm with the GrabCut algorithm to obtain the segmentation of synaptic clefts. Experimental results were validated by manual tracking, and the effectiveness of our proposed method was demonstrated. The experimental results in anisotropic and isotropic EM volumes demonstrate the effectiveness of our algorithm, and the average precision of our detection (92.8% in anisotropy, 93.5% in isotropy) and segmentation (88.6% in anisotropy, 93.0% in isotropy) suggests that our method achieves state-of-the-art results. CONCLUSIONS: Our fully automated approach contributes to the development of neuroscience, providing neurologists with a rapid approach for obtaining rich synaptic statistics.

10-Qubit Entanglement and Parallel Logic Operations with a Superconducting Circuit.

Here we report on the production and tomography of genuinely entangled Greenberger-Horne-Zeilinger states with up to ten qubits connecting to a bus resonator in a superconducting circuit, where the resonator-mediated qubit-qubit interactions are used to controllably entangle multiple qubits and to operate on different pairs of qubits in parallel. The resulting 10-qubit density matrix is probed by quantum state tomography, with a fidelity of 0.668±0.025. Our results demonstrate the largest entanglement created so far in solid-state architectures and pave the way to large-scale quantum computation.

The cut-off value of tumor size and appropriate timing of follow-up for management of minimal EUS-suspected gastric gastrointestinal stromal tumors.

BACKGROUD: The detectable rate of minimal gastric GISTs has continuously increased. While the surveillance and management of GIST <2 cm have been deemed controversial or lack evidence-based approaches.  The aim of the current study is to propose a cut-off value of tumor size for treatment policy and the appropriate timing for endoscopic ultrasonography (EUS) follow-up in the minimal EUS-suspected gastric GIST patients. METHODS: A single-institution retrospective study was performed. 69 patients with EUS-suspected gastric GISTs were studied from November 2008 to March 2015. 69 patients with minimal gastric GISTs ≤2 cm diagnosed by EUS were followed for a mean period of 29 months (range, 12 to 70). An at least 20% increase of the maximal diameter of the tumors was set as a significant change. RESULTS: During follow-up, Of the 69 minimal EUS-suspected GISTs, 16 (23.2%) showed significant changes in size. 11 out of 69 GISTs (15.9%), 6 out of 43 GISTs (14.0%), 7 out of 30 GISTs (23.3%) showed significant changes in size, at 1 year, 2 years, and more than 3 years respectively. The receiver operating characteristic curve analysis showed that the tumor size cut-off was 9.5 mm. Only 4.7 and 3.7% of gastric EUS-suspected GISTs of <9.5 mm in size showed significant changes at 1 year and 2 years, while 9.5% at more than 3 years. 34.6, 31.3 and 55.6% of gastric EUS-suspected GISTs of ≥ 9.5 mm in size showed significant changes at 1 year, 2 years and more than 3 years. CONCLUSIONS: Minimal EUS-suspected GISTs, larger than 9.5 mm may be associated with significant progression. The patients with a ≥ 9.5 mm GIST should have a EUS 6-12months, while <9.5 mm GIST may have a EUS extended to every 2-3 years.

Lymph node ratio as an independent prognostic indicator in stage III colorectal cancer: especially for fewer than 12 lymph nodes examined.

Although nodal invasion represents one of the most powerful prognostic indicators in colorectal cancer (CRC), marked heterogeneity exists within stage III patients. Lymph node ratio (LNR) may offer more precise prognostication in stage III CRC. The aim of this study is to investigate the prognostic impact of LNR on survival in stage III CRC patients. We retrospectively reviewed the data of 288 consecutive patients who underwent radical resection for stage III CRC between January 2000 and December 2008 in the Gastrointestinal Surgery Department, Peking University People's Hospital. The patients were divided into three groups according to LNR quartiles: LNR < 0.167 (n=72), 0.167 ≤ LNR < 0.562 (n = 140), and LNR ≥ 0.562 (n=76). The association between overall survival (OS) and disease-free survival (DFS) and 11 variables including age, gender, tumor location, size, grade, histology, tumor (T) stage, number of metastatic LNs, and LNR was analyzed by multivariate analysis. Survival curves were plotted by the Kaplan-Meier method. Both LNR and the number of metastatic LNs were significant prognostic factors for 5-year DFS and OS in stage III CRC patients. LNR was an independent prognostic factor for 5-year OS. LNR remained an independent prognostic factor in patients with fewer than 12 lymph nodes examined. LNR was a potent independent prognostic predictor for OS and DFS in stage III CRC patients, especially for patients with fewer than 12 lymph nodes examined.

Treating asthma patients with probiotics: a systematic review and meta-analysis.

Introduction: Objective: To evaluate the role of probiotics in the treatment of asthma patients by meta-analysis. Methods: PubMed, Embase, The Cochrane Library, Web of Science, and other databases were searched by computer, and the relevant literature on the treatment of asthma by probiotics that met the inclusion criteria was screened by manual retrieval. Meta-analysis was performed using Revman 5.4 software and the combined effect was evaluated by odds ratio (OR) or mean difference (MD) and 95 % confidence interval (CI). Results: a total of ten references were included, all of which were randomized controlled studies, and a total of 1,101 people were investigated. Fractional exhaled nitric oxide (FeNO) (MD = -7.17, 95 % CI: -12.81, -1.54), asthma symptom severity (MD = -0.07, 95 % CI: -0.10, -0.04), Childhood Asthma Control Test (CACT) (MD = 2.26, 95 % CI: 1.14, 3.39), and the number of acute episodes of asthma (OR = 0.30, 95 % CI: 0.19, 0.47) in the probiotics group were better than those in the control group. There was no significant difference in forced expiratory volume in the first second (FEV1) (MD = 0.11, 95 % CI: -0.05, 0.26) and FEV1/FVC (%) (MD = 0.32, 95 % CI: -1.48, 2.12). Conclusion: the use of probiotics in patients with asthma can improve lung inflammation and asthma symptoms, reduce the number of asthma attacks, and have no effect on lung function.

Introducción: Objetivo: evaluar el papel de los probióticos en el tratamiento de pacientes con asma mediante metaanálisis. Métodos: se realizaron búsquedas informáticas en PubMed, Embase, The Cochrane Library, Web of Science y otras bases de datos, y se examinó la literatura relevante sobre el tratamiento del asma con probióticos que cumplía con los criterios de inclusión mediante recuperación manual. El metaanálisis se realizó con el software Revman 5.4 y el efecto combinado se evaluó mediante la razón de probabilidades (OR) o diferencia media (MD) y el intervalo de confianza (IC) del 95 %. Resultados: se incluyó un total de diez referencias, todas ellas estudios controlados aleatorios, y se investigó un total de 1.101 personas. El óxido nítrico exhalado (FeNO) (MD = -7,17, IC 95 %: -12,81, -1,54), la gravedad de los síntomas del asma (MD = -0,07, IC 95 %: -0,10, -0,04), la Prueba de Control del Asma (CACT-ACT) (MD = 2,26, IC 95 %: 1,14, 3,39) y el número de episodios agudos de asma (OR = 0,30, IC 95 %: 0,19, 0,47) en el grupo de probióticos fueron mejores que en el grupo de control. No hubo diferencia significativa en volumen espiratorio forzado en el primer segundo (FEV1) (DM = 0,11, IC 95 %: -0,05, 0,26) y FEV1/FVC (%) (DM = 0,32, IC 95 %: -1,48, 2,12). Conclusión: el uso de probióticos en pacientes con asma puede mejorar la inflamación pulmonar y los síntomas del asma, reducir el número de ataques de asma y no tener efecto sobre la función pulmonar.

A Rare Case of Pleomorphic Adenoma in the Internal Auditory Canal.

Pleomorphic adenoma is a common tumor of the salivary gland tumor, but it is rare in the ear. To the authors' knowledge, this patient is the first reported case of pleomorphic adenoma arising in the internal auditory canal. There have been few documents reporting the manifestations and the therapy strategy of this disease. This study clearly demonstrated the experience in treating pleomorphic adenoma, including the characteristics of the clinical manifestation, the key procedures of surgery, and key points of the diagnosis. The translabyrinthine approach under the microscope performed to remove this tumor is a good option for resecting this type of tumor.

Analysis of Etiology, Diagnosis, and Treatment Strategy and Efficacy of Pulsatile Tinnitus Caused by Abnormal Vascular Anatomy.

OBJECTIVE: To investigate the etiology, clinical characteristics, diagnosis, and treatment strategies and efficacy of pulsatile tinnitus (PT) caused by vascular anatomy abnormality. METHODS: The clinical data of 45 patients with PT in our hospital from 2012 to 2019 were collected and retrospectively analyzed. RESULTS: All 45 patients had vascular anatomical abnormalities. The patients were divided into 10 categories according to the different locations of vascular abnormalities: sigmoid sinus diverticulum (SSD), sigmoid sinus wall dehiscence (SSWD), SSWD with high jugular bulb, pure dilated mastoid emissary vein, aberrant internal carotid artery (ICA) in the middle ear, transverse-sigmoid sinus (TSS) transition stenosis, TSS transition stenosis with SSD, persistent occipital sinus stenosis, petrous segment stenosis of ICA, and dural arteriovenous fistula. All patients complained of PT synchronous with heartbeat rhythm. Endovascular interventional therapy and extravascular open surgery were used according to the location of the vascular lesions. Tinnitus disappeared in 41 patients, was significantly relieved in 3 patients, and was unchanged in 1 patient postoperatively. Except for one patient with transient headache postoperatively, no obvious complications occurred. CONCLUSION: PT caused by vascular anatomy abnormalities can be identified by detailed medical history and physical and imaging examination. PT can be relieved or even completely alleviated after appropriate surgical treatments.

[FTIR spectral fitting algorithm based on continuous wavelet transform].

An FTIR spectrum fitting algorithm based on continuous wavelet transform is proposed. In calculating the factor of difference spectrum, the algorithm takes into account both the original spectrum and its continuous wavelet transformed spectra, which effectively overcomes the problem of reference peak selection and manual factor selection in most commercial software. The detailed discussions on wavelet scale, order and basis are included. The spectral fitting is performed on six wavelet basis functions and the obtained scale factor is used to quantify the content of liquor, and the corresponding mean absolute error ranges from 0.047 to 0.072, and the standard deviation ranges from 0.056 to 0.091. Experimental results show that the CWT combined with least squares fitting provides an accurate and reliable new method for FTIR spectral subtraction.

Regional Entrepreneurship, Business Environment, and High-Quality Economic Development: An Empirical Analysis of Nine Urban Agglomerations in China.

The article selects socioeconomic data related to 146 prefecture-level cities included in nine city clusters from 2014 to 2018 to establish a city-level socioeconomic system in China. A sensitivity analysis of regional entrepreneurship and economic quality development based on system dynamics was conducted to explore the changes in regional entrepreneurship and economic quality development over time and their sensitivity factors. In this way, the dynamic evolution mechanism of the system can be portrayed, and the optimization of the system can be achieved through the coordination of the factors within the system. The article sets up three scenarios to explore the fluctuations in regional entrepreneurship and economic quality development when three sensitive factors, namely, business environment, financial services scale, and innovation environment, change. Findings: There are differences in the development of cities within city clusters. The business environment and high-quality economic development of the central cities within the city cluster are stronger than those of the non-central cities. Therefore, regions should focus on synergistic development within city clusters when formulating related policies. The variation of regional entrepreneurship development and economic quality development, after a factor in the system is changed, is asymmetric. Because the sensitivity of different urban clusters and the way they are affected by sensitive factors varies, the state should pay more attention to the adaptability of cities when formulating corresponding policy measures and adapt its policy measures to the sensitivity characteristics of each region according to local conditions.

Deep residual contextual and subpixel convolution network for automated neuronal structure segmentation in micro-connectomics.

BACKGROUND AND OBJECTIVE: The goal of micro-connectomics research is to reconstruct the connectome and elucidate the mechanisms and functions of the nervous system via electron microscopy (EM). Due to the enormous variety of neuronal structures, neuron segmentation is among most difficult tasks in connectome reconstruction, and neuroanatomists desperately need a reliable neuronal structure segmentation method to reduce the burden of manual labeling and validation. METHODS: In this article, we proposed an effective deep learning method based on a deep residual contextual and subpixel convolution network to obtain the neuronal structure segmentation in anisotropic EM image stacks. Furthermore, lifted multicut is used for post-processing to optimize the prediction and obtain the reconstruction results. RESULTS: On the ISBI EM segmentation challenge, the proposed method ranks among the top of the leader board and yields a Rand score of 0.98788. On the public data set of mouse piriform cortex, it achieves a Rand score of 0.9562 and 0.9318 in the different testing stacks. The evaluation scores of our method are significantly improved when compared with those of state-of-the-art methods. CONCLUSIONS: The proposed automatic method contributes to the development of micro-connectomics, which improves the accuracy of neuronal structure segmentation and provides neuroanatomists with an effective approach to obtain the segmentation and reconstruction of neurons.

Aligned Organization of Synapses and Mitochondria in Auditory Hair Cells.

Recent studies have revealed great functional and structural heterogeneity in the ribbon-type synapses at the basolateral pole of the isopotential inner hair cell (IHC). This feature is believed to be critical for audition over a wide dynamic range, but whether the spatial gradient of ribbon morphology is fine-tuned in each IHC and how the mitochondrial network is organized to meet local energy demands of synaptic transmission remain unclear. By means of three-dimensional electron microscopy and artificial intelligence-based algorithms, we demonstrated the cell-wide structural quantification of ribbons and mitochondria in mature mid-cochlear IHCs of mice. We found that adjacent IHCs in staggered pairs differ substantially in cell body shape and ribbon morphology gradient as well as mitochondrial organization. Moreover, our analysis argues for a location-specific arrangement of correlated ribbon and mitochondrial function at the basolateral IHC pole.

Fear memory-associated synaptic and mitochondrial changes revealed by deep learning-based processing of electron microscopy data.

Serial section electron microscopy (ssEM) can provide comprehensive 3D ultrastructural information of the brain with exceptional computational cost. Targeted reconstruction of subcellular structures from ssEM datasets is less computationally demanding but still highly informative. We thus developed a region-CNN-based deep learning method to identify, segment, and reconstruct synapses and mitochondria to explore the structural plasticity of synapses and mitochondria in the auditory cortex of mice subjected to fear conditioning. Upon reconstructing over 135,000 mitochondria and 160,000 synapses, we find that fear conditioning significantly increases the number of mitochondria but decreases their size and promotes formation of multi-contact synapses, comprising a single axonal bouton and multiple postsynaptic sites from different dendrites. Modeling indicates that such multi-contact configuration increases the information storage capacity of new synapses by over 50%. With high accuracy and speed in reconstruction, our method yields structural and functional insight into cellular plasticity associated with fear learning.

Virus identification in electron microscopy images by residual mixed attention network.

BACKGROUND AND OBJECTIVE: Virus identification in electron microscopy (EM) images is considered as one of the front-line method in pathogen diagnosis and re-emerging infectious agents. However, the existing methods either focused on the detection of a single virus or required large amounts of manual labeling work to segment virus. In this work, we focus on the task of virus classification and propose an effective and simple method to identify different viruses. METHODS: We put forward a residual mixed attention network (RMAN) for virus classification. The proposed network uses channel attention, bottom-up and top-down attention, and incorporates a residual architecture in an end-to-end training manner, which is suitable for dealing with EM virus images and reducing the burden of manual annotation. RESULTS: We validate the proposed network through extensive experiments on a transmission electron microscopy virus image dataset. The top-1 error rate of our RMAN on 12 virus classes is 4.285%, which surpasses that of state-of-the-art networks and even human experts. In addition, the ablation study and the visualization of class activation mapping (CAM) further demonstrate the effectiveness of our method. CONCLUSIONS: The proposed automated method contributes to the development of medical virology, which provides virologists with a high-accuracy approach to recognize viruses as well as assist in the diagnosis of viruses.