Transfer learning can enhance classification performance of a target domain with insufficient training data by utilizing knowledge relating to the target domain from source domain. Nowadays, it is ...common to see two or more source domains available for knowledge transfer, which can improve performance of learning tasks in the target domain. However, the classification performance of the target domain decreases due to mismatching of probability distribution. Recent studies have shown that deep learning can build deep structures by extracting more effective features to resist the mismatching. In this paper, we propose a new multi-source deep transfer neural network algorithm, MultiDTNN, based on convolutional neural network and multi-source transfer learning. In MultiDTNN, joint probability distribution adaptation (JPDA) is used for reducing the mismatching between source and target domains to enhance features transferability of the source domain in deep neural networks. Then, the convolutional neural network is trained by utilizing the datasets of each source and target domain to obtain a set of classifiers. Finally, the designed selection strategy selects classifier with the smallest classification error on the target domain from the set to assemble the MultiDTNN framework. The effectiveness of the proposed MultiDTNN is verified by comparing it with other state-of-the-art deep transfer learning on three datasets.
Gastrointestinal (GI) manifestations have been increasingly reported in patients with coronavirus disease 2019 (COVID-19). However, the roles of the GI tract in severe acute respiratory syndrome ...coronavirus 2 (SARS-CoV-2) infection are not fully understood. We investigated how the GI tract is involved in SARS-CoV-2 infection to elucidate the pathogenesis of COVID-19.
Our previously established nonhuman primate (NHP) model of COVID-19 was modified in this study to test our hypothesis. Rhesus monkeys were infected with an intragastric or intranasal challenge with SARS-CoV-2. Clinical signs were recorded after infection. Viral genomic RNA was quantified by quantitative reverse transcription polymerase chain reaction. Host responses to SARS-CoV-2 infection were evaluated by examining inflammatory cytokines, macrophages, histopathology, and mucin barrier integrity.
Intranasal inoculation with SARS-CoV-2 led to infections and pathologic changes not only in respiratory tissues but also in digestive tissues. Expectedly, intragastric inoculation with SARS-CoV-2 resulted in the productive infection of digestive tissues and inflammation in both the lung and digestive tissues. Inflammatory cytokines were induced by both types of inoculation with SARS-CoV-2, consistent with the increased expression of CD68. Immunohistochemistry and Alcian blue/periodic acid–Schiff staining showed decreased Ki67, increased cleaved caspase 3, and decreased numbers of mucin-containing goblet cells, suggesting that the inflammation induced by these 2 types of inoculation with SARS-CoV-2 impaired the GI barrier and caused severe infections.
Both intranasal and intragastric inoculation with SARS-CoV-2 caused pneumonia and GI dysfunction in our rhesus monkey model. Inflammatory cytokines are possible connections for the pathogenesis of SARS-CoV-2 between the respiratory and digestive systems.
Display omitted
All-aqueous emulsions exploit spontaneous liquid-liquid separation and due to their water-based nature are particular advantageous for the biocompatible storage and processing of biomacromolecules. ...However, the ultralow interfacial tensions characteristic of all-aqueous interfaces represent an inherent limitation to the use of thermally adsorbed particles to achieve emulsion stability. Here, we use protein nanofibrils to generate colloidosome-like two-dimensional crosslinked networks of nanostructures templated by all-aqueous emulsions, which we term fibrillosomes. We show that this approach not only allows us to operate below the thermal limit at ultra-low surface tensions but also yields structures that are stable even in the complete absence of an interface. Moreover, we show that the growth and multilayer deposition of fibrils allows us to control the thickness of the capsule shells. These results open up the possibility of stabilizing aqueous two-phase systems using natural proteins, and creating self-standing protein capsules without the requirement for three-phase emulsions or water/oil interfaces.
Mammographic density is a strong breast cancer risk factor and a major determinant of screening sensitivity. However, there is currently no validated estimation method for full-field digital ...mammography (FFDM).
The performance of three area-based approaches (BI-RADS, the semi-automated Cumulus, and the fully-automated ImageJ-based approach) and three fully-automated volumetric methods (Volpara, Quantra and single energy x-ray absorptiometry (SXA)) were assessed in 3168 FFDM images from 414 cases and 685 controls. Linear regression models were used to assess associations between breast cancer risk factors and density among controls, and logistic regression models to assess density-breast cancer risk associations, adjusting for age, body mass index (BMI) and reproductive variables.
Quantra and the ImageJ-based approach failed to produce readings for 4% and 11% of the participants. All six density assessment methods showed that percent density (PD) was inversely associated with age, BMI, being parous and postmenopausal at mammography. PD was positively associated with breast cancer for all methods, but with the increase in risk per standard deviation increment in PD being highest for Volpara (1.83; 95% CI: 1.51 to 2.21) and Cumulus (1.58; 1.33 to 1.88) and lower for the ImageJ-based method (1.45; 1.21 to 1.74), Quantra (1.40; 1.19 to 1.66) and SXA (1.37; 1.16 to 1.63). Women in the top PD quintile (or BI-RADS 4) had 8.26 (4.28 to 15.96), 3.94 (2.26 to 6.86), 3.38 (2.00 to 5.72), 2.99 (1.76 to 5.09), 2.55 (1.46 to 4.43) and 2.96 (0.50 to 17.5) times the risk of those in the bottom one (or BI-RADS 1), respectively, for Volpara, Quantra, Cumulus, SXA, ImageJ-based method, and BI-RADS (P for trend <0.0001 for all). The ImageJ-based method had a slightly higher ability to discriminate between cases and controls (area under the curve (AUC) for PD = 0.68, P = 0.05), and Quantra slightly lower (AUC = 0.63; P = 0.06), than Cumulus (AUC = 0.65).
Fully-automated methods are valid alternatives to the labour-intensive "gold standard" Cumulus for quantifying density in FFDM. The choice of a particular method will depend on the aims and setting but the same approach will be required for longitudinal density assessments.
Abstract
The recently emerged Omicron (B.1.1.529) variant has rapidly surpassed Delta to become the predominant circulating SARS-CoV-2 variant, given the higher transmissibility rate and immune ...escape ability, resulting in breakthrough infections in vaccinated individuals. A new generation of SARS-CoV-2 vaccines targeting the Omicron variant are urgently needed. Here, we developed a subunit vaccine named RBD-HR/trimer by directly linking the sequence of RBD derived from the Delta variant (containing L452R and T478K) and HR1 and HR2 in SARS-CoV-2 S2 subunit in a tandem manner, which can self-assemble into a trimer. In multiple animal models, vaccination of RBD-HR/trimer formulated with MF59-like oil-in-water adjuvant elicited sustained humoral immune response with high levels of broad-spectrum neutralizing antibodies against Omicron variants, also inducing a strong T cell immune response in vivo. In addition, our RBD-HR/trimer vaccine showed a strong boosting effect against Omicron variants after two doses of mRNA vaccines, featuring its capacity to be used in a prime-boost regimen. In mice and non-human primates, RBD-HR/trimer vaccination could confer a complete protection against live virus challenge of Omicron and Delta variants. The results qualified RBD-HR/trimer vaccine as a promising next-generation vaccine candidate for prevention of SARS-CoV-2, which deserved further evaluation in clinical trials.
Since severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) became a pandemic event in the world, it has not only caused huge economic losses, but also a serious threat to global public ...health. Many scientific questions about SARS-CoV-2 and Coronavirus disease (COVID-19) were raised and urgently need to be answered, including the susceptibility of animals to SARS-CoV-2 infection. Here we tested whether tree shrew, an emerging experimental animal domesticated from wild animal, is susceptible to SARS-CoV-2 infection. No clinical signs were observed in SARS-CoV-2 inoculated tree shrews during this experiment except the increasing body temperature particularly in female animals. Low levels of virus shedding and replication in tissues occurred in all three age groups. Notably, young tree shrews (6 months to 12 months) showed virus shedding at the earlier stage of infection than adult (2 years to 4 years) and old (5 years to 7 years) animals that had longer duration of virus shedding comparatively. Histopathological examine revealed that pulmonary abnormalities were the main changes but mild although slight lesions were also observed in other tissues. In summary, tree shrew is less susceptible to SARS-CoV-2 infection compared with the reported animal models and may not be a suitable animal for COVID-19 related researches. However, tree shrew may be a potential intermediate host of SARS-CoV-2 as an asymptomatic carrier.
Close to half (45.4%) of the 2.3 million breast cancers (BC) diagnosed in 2020 were from Asia. While the burden of breast cancer has been examined at the level of broad geographic regions, literature ...on more in-depth coverage of the individual countries and subregions of the Asian continent is lacking. This narrative review examines the breast cancer burden in 47 Asian countries. Breast cancer screening guidelines and risk-based screening initiatives are discussed.
Tamoxifen treatment is associated with a reduction in mammographic density and an improved survival. However, the extent to which change in mammographic density during adjuvant tamoxifen therapy can ...be used to measure response to treatment is unknown.
Overall, 974 postmenopausal patients with breast cancer who had both a baseline and a follow-up mammogram were eligible for analysis. On the basis of treatment information abstracted from medical records, 474 patients received tamoxifen treatment and 500 did not. Mammographic density was measured by using an automated thresholding method and expressed as absolute dense area. Change in mammographic density was calculated as percentage change from baseline. Survival analysis was performed by using delayed-entry Cox proportional hazards regression models, with death as a result of breast cancer as the end point. Analyses were adjusted for a range of patient and tumor characteristics.
During a 15-year follow-up, 121 patients (12.4%) died from breast cancer. Women treated with tamoxifen who experienced a relative density reduction of more than 20% between baseline and first follow-up mammogram had a reduced risk of death as a result of breast cancer of 50% (hazard ratio, 0.50; 95% CI, 0.27 to 0.93) compared with women with stable mammographic density. In the no-tamoxifen group, there was no statistically significant association between mammographic density change and survival. The survival advantage was not observed when absolute dense areas at baseline or follow-up were evaluated separately.
A decrease in mammographic density after breast cancer diagnosis appears to serve as a prognostic marker for improved long-term survival in patients receiving adjuvant tamoxifen, and these data should be externally validated.
Wireless communication has changed and improved people's lives and society, especially with the arrival of the Internet of Things (IoT) era. Despite the maturity of wireless communication, the ...security issue of communication remains the most stubborn and troublesome problem due to the increasingly complex and large amounts of data. An intrusion detection system is the guarantee of secure communication. However, variable protocols and drastic growth in data volume make intrusion detection a difficult task. In this paper, we proposed a framework of anomaly-based network intrusion detection system to finish the detection job. First, UNSW-NB15 is selected as the research object. Based on this new dataset, we built a detection model combining a deep learning method and a shallow learning approach. The former one is a deep auto-encoder used for feature learning, which can discover important representations of data and accelerate detection. The latter one is a powerful support vector machine (SVM), where the artificial bee colony (ABC) algorithm is used to find optimal parameters for SVM with five-fold cross validation (5FCV). Various experiments are conducted and the simulation results prove that the proposed method performs quite better than some of state-of-the-art intrusion detection approaches, including the method based on the principal component analysis (PCA) and some other machine learning strategies.
With the exponential increase in malware, homology analysis has become a hot research topic in the malware detection field. This paper proposes MHAS, a malware homology analysis system based on ...ensemble learning and multifeatures. MHAS generates grayscale images from malware binary files and then uses the opcode tool IDA Pro to extract opcode sequences and system call graphs. Thus, RGB images and M-images are generated on the image matrix. Then, MHAS uses convolutional neural networks (CNNs) as base learners to perform bagging ensemble learning to learn features from the grayscale images, RGB images and M-images. Next, MHAS integrates the nine base learners using voting, learning and selective ensemble (in that order) and maps the integration results to the result matrix. Finally, the result matrix is again integrated using the learning method to obtain the final malware classification result. To verify the accuracy of MHAS, we performed a malware family classification experiment, that included samples of 10 malware families. The results showed that MHAS can reach an accuracy rate of 99.17%, meaning that it can effectively analyze and identify malware families.