Improved hypertensive stroke classification based on multi-scale feature fusion of head axial CT angiogram and multimodal learning.

PURPOSE: Strokes are severe cardiovascular and circulatory diseases with two main types: ischemic and hemorrhagic. Clinically, brain images such as computed tomography (CT) and computed tomography angiography (CTA) are widely used to recognize stroke types. However, few studies have combined imaging and clinical data to classify stroke or consider a factor as an Independent etiology. METHODS: In this work, we propose a classification model that automatically distinguishes stroke types with hypertension as an independent etiology based on brain imaging and clinical data. We first present a preprocessing workflow for head axial CT angiograms, including noise reduction and feature enhancement of the images, followed by an extraction of regions of interest. Next, we develop a multi-scale feature fusion model that combines the location information of position features and the semantic information of deep features. Furthermore, we integrate brain imaging with clinical information through a multimodal learning model to achieve more reliable results. RESULTS: Experimental results show our proposed models outperform state-of-the-art models on real imaging and clinical data, which reveals the potential of multimodal learning in brain disease diagnosis. CONCLUSION: The proposed methodologies can be extended to create AI-driven diagnostic assistance technology for categorizing strokes.

Evaluation of immunogenicity and protective efficacy of the outer membrane porin F (OprF) against Pseudomonas plecoglossicida in large yellow croaker (Larimichthys crocea).

Large yellow croaker (Larimichthys crocea) farming dominates the marine aquaculture industry in China. However, the epidemic outbreaks of visceral white nodules disease (VWND), caused by bacterial pathogen Pseudomonas plecoglossicida, have emerged as a significant concern within the large yellow croaker industry. Although vaccination is considered to be an effective method for preventing and controlling P. plecoglossicida infection, there is currently no commercially available vaccine targeting this bacterium. In the present study, the outer membrane porin F (OprF) of P. plecoglossicida was characterized and revealed a high sequence similarity with that of other Pseudomonas species. The recombinant OprF protein (rOprF) produced in Escherichia coli was then evaluated for its immunogenicity and protective role against P. plecoglossicida in large yellow croaker. The rOprF was identified to have immunogenicity by Western blot using large yellow croaker anti-P. plecoglossicida sera. Additionally, the indirect immunofluorescence assay (IIFA) provided evidence indicating the surface exposure of OprF in P. plecoglossicida. Fish vaccinated twice via intraperitoneal (IP) injection with the purified rOprF combined with commercial adjuvant ISA 763A VG exhibited a relative percent survival (RPS) of 70.60% after challenge with virulent P. plecoglossicida strain through immersion. The administration of rOprF resulted in a notable increase in specific serum antibody levels and serum lysozyme activity compared to the control groups. The immune-related genes in the spleen and head kidney of rOprF-vaccinated fish were remarkably upregulated compared with the PBS-vaccinated sham group after the P. plecoglossicida challenge. In summary, the findings of this study suggest that rOprF exhibits considerable potential in inducing a robust immune response, making it a viable candidate for vaccination against P. plecoglossicida infection in large yellow croaker.

Comparative secretome analysis reveals cross-talk between type III secretion system and flagella assembly in Pseudomonas plecoglossicida.

The Gram-negative bacterium Pseudomonas plecoglossicida has caused visceral granulomas disease in several farmed fish species, including large yellow croaker (Larimichthys crocea), which results in severe economic losses. Type III secretion systems (T3SS) are protein secretion and translocation nanomachines widely employed by many Gram-negative bacterial pathogens for infection and pathogenicity. However, the exact role of T3SS in the pathogenesis of P. plecoglossicida infection is still unclear. In this study, a T3SS translocators deletion strain (△popBD) of P. plecoglossicida was constructed to investigate the function of T3SS. Then comparative secretome analysis of the P. plecoglossicida wild-type (WT) and △popBD mutant strains was conducted by label-free quantitation (LFQ) mass spectrometry. The results show that knockout of T3SS translocators popB and popD has an adverse effect on the effector protein ExoU secretion, flagella assembly, and biofilm formation. Further experimental validations also confirmed that popB-popD deletion could affect the P. plecoglossicida flagella morphology/formation, adherence, mobility, and biofilm formation. These data indicate that a cross-talk exists between the P. plecoglossicida T3SS and the flagella system. Our results, therefore, will facilitate the further under-standing of the pathogenic mechanisms leading to visceral granulomas disease caused by P. plecoglossicida.

Study of efficacy and antibody duration to fourth-dose booster of Ad5-nCoV or inactivated SARS-CoV-2 vaccine in Chinese adults: a prospective cohort study.

Introduction: China experienced a record surge of coronavirus disease 2019 cases in December 2022, during the pandemic. Methods: We conducted a randomized, parallel-controlled prospective cohort study to evaluate efficacy and antibody duration after a fourth-dose booster with Ad5-nCoV or inactivated severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccine. Results: A total of 191 participants aged ≥18 years who had completed a three-dose regimen of the inactivated SARS-CoV-2 vaccine 6 months earlier were recruited to receive the intramuscular Ad5-nCoV booster or the inactivated SARS-CoV-2 vaccine. The Ad5-nCoV group had significantly higher antibody levels compared with the inactivated vaccine group at 6 months after the fourth vaccination dose. After the pandemic, the breakthrough infection rate for the Ad5-nCoV and the inactivated vaccine groups was 77.89% and 78.13%, respectively. Survival curve analysis (p = 0.872) and multivariable logistic regression analysis (p = 0.956) showed no statistically significant differences in breakthrough infection between the two groups. Discussion: Compared with a homologous fourth dose, a heterologous fourth dose of Ad5-nCoV elicited a higher immunogenic response in healthy adults who had been immunized with three doses of inactivated vaccine. Nevertheless, the efficacy of the two vaccine types was equivalent after the pandemic.

Safety and immunogenicity of Ad5-nCoV immunization after three-dose priming with inactivated SARS-CoV-2 vaccine in Chinese adults.

Data on the safety and immunity of a heterologous booster (fourth dose) after three-doses of inactivated SARS-CoV-2 vaccine in Chinese adults are limited. We evaluate the safety and immunogenicity of Ad5-nCoV in a randomized, double-blind, parallel-controlled phase 4 clinical trial in Zhejiang, China (NCT05373030). Participants aged 18-80 years (100 per group), administered three doses of inactivated SARS-CoV-2 vaccine ≥6 months earlier, are enrolled and randomized 1:1 into two groups, which are administered intramuscular Ad5-nCoV or inactivated SARS-CoV-2 vaccine (CoronaVac or Covilo). All observed adverse reactions are predictable and manageable. Ad5-nCoV elicits significantly higher RBD-specific IgG levels, with a geometric mean concentration of 2924.0 on day 14 post-booster, 7.8-fold that of the inactivated vaccine. Pseudovirus-neutralizing antibodies to Omicron BA.4/5 show a similar pattern, with geometric mean titers of 228.9 in Ad5-nCoV group and 65.5 in inactivated vaccine group. Ad5-nCoV booster maintains high antibody levels on day 90, with seroconversion of 71.4%, while that of inactivated vaccine is 5.2%, almost pre-booster levels. A fourth Ad5-nCoV vaccination following three-doses of inactivated SARS-CoV-2 vaccine is immunogenic, tolerable, and more efficient than inactivated SARS-CoV-2 vaccine. Ad5-nCoV elicits a stronger humoral response against Omicron BA.4/5 and maintains antibody levels for longer than homologous boosting.

Megalocytivirus and Other Members of the Family Iridoviridae in Finfish: A Review of the Etiology, Epidemiology, Diagnosis, Prevention and Control.

Aquaculture has expanded to become the fastest growing food-producing sector in the world. However, its expansion has come under threat due to an increase in diseases caused by pathogens such as iridoviruses commonly found in aquatic environments used for fish farming. Of the seven members belonging to the family Iridoviridae, the three genera causing diseases in fish comprise ranaviruses, lymphocystiviruses and megalocytiviruses. These three genera are serious impediments to the expansion of global aquaculture because of their tropism for a wide range of farmed-fish species in which they cause high mortality. As economic losses caused by these iridoviruses in aquaculture continue to rise, the urgent need for effective control strategies increases. As a consequence, these viruses have attracted a lot of research interest in recent years. The functional role of some of the genes that form the structure of iridoviruses has not been elucidated. There is a lack of information on the predisposing factors leading to iridovirus infections in fish, an absence of information on the risk factors leading to disease outbreaks, and a lack of data on the chemical and physical properties of iridoviruses needed for the implementation of biosecurity control measures. Thus, the synopsis put forth herein provides an update of knowledge gathered from studies carried out so far aimed at addressing the aforesaid informational gaps. In summary, this review provides an update on the etiology of different iridoviruses infecting finfish and epidemiological factors leading to the occurrence of disease outbreaks. In addition, the review provides an update on the cell lines developed for virus isolation and culture, the diagnostic tools used for virus detection and characterization, the current advances in vaccine development and the use of biosecurity in the control of iridoviruses in aquaculture. Overall, we envision that the information put forth in this review will contribute to developing effective control strategies against iridovirus infections in aquaculture.

A self-training subspace clustering algorithm based on adaptive confidence for gene expression data.

Gene clustering is one of the important techniques to identify co-expressed gene groups from gene expression data, which provides a powerful tool for investigating functional relationships of genes in biological process. Self-training is a kind of important semi-supervised learning method and has exhibited good performance on gene clustering problem. However, the self-training process inevitably suffers from mislabeling, the accumulation of which will lead to the degradation of semi-supervised learning performance of gene expression data. To solve the problem, this paper proposes a self-training subspace clustering algorithm based on adaptive confidence for gene expression data (SSCAC), which combines the low-rank representation of gene expression data and adaptive adjustment of label confidence to better guide the partition of unlabeled data. The superiority of the proposed SSCAC algorithm is mainly reflected in the following aspects. 1) In order to improve the discriminative property of gene expression data, the low-rank representation with distance penalty is used to mine the potential subspace structure of data. 2) Considering the problem of mislabeling in self-training, a semi-supervised clustering objective function with label confidence is proposed, and a self-training subspace clustering framework is constructed on this basis. 3) In order to mitigate the negative impact of mislabeled data, an adaptive adjustment strategy based on gravitational search algorithm is proposed for label confidence. Compared with a variety of state-of-the-art unsupervised and semi-supervised learning algorithms, the SSCAC algorithm has demonstrated its superiority through extensive experiments on two benchmark gene expression datasets.

A diagnostic scoring model of ENKTCL in the nose-Waldeyer's ring based on logistic regression: Differential diagnosis from DLBCL.

Objective: To establish a logistic regression model based on CT and MRI imaging features and Epstein-Barr (EB) virus nucleic acid to develop a diagnostic score model to differentiate extranodal NK/T nasal type (ENKTCL) from diffuse large B cell lymphoma (DLBCL). Methods: This study population was obtained from two independent hospitals. A total of 89 patients with ENKTCL (n = 36) or DLBCL (n = 53) from January 2013 to May 2021 were analyzed retrospectively as the training cohort, and 61 patients (ENKTCL=27; DLBCL=34) from Jun 2021 to Dec 2022 were enrolled as the validation cohort. All patients underwent CT/MR enhanced examination and EB virus nucleic acid test within 2 weeks before surgery. Clinical features, imaging features and EB virus nucleic acid results were analyzed. Univariate analyses and multivariate logistic regression analyses were performed to identify independent predictors of ENKTCL and establish a predictive model. Independent predictors were weighted with scores based on regression coefficients. A receiver operating characteristic (ROC) curve was created to determine the diagnostic ability of the predictive model and score model. Results: We searched for significant clinical characteristics, imaging characteristics and EB virus nucleic acid and constructed the scoring system via multivariate logistic regression and converted regression coefficients to weighted scores. The independent predictors for ENKTCL diagnosis in multivariate logistic regression analysis, including site of disease (nose), edge of lesion (blurred), T2WI (high signal), gyrus like changes, EB virus nucleic acid (positive), and the weighted score of regression coefficient was 2, 3, 4, 3, 4 points. The ROC curves, AUCs and calibration tests were carried out to evaluate the scoring models in both the training cohort and the validation cohort. The AUC of the scoring model in the training cohort were 0.925 (95% CI, 0.906-0.990) and the cutoff point was 5 points. In the validation cohort, the AUC was 0.959 (95% CI, 0.915-1.000) and the cutoff value was 6 points. Four score ranges were as follows: 0-6 points for very low probability of ENKTCL, 7-9 points for low probability; 10-11 points for middle probability; 12-16 points for very high probability. Conclusion: The diagnostic score model of ENKTCL based on Logistic regression model which combined with imaging features and EB virus nucleic acid. The scoring system was convenient, practical and could significantly improve the diagnostic accuracy of ENKTCL and the differential diagnosis of ENKTCL from DLBCL.

Gamma distribution based predicting model for breast cancer drug response based on multi-layer feature selection.

In the pursuit of precision medicine for cancer, a promising step is to predict drug response based on data mining, which can provide clinical decision support for cancer patients. Although some machine learning methods for predicting drug response from genomic data already exist, most of them focus on point prediction, which cannot reveal the distribution of predicted results. In this paper, we propose a three-layer feature selection combined with a gamma distribution based GLM and a two-layer feature selection combined with an ANN. The two regression methods are applied to the Encyclopedia of Cancer Cell Lines (CCLE) and the Cancer Drug Sensitivity Genomics (GDSC) datasets. Using ten-fold cross-validation, our methods achieve higher accuracy on anticancer drug response prediction compared to existing methods, with an R 2 and RMSE of 0.87 and 0.53, respectively. Through data validation, the significance of assessing the reliability of predictions by predicting confidence intervals and its role in personalized medicine are illustrated. The correlation analysis of the genes selected from the three layers of features also shows the effectiveness of our proposed methods.

Effect of organophosphate esters on microbial community and proteomics in constructed wetlands and its removal mechanism.

Organophosphorus esters (OPEs) may cause potential risks to human health and ecological environment safety when they enter water. In this study, A lab-scale vertical flow constructed wetlands (VFCWs) exposed to dichlorvos (DDVP) was carried out to reveal removal effect and mechanism of DDVP in VFCWs. The findings indicated CWs can remove DDVP with 94%-95% average removal efficiency in long-term operation. Besides, soluble phosphate (SRP) and total phosphorus (TP) were removed by VFCWs with 48.60%-64.10% average removal efficiency, and the addition of DDVP enhanced the effect of CWs on nitrogen removal. High-throughput sequencing demonstrated that Massiilia (2.67%-18.06%), Denitratisoma (2.07%-3.80%) and SM1A02 (2.85%-4.67%) played an important role in the removal process of DDVP in VFCWs. Proteomics of plant root showed that A0A3B6ARQ4 (increased 29.53 times) and LOC_Os11g38050.1 protein (decreased 0.001 times) responsed more sensitive to OPEs which suggested DDVP enhancesenhancing plants energy production and hydrolyase synthesis, thereby promoting it hydrolysis. Therefore, the use of VFCWs to treat organic phosphate wastewater has future prospects.

Chicken or Porcine Aminopeptidase N Mediates Cellular Entry of Pseudoviruses Carrying Spike Glycoprotein from the Avian Deltacoronaviruses HKU11, HKU13, and HKU17.

Members of deltacoronavirus (DCoV) have mostly been identified in diverse avian species as natural reservoirs, though the porcine DCoV (PDCoV) is a major swine enteropathogenic virus with global spread. The important role of aminopeptidase N (APN) orthologues from various mammalian and avian species in PDCoV cellular entry and interspecies transmission has been revealed recently. In this study, comparative analysis indicated that three avian DCoVs, bulbul DCoV HKU11, munia DCoV HKU13, and sparrow DCoV HKU17 (Chinese strain), and PDCoV in the subgenera Buldecovirus are grouped together at whole-genome levels; however, the spike (S) glycoprotein and its S1 subunit of HKU17 are more closely related to night heron DCoV HKU19 in Herdecovirus. Nevertheless, the S1 protein of HKU11, HKU13, or HKU17 bound to or interacted with chicken APN (chAPN) or porcine APN (pAPN) by flow cytometry analysis of cell surface expression of APN and by coimmunoprecipitation in APN-overexpressing cells. Expression of chAPN or pAPN allowed entry of pseudotyped lentiviruses with the S proteins from HKU11, HKU13 and HKU17 into nonsusceptible cells and natural avian and porcine cells, which could be inhibited by the antibody against APN or anti-PDCoV-S1. APN knockdown by siRNA or knockout by CRISPR/Cas9 in chicken or swine cell lines significantly or almost completely blocked infection of these pseudoviruses. Hence, we demonstrate that HKU11, HKU13, and HKU17 with divergent S genes likely engage chAPN or pAPN to enter the cells, suggesting a potential interspecies transmission from wild birds to poultry and from birds to mammals by certain avian DCoVs. IMPORTANCE The receptor usage of avian deltacoronaviruses (DCoVs) has not been investigated thus far, though porcine deltacoronavirus (PDCoV) has been shown to utilize aminopeptidase N (APN) as a cell receptor. We report here that chicken or porcine APN also mediates cellular entry by three avian DCoV (HKU11, HKU13, and HKU17) spike pseudoviruses, and the S1 subunit of three avian DCoVs binds to APN in vitro and in the surface of avian and porcine cells. The results fill the gaps in knowledge about the avian DCoV receptor and elucidate important insights for the monitoring and prevention of potential interspecies transmission of certain avian DCoVs. In view of the diversity of DCoVs, whether this coronavirus genus will cause novel virus to emerge in other mammals from birds, are worthy of further surveillance and investigation.

Complete genome sequence and characterization of four Decapod iridescent virus 1 isolates from crab and shrimp.

Decapod iridescent virus 1 (DIV1) is an emerging viral pathogen that infects diverse freshwater and marine crustacean species and causes considerable economic losses that seriously threaten crustacean farming and has caused enormous financial losses in recent years. In this study, we detected DIV1 from diseased crabs, with clinical symptoms such as loss of vitality and white gill filaments with edema, in a Marsupenaeus japonicus and Portunus trituberculatus polyculture pond. Four DIV1 isolates from crab samples (two isolates) and shrimp samples (two isolates) were sequenced and assembled successfully. Molecular characterization and phylogenetic analysis of the four DIV1 isolates were conducted. The DIV1 isolates from crab samples have a close genetic relationship with shrimp DIV1s, indicating the viruses share the same ancestor with those from shrimps. Our study provides valuable insights into disease prevention and control of the shrimp-crab polyculture system.

Prediction of axillary lymph node pathological complete response to neoadjuvant therapy using nomogram and machine learning methods.

Purpose: To determine the feasibility of predicting the rate of an axillary lymph node pathological complete response (apCR) using nomogram and machine learning methods. Methods: A total of 247 patients with early breast cancer (eBC), who underwent neoadjuvant therapy (NAT) were included retrospectively. We compared pre- and post-NAT ultrasound information and calculated the maximum diameter change of the primary lesion (MDCPL): [(pre-NAT maximum diameter of primary lesion - post-NAT maximum diameter of preoperative primary lesion)/pre-NAT maximum diameter of primary lesion] and described the lymph node score (LNS) (1): unclear border (2), irregular morphology (3), absence of hilum (4), visible vascularity (5), cortical thickness, and (6) aspect ratio <2. Each description counted as 1 point. Logistic regression analyses were used to assess apCR independent predictors to create nomogram. The area under the curve (AUC) of the receiver operating characteristic curve as well as calibration curves were employed to assess the nomogram's performance. In machine learning, data were trained and validated by random forest (RF) following Pycharm software and five-fold cross-validation analysis. Results: The mean age of enrolled patients was 50.4 ± 10.2 years. MDCPL (odds ratio [OR], 1.013; 95% confidence interval [CI], 1.002-1.024; p=0.018), LNS changes (pre-NAT LNS - post-NAT LNS; OR, 2.790; 95% CI, 1.190-6.544; p=0.018), N stage (OR, 0.496; 95% CI, 0.269-0.915; p=0.025), and HER2 status (OR, 2.244; 95% CI, 1.147-4.392; p=0.018) were independent predictors of apCR. The AUCs of the nomogram were 0.74 (95% CI, 0.68-0.81) and 0.76 (95% CI, 0.63-0.90) for training and validation sets, respectively. In RF model, the maximum diameter of the primary lesion, axillary lymph node, and LNS in each cycle, estrogen receptor status, progesterone receptor status, HER2, Ki67, and T and N stages were included in the training set. The final validation set had an AUC value of 0.85 (95% CI, 0.74-0.87). Conclusion: Both nomogram and machine learning methods can predict apCR well. Nomogram is simple and practical, and shows high operability. Machine learning makes better use of a patient's clinicopathological information. These prediction models can assist surgeons in deciding on a reasonable strategy for axillary surgery.

Bile acids promote the caveolae-associated entry of swine acute diarrhea syndrome coronavirus in porcine intestinal enteroids.

Intestinal microbial metabolites have been increasingly recognized as important regulators of enteric viral infection. However, very little information is available about which specific microbiota-derived metabolites are crucial for swine enteric coronavirus (SECoV) infection in vivo. Using swine acute diarrhea syndrome (SADS)-CoV as a model, we were able to identify a greatly altered bile acid (BA) profile in the small intestine of infected piglets by untargeted metabolomic analysis. Using a newly established ex vivo model-the stem cell-derived porcine intestinal enteroid (PIE) culture-we demonstrated that certain BAs, cholic acid (CA) in particular, enhance SADS-CoV replication by acting on PIEs at the early phase of infection. We ruled out the possibility that CA exerts an augmenting effect on viral replication through classic farnesoid X receptor or Takeda G protein-coupled receptor 5 signaling, innate immune suppression or viral attachment. BA induced multiple cellular responses including rapid changes in caveolae-mediated endocytosis, endosomal acidification and dynamics of the endosomal/lysosomal system that are critical for SADS-CoV replication. Thus, our findings shed light on how SECoVs exploit microbiome-derived metabolite BAs to swiftly establish viral infection and accelerate replication within the intestinal microenvironment.

Chest L-Transformer: Local Features With Position Attention for Weakly Supervised Chest Radiograph Segmentation and Classification.

We consider the problem of weakly supervised segmentation on chest radiographs. The chest radiograph is the most common means of screening and diagnosing thoracic diseases. Weakly supervised deep learning models have gained increasing popularity in medical image segmentation. However, these models are not suitable for the critical characteristics presented in chest radiographs: the global symmetry of chest radiographs and dependencies between lesions and their positions. These models extract global features from the whole image to make the image-level decision. The global symmetry can lead these models to misclassification of symmetrical positions of the lesions. Thoracic diseases often have special disease prone areas in chest radiographs. There is a relationship between the lesions and their positions. In this study, we propose a weakly supervised model, called Chest L-Transformer, to take these characteristics into account. Chest L-Transformer classifies an image based on local features to avoid the misclassification caused by the global symmetry. Moreover, associated with Transformer attention mechanism, Chest L-Transformer models the dependencies between the lesions and their positions and pays more attention to the disease prone areas. Chest L-Transformer is only trained with image-level annotations for lesion segmentation. Thus, Log-Sum-Exp voting and its variant are proposed to unify the pixel-level prediction with the image-level prediction. We demonstrate a significant segmentation performance improvement over the current state-of-the-art while achieving competitive classification performance.

Zn2+ Cross-Linked Alginate Carrying Hollow Silica Nanoparticles Loaded with RL-QN15 Peptides Provides Promising Treatment for Chronic Skin Wounds.

Chronic and non-healing wounds pose a great challenge to clinical management and patients. Many studies have explored novel interventions against skin wounds, with bioactive peptides, nanoparticles, and hydrogels arousing considerable attention regarding their therapeutic potential. In this study, the prohealing peptide RL-QN15 was loaded into hollow silica nanoparticles (HSNs), with these HSN@RL-QN15 nanocomposites then combined with zinc alginate (ZA) gels to obtain HSN@RL-QN15/ZA hydrogel. The characteristics, biological properties, and safety profiles of the hydrogel composites were then evaluated. Results showed that the hydrogel had good porosity, hemocompatibility, biocompatibility, and broad-spectrum antimicrobial activity, with the slow release of loaded RL-QN15. Further analysis indicated that the hydrogel promoted skin cell proliferation and keratinocyte scratch repair, regulated angiogenesis, reduced inflammation, and accelerated re-epithelialization and granulation tissue formation, resulting in the rapid healing of both full-thickness skin wounds and methicillin-resistant Staphylococcus aureus biofilm-infected chronic wounds in mice. This peptide-based hydrogel provides a novel intervention for the treatment of chronic skin wounds and shows promise as a wound dressing in the field of tissue regeneration.

BUSnet: A Deep Learning Model of Breast Tumor Lesion Detection for Ultrasound Images.

Ultrasound (US) imaging is a main modality for breast disease screening. Automatically detecting the lesions in US images is essential for developing the artificial-intelligence-based diagnostic support technologies. However, the intrinsic characteristics of ultrasound imaging, like speckle noise and acoustic shadow, always degenerate the detection accuracy. In this study, we developed a deep learning model called BUSnet to detect the breast tumor lesions in US images with high accuracy. We first developed a two-stage method including the unsupervised region proposal and bounding-box regression algorithms. Then, we proposed a post-processing method to enhance the detecting accuracy further. The proposed method was used to a benchmark dataset, which includes 487 benign samples and 210 malignant samples. The results proved the effectiveness and accuracy of the proposed method.

First evidence that an emerging mammalian alphacoronavirus is able to infect an avian species.

A novel swine enteric alphacoronavirus, swine acute diarrhoea syndrome coronavirus (SADS-CoV), related to Rhinolophus bat CoV HKU2 in the subgenus Rhinacovirus emerged in southern China in 2017, causing diarrhoea in newborn piglets, and critical questions remain about the pathogenicity, cross-species transmission and potential animal reservoirs. Our laboratory's previous research has shown that SADS-CoV can replicate in various cell types from different species, including chickens. Here, we systematically explore the susceptibility of chickens to a cell-adapted SADS-CoV strain both in vitro and in vivo. First, evidence of SADS-CoV replication in primary chicken cells, including cytopathic effects, immunofluorescence staining, growth curves and structural protein expression, was proven. Furthermore, we observed that SADS-CoV replicated in chicken embryos without causing gross lesions and that experimental infection of chicks resulted in mild respiratory symptoms. More importantly, SADS-CoV shedding and viral distribution in the lungs, spleens, small intestines and large intestines of infected chickens were confirmed by quantitative reverse transcription polymerase chain reaction and immunohistochemistry. The genomic sequence of the original SADS-CoV from the pig source sample in 2017 was determined to have nine nucleotide differences compared to the cell-adapted strain used; among these were three nonsynonymous mutations in the spike gene. These results collectively demonstrate that chickens are susceptible to SADS-CoV infection, suggesting that they are a potential animal reservoir. To our knowledge, this study provides the first experimental evidence of cross-species infection in which a mammalian alphacoronavirus is able to infect an avian species.