Abstract ：

Nowadays, the pneumonia has widely spread around the world. CT images, as a mostly used means to detect pneumonia, take a long time to read manually by radiologists. Instead, automatic medical image segmentation technology can segment the lesion in a few seconds. Considering the difficulties in segmentation of pneumonia lesion, such as the extreme variations in the morphology of the lesions with noisy background, in this paper, we propose an accurate and efficient lesion segmentation algorithm, Adversarial Residual U2Net (ARes-U2Net) for COVID-19 infection segmentation. The model is comprised of two parts: segmented network (S) and critic network (C), which are trained alternately with minimizing and maximizing a multi-scale L1 function respectively. The segmented network (S) has U-shaped structure with residual connections, which extracts the multi-scale feature information. The critic network (C) can evaluate the multi-scale output of the segmented network by FCN layers. In the experiments, we designed intra-dataset and cross-dataset scenario experiments on a new dataset and four public datasets. The Dice Score, IoU, spec and prec of our proposed model are 64.99%, 54.59%, 99.77% and 76.73% on the constructed dataset, which significantly outperform other compared methods. The consistent results can also be derived for cross-data scenarios. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Keyword ：

Image segmentation Deep learning COVID-19 Medical imaging Network layers Computerized tomography

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Automated recognition of pneumonia from chest CT plays an important role in the subsequent clinical treatment for patients. While a few pioneering works only focus on several random slices from chest CT image, thus they have ignored the anatomical dependency information of local lesions. Considering it, this paper explores a novel automatic classification method for pneumonia detection based on fusing regional and global information, which not only improves detection performance, but also provides explainable diagnostic basis for radiologists. Firstly, identifying the interested local region by a lesion detection module, then we extracts the correlation relationship between local regions through a graph attention module. The image-level classification results can be acquired by fusing the information of global and local region. To realize the detection of full CT sequence, a person-level classifier is designed in the proposed model. In the experiment, we collected 781 chest CT sequences in total corresponding to 274 cases of viral pneumonia patients, 285 cases of bacterial pneumonia patients and 222 cases of healthy people. The experimental results show that our model achieves the accuracy of 95.5%, with 95.6% precision and 0.991 AUC. The recall and F1 score are 95.8% and 95.7% respectively, which outperformed previous works. Therefore, our method can be regarded as an efficient assisted tool in the diagnose of pneumonia. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

Keyword ：

Computerized tomography Patient treatment Diagnosis Classification (of information)

Cite：

Copy from the list or Export to your reference management。

Abstract ：

COVID-19 is a global pandemic that has caused significant global, social, and economic disruption. To effectively assist in screening and monitoring diagnosed cases, it is crucial to accurately segment lesions from Computer Tomography (CT) scans. Due to the lack of labeled data and the presence of redundant parameters in 3D CT, there are still significant challenges in diagnosing COVID-19 in related fields. To address the problem, we have developed a new model called the Cascaded 3D Dilated convolutional neural network (CD-Net) for directly processing CT volume data. To reduce memory consumption when cutting volume data into small patches, we initially design a cascade architecture in CD-Net to preserve global information. Then, we construct a Multi-scale Parallel Dilated Convolution (MPDC) block to aggregate features of different sizes and simultaneously reduce the parameters. Moreover, to alleviate the shortage of labeled data, we employ classical transfer learning, which requires only a small amount of data while achieving better performance. Experimental results conducted on the different public-available datasets verify that the proposed CD-Net has reduced the negative–positive ratio and outperformed other existing segmentation methods while requiring less data. © 2024 Elsevier Ltd

Keyword ：

Transfer learning Convolutional neural networks Computerized tomography Cutting Convolution

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Pneumonia diagnosis based on CT scans is crucial for the effective treatment. Existing deep leanring-based methods mainly focus on the global struction of the whole lung organs, while ignore the information of local detailed lesions. This can easily lead to errors in pneumonia decisions and a decline in classification accuracy. Actully, the diagnosis process of specialists in practice involves basically two steps glancing the whole lung organs to capture global information (global view) and gazing at local regions for observing detailed lesion (local view). To mimic this behaviour, we propose a multi-view information fusion network for pneumonia diagnosis from full sequence CTs. First, we design a multi-view information fusion network to extract spatial features from lung CT slices from global and local perspectives. Then, a recursive neural network (RNN) is utilized to solve the problem of dependency between slices and the continuity of lesions. Extensive experiments on real-world datasets are conducted and the results demonstrate the effectiveness of our proposed method. © 2023 IEEE.

Keyword ：

Classification (of information) Image classification Computerized tomography Deep learning Medical imaging Information fusion Computer aided diagnosis Biological organs Neural networks

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Shiwei Longdanhua Granule (SWLDH) is a classic Tibetan medicine (TM) ranking in the top 20 Chinese patent medicines in prescription rate to treat respiratory diseases like pneumonia, acute and chronic tracheobronchitis, acute exacerbation of COPD and bronchial asthma in solution of inflammation, cough and phlegm obstruction in clinical practice. However, its systematic pharmacological mechanisms have not been elucidated yet. Here, we studied the therapeutic efficacy of SWLDH in treatment of acute respiratory diseases in BALB/c mice by comprehensive analysis of airway inflammation, oxidative stress, mucus hypersecretion, cough hypersensitivities and indicators associated with the development of chronic diseases. Our results show that SWLDH might exhibit its inhibitory effects on pulmonary inflammation by interference with arachidonic acid (AA) metabolism pathways. Oxidative stress that highly related to the degree of tissue injury could be alleviated by enhancing the reductive activities of glutathione redox system, thioredoxin system and the catalytic activities of catalase and superoxide dismutase (SOD) after SWLDH treatment. In addition, SWLDH could significantly abrogate the mucus hypersecretion induced bronchiole obstruction by inactivate the globlet cells and decrease the secretion of gelforming mucins (MUC5AC and MUC5B) under pathological condition, demonstrating its mucoactive potency. SWLDH also showed reversed effects on the release of neuropeptides that are responsible for airway sensory hypersensitivity. Simultaneously observed inhibition of calcium influx, reduction in in vivo biosynthesis of acetylcholine and the recovery of the content of cyclic adenosine monophosphate (cAMP) might collaboratively contribute to cause airway smooth muscle cells (ASMCs) relexation. These findings indicated that SWLDH might exhibited antitussive potency via suppression of the urge to cough and ASMCs contraction. Moreover, SWLDH might affect airway remodeling. We found SWLDH could retard the elevation of TGF-beta 1 and alpha-SMA, which are important indicators for hyperplasia and contraction during the progression of the chronic airway inflammatory diseases like COPD and asthma.

Keyword ：

Oxidative stress Airway contraction Mucin hypersecretion Neurogenic inflammation Pulmonary inflammation

Cite：

Copy from the list or Export to your reference management。

Abstract ：

COVID-19 has been rapidly spreading worldwide and infected more than 1 million people with over 690k deaths reported. It is urgent and crucial to identify COVID-19-infected patients by computed tomography (CT) accurately and rapidly. However, we found that two problems, weak supervision and lack of interpretability, hindered its development. To address these challenges, we propose an attention-based multi-flow network for COVID-19 classification and lesion localization from chest CT. In the proposed model, we built a Resnet-based multi-flow network to learn the local information and the longitudinal information from the full chest sequence slice. To assist doctors in decision-making, the attention mechanism integrated into the network, which can locate the key slices and key parts from a full chest CT sequence of patients. We have systematically evaluated our method on the CT images of 1031 cases, including 420 COVID-19 cases, 311CAP cases, and 300 non-pneumonia cases. Our method could obtain an average accuracy of 82.3%, with 85.7% sensitivity and 86.4 % specificity, which outperformed previous works. © 2022 IEEE.

Keyword ：

Decision making COVID-19 Computerized tomography Deep learning Behavioral research

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Background Evidence supporting corticosteroids adjunctive treatment (CAT) for Pneumocystis jirovecii pneumonia (PCP) in non-HIV patients is highly controversial. We aimed to systematically review the literature and perform a meta-analysis of available data relating to the effect of CAT on mortality of PCP in non-HIV patients. Methods We searched Pubmed, Medline, Embase, and Cochrane database from 1989 through 2019. Data on clinical outcomes from non-HIV PCP were extracted with a standardized instrument. Heterogeneity was assessed with the I-2 index. Pooled odds ratios and 95% confidence interval were calculated using a fixed effects model. We analyzed the impact of CAT on mortality of non-HIV PCP in the whole PCP population, those who had hypoxemia (PaO2 < 70 mmHg) and who had respiratory failure (PaO2 < 60 mmHg). Results In total, 259 articles were identified, and 2518 cases from 16 retrospective observational studies were included. In all non-HIV PCP cases included, there was an association between CAT and increased mortality (odds ratio, 1.37; 95% confidence interval 1.07-1.75; P = 0.01). CAT showed a probable benefit of decreasing mortality in hypoxemic non-HIV PCP patients (odds ratio, 0.69; 95% confidence interval 0.47-1.01; P = 0.05). Furthermore, in a subgroup analysis, CAT showed a significantly lower mortality in non-HIV PCP patients with respiratory failure compared to no CAT (odds ratio, 0.63; 95% confidence interval 0.41-0.95; P = 0.03). Conclusions Our meta-analysis suggests that among non-HIV PCP patients with respiratory failure, CAT use may be associated with better clinical outcomes, and it may be associated with increased mortality in unselected non-HIV PCP population. Clinical trials are needed to compare CAT vs no-CAT in non-HIV PCP patients with respiratory failure. Furthermore, CAT use should be withheld in non-HIV PCP patients without hypoxemia.

Keyword ：

Non-HIV Respiratory failure Corticosteroids adjunctive treatment (CAT) Pneumocystis pneumonia (PCP)

Cite：

Copy from the list or Export to your reference management。

Abstract ：

New influenza A viruses that emerge frequently elicit composite inflammatory responses to both infection and structural damage of alveolar-capillary barrier cells that hinders regeneration of respiratory function. The host factors that relinquish restoration of lung health to enduring lung injury are insufficiently understood. Here, we investigated the role of endophilin B2 (B2) in susceptibility to severe influenza infection. WT and B2-deficient mice were infected with H1N1 PR8 by intranasal administration and course of influenza pneumonia, inflammatory, and tissue responses were monitored over time. Disruption of B2 enhanced recovery from severe influenza infection as indicated by swift body weight recovery and significantly better survival of endophilin B2-deficient mice compared to WT mice. Compared to WT mice, the B2-deficient lungs exhibited induction of genes that express surfactant proteins, ABCA3, GM-CSF, podoplanin, and caveolin mRNA after 7 days, temporal induction of CCAAT/ enhancer binding protein CEBP alpha, beta, and delta mRNAs 3-14 days after infection, and differences in alveolar extracellular matrix integrity and respiratory mechanics. Flow cytometry and gene expression studies demonstrated robust recovery of alveolar macrophages and recruitment of CD4+ lymphocytes in B2-deficient lungs. Targeting of endophilin B2 alleviates adverse effects of IAV infection on respiratory and immune cells enabling restoration of alveolar homeostasis.

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Background: Viral and atypical bacterial pathogens play an important role in respiratory tract infection. Using the Pneumoslide IgM test, the presented study explored the aetiology of community-acquired pneumonia and investigated further whether there was an association between age or season and aetiological organisms. Methods: Serum samples, taken between August 2011 and August 2013, from patients with CAP were tested with the Pneumoslide IgM kit. The Pneumoslide IgM technology can simultaneously diagnose 9 viral and atypical bacterial pathogens: Legionella pneumophila serogroup 1 (LP1), Mycoplasma pneumoniae (MP), Coxiella burnetii (COX), Chlamydophila pneumonia (CP), Adenovirus (ADV), Respiratory syncytial virus (RSV), Influenza A (INFA), Influenza B (INFB), Parainfluenza 1, 2 and 3 (PIVs). The data was analyzed by using Statistical Package for the Social Sciences for Windows (SPSS, version 11.0). Results: Of a total of 1204 serum samples tested, 624 samples were positive. M. pneumoniae was the dominant pathogen, with INFB, PIVs, and RSV ranking second to fourth, respectively. The positive percentages of MP, INFB, PIVs and RSV were found to be associated with age, especially MP, INFB and PIVs. The positive percentages of MP, PIVs and RSV were also found to be associated with season. The positive percentage of MP in autumn was the highest. The positive percentages of LP1 in August and September, ADV in June and INFB in March were relatively higher than that in other months. Conclusions: The results show there were 4 main viral and atypical bacterial pathogens causing CAP in our study. Some pathogens were found to be associated with age and season. M. pneumoniae was the most predominant pathogen among these 9 pathogens. It is necessary to take preventative measures in order to prevent the spread of these pathogens in susceptible age groups during peak season.

Keyword ：

Community-acquired pneumonia Aetiology M. pneumoniae Pneumoslide IgM

Cite：

Copy from the list or Export to your reference management。

Abstract ：

Object: To develop a typing method for Staphylococcal hemolysin genes, and to research on the distribution of hemolysin phenotype and hemolysin genes in Staphylococcus aureus isolates obtained from milk of cow suffered mastitis and to analysis there relevance. Methods: The hemolysin pheno-type was oberserved with the method of 5% blood plate. Hemolysin genes were assessed via polymerase chain reaction. Results: The typing method for Staphylococccal hemolysin phenotype and genes with PCR was developed. The isolates with α- hemolysis are 56 in 129 isolates, account for 43.4%; 43 show beta-hemolysis, account for 34.11%; Another 29 isolates showed no hemolysis phenotype, and it account for 22.48%. The isolates with hla gene account for 34.88%, hlb gene account for 42.60%.Conclusion: In the hemolytic phenotype, α- hemolysis are more than beta-hemolysis, however the hlb gene detection rate is higher than the hla gene. The distribution of hemolysin phenotype and hemolysin genes is not a corresponding relationship of Staphylococcus aureus isolates from raw milk of cow. The study can provide a basis for prevention and treatment of mastitis in dairy cows caused by Staphylococcus aureus. Staphylococcus aureus can cause a range of illnesses from minor skin infections, such as pimples, impetigo (may also be caused by Streptococcus pyogenes), cellulitis fol-liculitis, carbuncles, scalded skin syndrome and abscesses, to life-threatening diseases such as pneumonia, meningitis, osteomyelitis, endocarditis, toxic shock syndrome (TSS), bacteremia and sepsis, it can also cause bovine's mastitis. S. aureus have many virulence factors, such as hemolysin toxins, Panton-Valentine leukocidin (PVL), coagulase, DNAse, and many enterotoxins. S. aureus not only threat to dairy cattle health, but also endangere the safty of milk categories of food.

Keyword ：

Genetype distribution; Hemolysin phenotype; Mastitis; Staphylococcus aureus

Cite：

Copy from the list or Export to your reference management。