Multi-domain medical image translation generation for lung image classification based on generative adversarial networks.

OBJECTIVE: Lung image classification-assisted diagnosis has a large application market. Aiming at the problems of poor attention to existing translation models, the insufficient ability of key transfer and generation, insufficient quality of generated images, and lack of detailed features, this paper conducts research on lung medical image translation and lung image classification based on generative adversarial networks. METHODS: This paper proposes a medical image multi-domain translation algorithm MI-GAN based on the key migration branch. After the actual analysis of the imbalanced medical image data, the key target domain images are selected, the key migration branch is established, and a single generator is used to complete the medical image multi-domain translation. The conversion between domains ensures the attention performance of the medical image multi-domain translation model and the quality of the synthesized images. At the same time, a lung image classification model based on synthetic image data augmentation is proposed. The synthetic lung CT medical images and the original real medical images are used as the training set together to study the performance of the auxiliary diagnosis model in the classification of normal healthy subjects, and also of the mild and severe COVID-19 patients. RESULTS: Based on the chest CT image dataset, MI-GAN has completed the mutual conversion and generation of normal lung images without disease, viral pneumonia and Mild COVID-19 images. The synthetic images GAN-test and GAN-train indicators reached, respectively 92.188% and 85.069%, compared with other generative models in terms of authenticity and diversity, there is a considerable improvement. The accuracy rate of pneumonia diagnosis of the lung image classification model is 93.85%, which is 3.1% higher than that of the diagnosis model trained only with real images; the sensitivity of disease diagnosis is 96.69%, a relative improvement of 7.1%. 1%, the specificity was 89.70%; the area under the ROC curve (AUC) increased from 94.00% to 96.17%. CONCLUSION: In this paper, a multi-domain translation model of medical images based on the key transfer branch is proposed, which enables the translation network to have key transfer and attention performance. It is verified on lung CT images and achieved good results. The required medical images are synthesized by the above medical image translation model, and the effectiveness of the synthesized images on the lung image classification network is verified experimentally.

Classification of lungs infected COVID-19 images based on inception-ResNet.

OBJECTIVE: Nowadays, COVID-19 is spreading rapidly worldwide, and seriously threatening lives . From the perspective of security and economy, the effective control of COVID-19 has a profound impact on the entire society. An effective strategy is to diagnose earlier to prevent the spread of the disease and prompt treatment of severe cases to improve the chance of survival. METHODS: The method of this paper is as follows: Firstly, the collected data set is processed by chest film image processing, and the bone removal process is carried out in the rib subtraction module. Then, the set preprocessing method performed histogram equalization, sharpening, and other preprocessing operations on the chest film. Finally, shallow and high-level feature mapping through the backbone network extracts the processed chest radiographs. We implement the self-attention mechanism in Inception-Resnet, perform the standard classification, and identify chest radiograph diseases through the classifier to realize the auxiliary COVID-19 diagnosis process at the medical level, all in an effort to further enhance the classification performance of the convolutional neural network. Numerous computer simulations demonstrate that the Inception-Resnet convolutional neural network performs CT image categorization and enhancement with greater efficiency and flexibility than conventional segmentation techniques. RESULTS: The experimental COVID-19 CT dataset obtained in this paper is the new data for CT scans and medical imaging of normal, early COVID-19 patients and severe COVID-19 patients from Jinyintan hospital. The experiment plots the relationship between model accuracy, model loss and epoch, using ACC, TPR, SPE, F1 score and G-mean to measure the image maps of patients with and without the disease. Statistical measurement values are obtained by Inception-Resnet are 88.23%, 83.45%, 89.72%, 95.53% and 88.74%. The experimental results show that Inception-Resnet plays a more effective role than other image classification methods in evaluation indicators, and the method has higher robustness, accuracy and intuitiveness. CONCLUSION: With CT images in the clinical diagnosis of COVID-19 images being widely used and the number of applied samples continuously increasing, the method in this paper is expected to become an additional diagnostic tool that can effectively improve the diagnostic accuracy of clinical COVID-19 images.

Landscape of B Cell Receptor Repertoires in COVID-19 Patients Revealed Through CDR3 Sequencing of Immunoglobulin Heavy and Light Chains.

The outbreak and persistence of coronavirus disease 2019 (COVID-19) threaten human health. B cells play a vital role in fighting the infections caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Despite many studies on the immune responses in COVID-19 patients, it is still unclear how B cell receptor (BCR) constituents, including immunoglobulin heavy (IGHs) and light chains (IGLs), respond to SARS-CoV-2 in patients with varying symptoms. In this study, we conducted complementarity-determining region 3 (CDR3) sequencing of BCR IGHs and IGLs from the peripheral blood of COVID-19 patients and healthy donors. The results showed significantly reduced clonal diversity, more expanded clones, and longer CDR3 lengths of IGH and IGL in COVID-19 patients than those in healthy individuals. The IGLs had a much higher percentage of VJ skew usage (47.83% IGLV and 42.86% IGLJ were significantly regulated) than the IGHs (12.09% IGHV and 0% IGHJ) between the healthy individuals and patients, which indicated the importance of BCR light chains. Furthermore, we found a largely expanded IGLV3-25 gene cluster mostly pairing with IGLJ1 and ILGJ2 in COVID-19 patients and a newly identified upregulated IGLJ1 gene and IGLJ2+IGLV13-21 recombination, both of which are potential sources of SARS-CoV-2-targeting antibodies. Our findings on specific immune B-cell signatures associated with COVID-19 have clinical implications for vaccine and biomarker development for disease diagnosis.

Monoclonal Antibodies and Invasive Aspergillosis: Diagnostic and Therapeutic Perspectives.

Invasive aspergillosis (IA) is a life-threatening fungal disease that causes high morbidity and mortality in immunosuppressed patients. Early and accurate diagnosis and treatment of IA remain challenging. Given the broad range of non-specific clinical symptoms and the shortcomings of current diagnostic techniques, most patients are either diagnosed as "possible" or "probable" cases but not "proven". Moreover, because of the lack of sensitive and specific tests, many high-risk patients receive an empirical therapy or a prolonged treatment of high-priced antifungal agents, leading to unnecessary adverse effects and a high risk of drug resistance. More precise diagnostic techniques alongside a targeted antifungal treatment are fundamental requirements for reducing the morbidity and mortality of IA. Monoclonal antibodies (mAbs) with high specificity in targeting the corresponding antigen(s) may have the potential to improve diagnostic tests and form the basis for novel IA treatments. This review summarizes the up-to-date application of mAb-based approaches in assisting IA diagnosis and therapy.

Public Knowledge, Attitudes, and Practices Behaviors Towards Coronavirus Disease 2019 (COVID-19) During a National Epidemic-China.

Background: The rapid outbreak of coronavirus disease 2019 (COVID-19) posed a serious threat to China, followed by compulsive measures taken against the national emergency to control its further spread. This study was designed to describe residents' knowledge, attitudes, and practice behaviors (KAP) during the outbreak of COVID-19. Methods: An anonymous online questionnaire was randomly administrated to residents in mainland China between Mar 7 and Mar 16, 2020. Residents' responses to KAP were quantified by descriptive and stratified analyses. A Multiple Logistic Regression model was employed to identify risk factors associated with KAP scores. Results: A total of 10,195 participants were enrolled from 32 provinces of China. Participants of the ≥61 years group had higher KAP scores [adjusted Odds Ratio (ORadj) = 4.8, 95% Confidence Interval (CI): 3.0-7.7, P < 0.0001], and the married participants and those in low-income families had higher scores of KAP (ORadj = 1.2, 95% CI: 1.1-1.3; ORadj = 1.8, 95% CI: 1.6-2.2, respectively, both P < 0.0001). The participants living with more than two family members had higher scores in an increasing ORs when the family members increased (ORadj = 1.3, 95% CI: 1.1-1.6, P = 0.013; ORadj = 1.3, 95% CI: 1.1-1.6, P = 0.003; ORadj = 1.3, 95% CI: 1.0-1.6, P = 0.02; for groups of 2, 3-4 and ≥5, respectively). Conclusions: Out of the enrolled participants who completed the survey, 85.5% responded positively toward the mandatory public health interventions implemented nationwide by the Chinese authorities. These effective practices seem to be related to a proper attitude generated by the increased knowledge and better awareness of the risks related to the COVID-19 pandemic and the consequent need for safe and responsible behavior.

Clinical features and risk factors associated with severe COVID-19 patients in China.

BACKGROUND: Coronavirus disease 2019 (COVID-19), which is caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has rapidly spread throughout the world. In this study, we aimed to identify the risk factors for severe COVID-19 to improve treatment guidelines. METHODS: A multicenter, cross-sectional study was conducted on 313 patients hospitalized with COVID-19. Patients were classified into two groups based on disease severity (nonsevere and severe) according to initial clinical presentation. Laboratory test results and epidemiological and clinical characteristics were analyzed using descriptive statistics. Univariate and multivariate logistic regression models were used to detect potential risk factors associated with severe COVID-19. RESULTS: A total of 289 patients (197 nonsevere and 92 severe cases) with a median age of 45.0 (33.0, 61.0) years were included in this study, and 53.3% (154/289) were male. Fever (192/286, 67.1%) and cough (170/289, 58.8%) were commonly observed, followed by sore throat (49/289, 17.0%). Multivariate logistic regression analysis suggested that patients who were aged ≥ 65 years (OR: 2.725, 95% confidence interval [CI]: 1.317-5.636; P = 0.007), were male (OR: 1.878, 95% CI: 1.002-3.520, P = 0.049), had comorbid diabetes (OR: 3.314, 95% CI: 1.126-9.758, P = 0.030), cough (OR: 3.427, 95% CI: 1.752-6.706, P < 0.001), and/or diarrhea (OR: 2.629, 95% CI: 1.109-6.231, P = 0.028) on admission had a higher risk of severe disease. Moreover, stratification analysis indicated that male patients with diabetes were more likely to have severe COVID-19 (71.4% vs. 28.6%, χ2 = 8.183, P = 0.004). CONCLUSIONS: The clinical characteristics of those with severe and nonsevere COVID-19 were significantly different. The elderly, male patients with COVID-19, diabetes, and presenting with cough and/or diarrhea on admission may require close monitoring to prevent deterioration.

From SARS and MERS to COVID-19: a brief summary and comparison of severe acute respiratory infections caused by three highly pathogenic human coronaviruses.

Within two decades, there have emerged three highly pathogenic and deadly human coronaviruses, namely SARS-CoV, MERS-CoV and SARS-CoV-2. The economic burden and health threats caused by these coronaviruses are extremely dreadful and getting more serious as the increasing number of global infections and attributed deaths of SARS-CoV-2 and MERS-CoV. Unfortunately, specific medical countermeasures for these hCoVs remain absent. Moreover, the fast spread of misinformation about the ongoing SARS-CoV-2 pandemic uniquely places the virus alongside an annoying infodemic and causes unnecessary worldwide panic. SARS-CoV-2 shares many similarities with SARS-CoV and MERS-CoV, certainly, obvious differences exist as well. Lessons learnt from SARS-CoV and MERS-CoV, timely updated information of SARS-CoV-2 and MERS-CoV, and summarized specific knowledge of these hCoVs are extremely invaluable for effectively and efficiently contain the outbreak of SARS-CoV-2 and MERS-CoV. By gaining a deeper understanding of hCoVs and the illnesses caused by them, we can bridge knowledge gaps, provide cultural weapons for fighting and controling the spread of MERS-CoV and SARS-CoV-2, and prepare effective and robust defense lines against hCoVs that may emerge or reemerge in the future. To this end, the state-of-the-art knowledge and comparing the biological features of these lethal hCoVs and the clinical characteristics of illnesses caused by them are systematically summarized in the review.