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.

Development of SARS-CoV-2 variant protein microarray for profiling humoral immunity in vaccinated subjects.

SARS-CoV-2 is quickly evolving from wild-type to many variants and spreading around the globe. Since many people have been vaccinated with various types of vaccines, it is crucial to develop a high throughput platform for measuring the antibody responses and surrogate neutralizing activities against multiple SARS-CoV-2 variants. To meet this need, the present study developed a SARS-CoV-2 variant (CoVariant) array which consists of the extracellular domain of spike variants, e.g., wild-type, D614G, B.1.1.7, B.1.351, P.1, B.1.617, B.1.617.1, B.1.617.2, and B.1.617.3. A surrogate virus neutralization on the CoVariant array was established to quantify the bindings of antibody and host receptor ACE2 simultaneously to spike variants. By using a chimeric anti-spike antibody, we demonstrated a broad binding spectrum of antibodies while inhibiting the bindings of ACE2 to spike variants. To monitor the humoral immunities after vaccination, we collected serums from unvaccinated, partial, or fully vaccinated individuals with either mRNA-1273 or AZD1222 (ChAdOx1). The results showed partial vaccination increased the surrogate neutralization against all the mutants while full vaccination boosted the most. Although IgG, IgA, and IgM isotypes correlated with surrogate neutralizing activities, they behave differently throughout the vaccination processes. Overall, this study developed CoVariant arrays and assays for profiling the humoral responses which are useful for immune assessment, vaccine research, and drug development.

Exhausting T Cells During HIV Infection May Improve the Prognosis of Patients with COVID-19.

T-cell reduction is an important characteristic of coronavirus disease 2019 (COVID-19), and its immunopathology is a subject of debate. It may be due to the direct effect of the virus on T-cell exhaustion or indirectly due to T cells redistributing to the lungs. HIV/AIDS naturally served as a T-cell exhaustion disease model for recognizing how the immune system works in the course of COVID-19. In this study, we collected the clinical charts, T-lymphocyte analysis, and chest CT of HIV patients with laboratory-confirmed COVID-19 infection who were admitted to Jin Yin-tan Hospital (Wuhan, China). The median age of the 21 patients was 47 years [interquartile range (IQR) = 40-50 years] and the median CD4 T-cell count was 183 cells/µl (IQR = 96-289 cells/µl). Eleven HIV patients were in the non-AIDS stage and 10 were in the AIDS stage. Nine patients received antiretroviral treatment (ART) and 12 patients did not receive any treatment. Compared to the reported mortality rate (nearly 4%-10%) and severity rate (up to 20%-40%) among COVID-19 patients in hospital, a benign duration with 0% severity and mortality rates was shown by 21 HIV/AIDS patients. The severity rates of COVID-19 were comparable between non-AIDS (median CD4 = 287 cells/µl) and AIDS (median CD4 = 97 cells/µl) patients, despite some of the AIDS patients having baseline lung injury stimulated by HIV: 7 patients (33%) were mild (five in the non-AIDS group and two in the AIDS group) and 14 patients (67%) were moderate (six in the non-AIDS group and eight in the AIDS group). More importantly, we found that a reduction in T-cell number positively correlates with the serum levels of interleukin 6 (IL-6) and C-reactive protein (CRP), which is contrary to the reported findings on the immune response of COVID-19 patients (lower CD4 T-cell counts with higher levels of IL-6 and CRP). In HIV/AIDS, a compromised immune system with lower CD4 T-cell counts might waive the clinical symptoms and inflammatory responses, which suggests lymphocyte redistribution as an immunopathology leading to lymphopenia in COVID-19.

Clinical characteristics of chronic liver disease with coronavirus disease 2019 (COVID-19): a cohort study in Wuhan, China.

BACKGROUND: Previous work has described acute liver injury (ALI) in coronavirus disease 2019 (COVID-19) pneumonia patients, However, there is limited analyses available investigating chronic liver disease (CLD) in COVID-19 patients. This study aimed to investigate clinical characteristics and outcomes of CLD confirmed in COVID-19 patients. RESULTS: A total of 104 cases (each group containing 52 patients) were analyzed in this study. The CLD group showed an average of 14 (10.0~21.2) length of stay (LOS) days, compared to the group without CLD that only showed an average of 12.5 (10~16) LOS days (Relative Risk [RR] = 1.34, 95% CI (1.22~1.48), P<0.001; Adjusted Relative Risk was 1.24 (95% CI: 1.12~1.39)). The CLD group contained a higher mortality rate and slight liver injury. Furthermore, COX regression model analyses suggested that the neutrophil-to-lymphocyte ratio (NLR) was an independent predictor of mortality risk (P < 0.001) in the CLD group. Additionally, a high NLR significantly correlated with a shorter overall survival (P <0.001). CONCLUSIONS: COVID-19 patients also diagnosed with CLD suffered longer LOS, slight liver injuries and a higher mortality when compared to COVID-19 patients without CLD. The NLR was an independent risk factor for in-hospital deaths. Increased expression of NLR was an indicator of poor prognosis in COVID-19 patients with CLD. Thus, COVID-19 patients diagnosed with CLD and who show a higher NLR need additional care. METHODS: A retrospective cohort study was performed at the Wuhan Jin Yin-tan Hospital from February 2, 2020 to April 2, 2020. COVID-19 patients diagnosed with CLD or not diagnosed with CLD were enrolled in this study. The clinical characteristics and outcomes of these patients were compared.