A personal COVID-19 dendritic cell vaccine made at point-of-care: Feasibility, safety, and antigen-specific cellular immune responses.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has caused a world-wide pandemic. Internationally, because of availability, accessibility, and distribution issues, there is a need for additional vaccines. This study aimed to: establish the feasibility of personal dendritic cell vaccines to the SARS-CoV-2 spike protein, establish the safety of a single subcutaneous vaccine injection, and determine the antigen-specific immune response following vaccination. In Phase 1, 31 subjects were assigned to one of nine formulations of autologous dendritic cells and lymphocytes (DCL) incubated with 0.10, 0.33, or 1.0 µg of recombinant SARS-CoV-2 spike protein, and admixed with saline or 250 or 500 µg of granulocyte-macrophage colony-stimulating factor (GM-CSF) prior to injection, then assessed for safety and humoral response. In Phase 2, 145 subjects were randomized to one of three formulations defined by incubation with the same three quantities of spike protein without GM-CSF, then assessed for safety and cellular response. Vaccines were successfully manufactured for every subject at point-of-care. Approximately 46.4% of subjects had a grade 1 adverse event (AE); 6.5% had a grade 2 AE. Among 169 evaluable subjects, there were no acute allergic, grade 3 or 4, or serious AE. In Phase 1, anti-receptor binding domain antibodies were increased in 70% of subjects on day-28. In Phase 2, in the 127 subjects who did not have high levels of gamma interferon-producing cells at baseline, 94.4% had increased by day 14 and 96.8% by day 28. Point-of-care personal vaccine manufacturing was feasible. Further development of such subject-specific vaccines is warranted.

UBNet: Deep learning-based approach for automatic X-ray image detection of pneumonia and COVID-19 patients.

BACKGROUND: Analysis of chest X-ray images is one of the primary standards in diagnosing patients with COVID-19 and pneumonia, which is faster than using PCR Swab method. However, accuracy of using X-ray images needs to be improved. OBJECTIVE: To develop a new deep learning system of chest X-ray images and evaluate whether it can quickly and accurately detect pneumonia and COVID-19 patients. METHODS: The developed deep learning system (UBNet v3) uses three architectural hierarchies, namely first, to build an architecture containing 7 convolution layers and 3 ANN layers (UBNet v1) to classify between normal images and pneumonia images. Second, using 4 layers of convolution and 3 layers of ANN (UBNet v2) to classify between bacterial and viral pneumonia images. Third, using UBNet v1 to classify between pneumonia virus images and COVID-19 virus infected images. An open-source database with 9,250 chest X-ray images including 3,592 COVID-19 images were used in this study to train and test the developed deep learning models. RESULTS: CNN architecture with a hierarchical scheme developed in UBNet v3 using a simple architecture yielded following performance indices to detect chest X-ray images of COVID-19 patients namely, 99.6%accuracy, 99.7%precision, 99.7%sensitivity, 99.1%specificity, and F1 score of 99.74%. A desktop GUI-based monitoring and classification system supported by a simple CNN architecture can process each chest X-ray image to detect and classify COVID-19 image with an average time of 1.21 seconds. CONCLUSION: Using three hierarchical architectures in UBNet v3 improves system performance in classifying chest X-ray images of pneumonia and COVID-19 patients. A simple architecture also speeds up image processing time.