Detecting Coronavirus (COVID -19) Disease Cues from Chest Radiography Images

This paper proposes a deep learning-based approach to detect COVID-19 infections in lung tissues from chest Computed Tomography (CT) images. A two-stage classification model is designed to identify the infection from CT scans of COVID-19 and Community Acquired Pneumonia (CAP) patients. The proposed neural model named, Residual C-NiN uses a modified convolutional neural network (CNN) with residual connections and a Network-in-Network (NiN) architecture for COVID-19 and CAP detection. The model is trained with the Signal Processing Grand Challenge (SPGC) 2021 COVID dataset. The proposed neural model achieves a slice-level classification accuracy of 93.54% on chest CT images and patient-level classification accuracy of 86.59% with class-wise sensitivity of 92.72%, 55.55%, and 95.83% for COVID-19, CAP, and Normal classes, respectively. Experimental results show the benefit of adding NiN and residual connections in the proposed neural architecture. Experiments conducted on the dataset show significant improvement over the existing state-of-the-art methods reported in the literature. © 2022 ACM.

Functional SARS-CoV-2-specific T cells of donor origin in allogeneic stem cell transplant recipients of a T-cell-replete infusion: A prospective observational study

In the current post-pandemic era, recipients of an allogeneic hematopoietic stem cell transplant (HCT) deserve special attention. In these vulnerable patients, vaccine effectiveness is reduced by post-transplant immune-suppressive therapy;consequently, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) disease (COVID-19) is often associated with elevated morbidity and mortality. Characterizing SARS-CoV-2 adaptive immunity transfer from immune donors to HCT recipients in the context of immunosuppression will help identify optimal timing and vaccination strategies that can provide adequate protection to HCT recipients against infection with evolving SARS-CoV-2 variants. We performed a prospective observational study (NCT04666025 at ClinicalTrials.gov) to longitudinally monitor the transfer of SARS-CoV-2-specific antiviral immunity from HCT donors, who were either vaccinated or had a history of COVID-19, to their recipients via T-cell replete graft. Levels, function, and quality of SARS-CoV-2-specific immune responses were longitudinally analyzed up to 6 months post-HCT in 14 matched unrelated donor/recipients and four haploidentical donor/recipient pairs. A markedly skewed donor-derived SARS-CoV-2 CD4 T-cell response was measurable in 15 (83%) recipients. It showed a polarized Th1 functional profile, with the prevalence of central memory phenotype subsets. SARS-CoV-2-specific IFN-γ was detectable throughout the observation period, including early post-transplant (day +30). Functionally experienced SARS-CoV-2 Th1-type T cells promptly expanded in two recipients at the time of post-HCT vaccination and in two others who were infected and survived post-transplant COVID-19 infection. Our data suggest that donor-derived SARS-CoV-2 T-cell responses are functional in immunosuppressed recipients and may play a critical role in post-HCT vaccine response and protection from the fatal disease. Clinical trial registration clinicaltrials.gov, identifier NCT04666025.

Functional SARS-CoV-2-specific T cells of donor origin in allogeneic stem cell transplant recipients of a T-cell-replete infusion: A prospective observational study.

In the current post-pandemic era, recipients of an allogeneic hematopoietic stem cell transplant (HCT) deserve special attention. In these vulnerable patients, vaccine effectiveness is reduced by post-transplant immune-suppressive therapy; consequently, severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) disease (COVID-19) is often associated with elevated morbidity and mortality. Characterizing SARS-CoV-2 adaptive immunity transfer from immune donors to HCT recipients in the context of immunosuppression will help identify optimal timing and vaccination strategies that can provide adequate protection to HCT recipients against infection with evolving SARS-CoV-2 variants. We performed a prospective observational study (NCT04666025 at ClinicalTrials.gov) to longitudinally monitor the transfer of SARS-CoV-2-specific antiviral immunity from HCT donors, who were either vaccinated or had a history of COVID-19, to their recipients via T-cell replete graft. Levels, function, and quality of SARS-CoV-2-specific immune responses were longitudinally analyzed up to 6 months post-HCT in 14 matched unrelated donor/recipients and four haploidentical donor/recipient pairs. A markedly skewed donor-derived SARS-CoV-2 CD4 T-cell response was measurable in 15 (83%) recipients. It showed a polarized Th1 functional profile, with the prevalence of central memory phenotype subsets. SARS-CoV-2-specific IFN-γ was detectable throughout the observation period, including early post-transplant (day +30). Functionally experienced SARS-CoV-2 Th1-type T cells promptly expanded in two recipients at the time of post-HCT vaccination and in two others who were infected and survived post-transplant COVID-19 infection. Our data suggest that donor-derived SARS-CoV-2 T-cell responses are functional in immunosuppressed recipients and may play a critical role in post-HCT vaccine response and protection from the fatal disease. Clinical trial registration: clinicaltrials.gov, identifier NCT04666025.

EMPLOYING ACOUSTIC FEATURES TO AID NEURAL NETWORKS TOWARDS PLATFORM AGNOSTIC LEARNING IN LUNG ULTRASOUND IMAGING

With the recent outbreak of COVID-19, ultrasound is fast becoming an inevitable diagnostic tool for regular and continuous monitoring of the lung. However, lung ultrasound (LUS) is unique in the perspective that, the artefacts created by acoustic wave propagation is aiding clinicians in diagnosis. In this work, a novel approach is presented to extract acoustic wave propagation driven features such as acoustic shadows, local phase-based feature symmetry, and integrated backscattering to automatically detect the pleura and to aid a pretrained neural network to classify the severity of lung infection based on the region below pleura. A detailed analysis of the proposed approach on LUS images over the infection to full recovery period of ten confirmed COVID-19 subjects across 400 videos shows an average five-fold cross-validation accuracy, sensitivity, and specificity of 97%, 92%, and 98% respectively over randomly selected 5000 frames. The results and analysis show that, when the input dataset is limited and diverse as in the case of COVID-19 pandemic, an aided effort of combining acoustic propagation-based features along with the gray scale images, as proposed in this work, improves the performance of the neural network significantly even when tested against a completely new data acquisition. © 2021 IEEE.