Dual Multiscale Mean Teacher Network for Semi-Supervised Infection Segmentation in Chest CT Volume for COVID-19.

Automated detecting lung infections from computed tomography (CT) data plays an important role for combating coronavirus 2019 (COVID-19). However, there are still some challenges for developing AI system: 1) most current COVID-19 infection segmentation methods mainly relied on 2-D CT images, which lack 3-D sequential constraint; 2) existing 3-D CT segmentation methods focus on single-scale representations, which do not achieve the multiple level receptive field sizes on 3-D volume; and 3) the emergent breaking out of COVID-19 makes it hard to annotate sufficient CT volumes for training deep model. To address these issues, we first build a multiple dimensional-attention convolutional neural network (MDA-CNN) to aggregate multiscale information along different dimension of input feature maps and impose supervision on multiple predictions from different convolutional neural networks (CNNs) layers. Second, we assign this MDA-CNN as a basic network into a novel dual multiscale mean teacher network (DM 2 T-Net) for semi-supervised COVID-19 lung infection segmentation on CT volumes by leveraging unlabeled data and exploring the multiscale information. Our DM 2 T-Net encourages multiple predictions at different CNN layers from the student and teacher networks to be consistent for computing a multiscale consistency loss on unlabeled data, which is then added to the supervised loss on the labeled data from multiple predictions of MDA-CNN. Third, we collect two COVID-19 segmentation datasets to evaluate our method. The experimental results show that our network consistently outperforms the compared state-of-the-art methods.

Clinical and Autoimmune Characteristics of Severe and Critical Cases of COVID-19.

In this study we report on the clinical and autoimmune characteristics of severe and critical novel coronavirus pneumonia caused by severe acute respiratory syndrome-associated coronavirus 2 (SARS-CoV-2). The clinical, autoimmune, and laboratory characteristics of 21 patients who had laboratory-confirmed severe and critical cases of coronavirus disease 2019 (COVID-19) from the intensive care unit of the Huangshi Central Hospital, Hubei Province, China, were investigated. A total of 21 patients (13 men and 8 women), including 8 (38.1%) severe cases and 13 (61.9%) critical cases, were enrolled. Cough (90.5%) and fever (81.0%) were the dominant symptoms, and most patients (76.2%) had at least one coexisting disorder on admission. The most common characteristics on chest computed tomography were ground-glass opacity (100%) and bilateral patchy shadowing (76.2%). The most common findings on laboratory measurement were lymphocytopenia (85.7%) and elevated levels of C-reactive protein (94.7%) and interleukin-6 (89.5%). The prevalence of anti-52 kDa SSA/Ro antibody, anti-60 kDa SSA/Ro antibody, and antinuclear antibody was 20%, 25%, and 50%, respectively. We also retrospectively analyzed the clinical and laboratory data from 21 severe and critical cases of COVID-19. Autoimmune phenomena exist in COVID-19 subjects, and the present results provide the rationale for a strategy of preventing immune dysfunction and optimal immunosuppressive therapy.