Fuzzy Attention Neural Network to Tackle Discontinuity in Airway Segmentation.

Airway segmentation is crucial for the examination, diagnosis, and prognosis of lung diseases, while its manual delineation is unduly burdensome. To alleviate this time-consuming and potentially subjective manual procedure, researchers have proposed methods to automatically segment airways from computerized tomography (CT) images. However, some small-sized airway branches (e.g., bronchus and terminal bronchioles) significantly aggravate the difficulty of automatic segmentation by machine learning models. In particular, the variance of voxel values and the severe data imbalance in airway branches make the computational module prone to discontinuous and false-negative predictions, especially for cohorts with different lung diseases. The attention mechanism has shown the capacity to segment complex structures, while fuzzy logic can reduce the uncertainty in feature representations. Therefore, the integration of deep attention networks and fuzzy theory, given by the fuzzy attention layer, should be an escalated solution for better generalization and robustness. This article presents an efficient method for airway segmentation, comprising a novel fuzzy attention neural network (FANN) and a comprehensive loss function to enhance the spatial continuity of airway segmentation. The deep fuzzy set is formulated by a set of voxels in the feature map and a learnable Gaussian membership function. Different from the existing attention mechanism, the proposed channel-specific fuzzy attention addresses the issue of heterogeneous features in different channels. Furthermore, a novel evaluation metric is proposed to assess both the continuity and completeness of airway structures. The efficiency, generalization, and robustness of the proposed method have been proved by training on normal lung disease while testing on datasets of lung cancer, COVID-19, and pulmonary fibrosis.

Prevalence and Characteristics of Rheumatoid-Associated Autoantibodies in Patients with COVID-19.

OBJECTIVE: Patients with rheumatic immune diseases were more likely to develop severe or critical COVID-19. We aimed to determine whether rheumatoid factor antibodies were present in COVID patients and the level and type of rheumatoid factor antibodies produced in COVID-19 patients were related to the degree of the patient's condition. The study also aimed to determine the prevalence and characteristics of rheumatoid factor antibodies in patients with COVID-19. METHODS: Sera collected from 129 patients with COVID-19 were tested for rheumatoid factor antibodies by ELISA. Five patients were tracked for several months to monitor dynamic changes of these antibodies. RESULTS: Rheumatoid-associated autoantibodies were detected in 20.16% of patients (26/129) following infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). In addition, IgM-RF was primarily present in critically ill patients, while IgA-RF was mainly present in mild patients. Five patients were able to track for several months to monitor dynamic changes of these antibodies. Rheumatoid factor antibodies peaks in the later phase of the disease and last for longer time. Anti-Jo-1 antibody was found in one of the five patients. CONCLUSION: This was the case series report that rheumatoid-associated autoantibodies are present in patients with COVID-19. The clinical significance of these antibodies was not fully understood and needed further characterization. These autoantibodies are related to the severity of the patient's disease and exist for a long time in the patient's body, while their impact on the patient's health is unknown.

Evaluation of serum hepatic enzyme activities in different COVID-19 phenotypes.

Coronavirus disease 2019 (COVID-19) is a newly emerging infectious disease. Our understanding of the clinical characteristics of liver damage and the relationship with disease severity in COVID-19 is still limited. To investigate the serum hepatic enzyme activities in different phenotypes of COVID-19 patients, evaluate their relationship with the illness severity and analyze the correlation of glycyrrhizin treatment and abnormal liver enzyme activities, one hundred and forty-seven patients with COVID-19 were enrolled in a retrospective study that investigated hepatic dysfunction. Liver alanine aminotransferase (ALT), aspartate aminotransferase (AST), lactic dehydrogenase (LDH), Y-glutamyl transferase (GGT), superoxide dismutase (SOD), and alkaline phosphatase (ALP) were analyzed in these patients. Patients with diammonium glycyrrhizinate (DG) treatment were further investigated. Of the 147 patients, 56 (38.1%) had abnormal ALT activity and 80 (54.4%) had abnormal AST activity. The peak of abnormal hepatic enzyme activities occurred at 3 to 6 days after on admission. Serum AST and LDH levels were elevated, while the SOD level was decreased in severe and critical patients, compared with mild cases. DG treatment may alleviate the abnormal liver enzyme activities in non-critical COVID-19 patients. Abnormal liver functions may be observed in patients with COVID-19, and were associated with SARS-CoV-2-induced acute liver damage. Glycyrrhizin treatment may be an effective therapeutic approach for the outcome of abnormal hepatic enzyme activities in severe COVID-19 cases. Serum hepatic enzyme tests may reflect the illness severity and should be monitored.

Correlation of Krebs von den Lungen-6 and fibronectin with pulmonary fibrosis in coronavirus disease 2019.

OBJECTIVE: Coronavirus Disease 2019 (COVID-19) caused by a novel severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is still spreading worldwide, which may progress to pulmonary fibrosis (PF), leading to the worsen outcome. As the markers of lung injury, the correlation of Krebs von den Lungen-6 (KL-6) and fibronectin (Fn) with pulmonary fibrosis in COVID-19 was still unclear. METHODS: 113 patients diagnosed as COVID-19 were enrolled in this retrospective study, and divided into three categories as mild, moderate and severe cases. The concentrations of serum KL-6 and Fn at hospital admission were tested using the method of latex agglutination assay and immunoturbidimetic assay, respectively. RESULTS: Compared with that in the non-severe COVID-19 cases and normal control subjects, serum KL-6 concentration on admission was significantly higher in the severe group, which was positively correlated with C-reactive protein, and negatively correlated with lymphocytes count. Whereas, no obvious elevation in serum Fn concentration was investigated in COVID-19 patients with the different phenotypes. The severe cases displayed the higher incident rate of pulmonary fibrosis at hospital discharge. Compared with non-PF patients, the COVID-19 cases with PF had the higher serum KL-6 values. CONCLUSION: Serum KL-6 concentration was significantly elevated in severe COVID-19 patients, which may be useful for evaluating the disease severity. For early prevention of the development of pulmonary fibrosis, high concentrations of serum KL-6 in the early stage of COVID-19 should be paid close attention.