Federated semi-supervised learning for COVID region segmentation in chest CT using multi-national data from China, Italy, Japan.

The recent outbreak of Coronavirus Disease 2019 (COVID-19) has led to urgent needs for reliable diagnosis and management of SARS-CoV-2 infection. The current guideline is using RT-PCR for testing. As a complimentary tool with diagnostic imaging, chest Computed Tomography (CT) has been shown to be able to reveal visual patterns characteristic for COVID-19, which has definite value at several stages during the disease course. To facilitate CT analysis, recent efforts have focused on computer-aided characterization and diagnosis with chest CT scan, which has shown promising results. However, domain shift of data across clinical data centers poses a serious challenge when deploying learning-based models. A common way to alleviate this issue is to fine-tune the model locally with the target domains local data and annotations. Unfortunately, the availability and quality of local annotations usually varies due to heterogeneity in equipment and distribution of medical resources across the globe. This impact may be pronounced in the detection of COVID-19, since the relevant patterns vary in size, shape, and texture. In this work, we attempt to find a solution for this challenge via federated and semi-supervised learning. A multi-national database consisting of 1704 scans from three countries is adopted to study the performance gap, when training a model with one dataset and applying it to another. Expert radiologists manually delineated 945 scans for COVID-19 findings. In handling the variability in both the data and annotations, a novel federated semi-supervised learning technique is proposed to fully utilize all available data (with or without annotations). Federated learning avoids the need for sensitive data-sharing, which makes it favorable for institutions and nations with strict regulatory policy on data privacy. Moreover, semi-supervision potentially reduces the annotation burden under a distributed setting. The proposed framework is shown to be effective compared to fully supervised scenarios with conventional data sharing instead of model weight sharing.

Prediction of an increase in oxygen requirement of SARS-CoV-2 pneumonia using three different scoring systems.

INTRODUCTION: In patients with severe coronavirus disease 2019 (COVID-19), respiratory failure is a major complication and its symptoms occur around one week after onset. The CURB-65, A-DROP and expanded CURB-65 tools are known to predict the risk of mortality in patients with community-acquired pneumonia. In this retrospective single-center retrospective study, we aimed to assess the correlations of the A-DROP, CURB-65, and expanded CURB-65 scores on admission with an increase in oxygen requirement in patients with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pneumonia. METHODS: We retrospectively analyzed 207 patients who were hospitalized with SARS-CoV-2 pneumonia at the Self-Defense Forces Central Hospital in Tokyo, Japan. Performance of A-DROP, CURB-65, and the expanded CURB-65 scores were validated. In addition, we assessed whether there were any associations between an increase in oxygen requirement and known risk factors for critical illness in COVID-19, including elevation of liver enzymes and C-reactive protein (CRP), lymphocytopenia, high D-dimer levels and the chest computed tomography (CT) score. RESULTS: The areas under the curve for the ability of CURB-65, A-DROP, and the expanded CURB-65 scores to predict an increase in oxygen requirement were 0.6961, 0.6980 and 0.8327, respectively, and the differences between the three groups were statistically significant (p < 0.001). Comorbid cardiovascular disease, lymphocytopenia, elevated CRP, liver enzyme and D-dimer levels, and higher chest CT score were significantly associated with an increase in oxygen requirement CONCLUSIONS: The expanded CURB-65 score can be a better predictor of an increase in oxygen requirement in patients with SARS-CoV-2 pneumonia.

CT and clinical assessment in asymptomatic and pre-symptomatic patients with early SARS-CoV-2 in outbreak settings.

OBJECTIVES: The early infection dynamics of patients with SARS-CoV-2 are not well understood. We aimed to investigate and characterize associations between clinical, laboratory, and imaging features of asymptomatic and pre-symptomatic patients with SARS-CoV-2. METHODS: Seventy-four patients with RT-PCR-proven SARS-CoV-2 infection were asymptomatic at presentation. All were retrospectively identified from 825 patients with chest CT scans and positive RT-PCR following exposure or travel risks in outbreak settings in Japan and China. CTs were obtained for every patient within a day of admission and were reviewed for infiltrate subtypes and percent with assistance from a deep learning tool. Correlations of clinical, laboratory, and imaging features were analyzed and comparisons were performed using univariate and multivariate logistic regression. RESULTS: Forty-eight of 74 (65%) initially asymptomatic patients had CT infiltrates that pre-dated symptom onset by 3.8 days. The most common CT infiltrates were ground glass opacities (45/48; 94%) and consolidation (22/48; 46%). Patient body temperature (p < 0.01), CRP (p < 0.01), and KL-6 (p = 0.02) were associated with the presence of CT infiltrates. Infiltrate volume (p = 0.01), percent lung involvement (p = 0.01), and consolidation (p = 0.043) were associated with subsequent development of symptoms. CONCLUSIONS: COVID-19 CT infiltrates pre-dated symptoms in two-thirds of patients. Body temperature elevation and laboratory evaluations may identify asymptomatic patients with SARS-CoV-2 CT infiltrates at presentation, and the characteristics of CT infiltrates could help identify asymptomatic SARS-CoV-2 patients who subsequently develop symptoms. The role of chest CT in COVID-19 may be illuminated by a better understanding of CT infiltrates in patients with early disease or SARS-CoV-2 exposure. KEY POINTS: • Forty-eight of 74 (65%) pre-selected asymptomatic patients with SARS-CoV-2 had abnormal chest CT findings. • CT infiltrates pre-dated symptom onset by 3.8 days (range 1-5). • KL-6, CRP, and elevated body temperature identified patients with CT infiltrates. Higher infiltrate volume, percent lung involvement, and pulmonary consolidation identified patients who developed symptoms.

Comparison of COVID-19 disease between young and elderly patients: Hidden viral shedding of COVID-19.

OBJECTIVES: The symptoms of Coronavirus disease 2019 (COVID-19) vary among patients. The aim of this study was to investigate the clinical manifestation and disease duration in young versus elderly patients. METHODS: We retrospectively analyzed 187 patients (87 elderly and 100 young patients) with confirmed COVID-19. The clinical characteristics and chest computed tomography (CT) extent as defined by a score were compared between the two groups. RESULTS: The numbers of asymptomatic cases and severe cases were significantly higher in the elderly group (elderly group vs. young group; asymptomatic cases, 31 [35.6%] vs. 10 [10%], p < 0.0001; severe cases, 25 [28.7%] vs. 8 [8.0%], p = 0.0002). The proportion of asymptomatic patients and severe patients increased across the 10-year age groups. There was no significant difference in the total CT score and number of abnormal cases. A significant positive correlation between the disease duration and patient age was observed in asymptomatic patients (ρ = 0.4570, 95% CI 0.1198-0.6491, p = 0.0034). CONCLUSIONS: Although the extent of lung involvement did not have a significant difference between the young and elderly patients, elderly patients were more likely to have severe clinical manifestations. Elderly patients were also more likely to be asymptomatic and a source of COVID-19 viral shedding.

Artificial intelligence for the detection of COVID-19 pneumonia on chest CT using multinational datasets.

Chest CT is emerging as a valuable diagnostic tool for clinical management of COVID-19 associated lung disease. Artificial intelligence (AI) has the potential to aid in rapid evaluation of CT scans for differentiation of COVID-19 findings from other clinical entities. Here we show that a series of deep learning algorithms, trained in a diverse multinational cohort of 1280 patients to localize parietal pleura/lung parenchyma followed by classification of COVID-19 pneumonia, can achieve up to 90.8% accuracy, with 84% sensitivity and 93% specificity, as evaluated in an independent test set (not included in training and validation) of 1337 patients. Normal controls included chest CTs from oncology, emergency, and pneumonia-related indications. The false positive rate in 140 patients with laboratory confirmed other (non COVID-19) pneumonias was 10%. AI-based algorithms can readily identify CT scans with COVID-19 associated pneumonia, as well as distinguish non-COVID related pneumonias with high specificity in diverse patient populations.