ABSTRACT
Understanding chest CT imaging of the coronavirus disease 2019 (COVID-19) will help detect infections early and assess the disease progression. Especially, automated severity assessment of COVID-19 in CT images plays an essential role in identifying cases that are in great need of intensive clinical care. However, it is often challenging to accurately assess the severity of this disease in CT images, due to variable infection regions in the lungs, similar imaging biomarkers, and large inter-case variations. To this end, we propose a synergistic learning framework for automated severity assessment of COVID-19 in 3D CT images, by jointly performing lung lobe segmentation and multi-instance classification. Considering that only a few infection regions in a CT image are related to the severity assessment, we first represent each input image by a bag that contains a set of 2D image patches (with each cropped from a specific slice). A multi-task multi-instance deep network (called M 2 UNet) is then developed to assess the severity of COVID-19 patients and also segment the lung lobe simultaneously. Our M 2 UNet consists of a patch-level encoder, a segmentation sub-network for lung lobe segmentation, and a classification sub-network for severity assessment (with a unique hierarchical multi-instance learning strategy). Here, the context information provided by segmentation can be implicitly employed to improve the performance of severity assessment. Extensive experiments were performed on a real COVID-19 CT image dataset consisting of 666 chest CT images, with results suggesting the effectiveness of our proposed method compared to several state-of-the-art methods.
ABSTRACT
Rationale: The coronavirus disease (COVID-19) pandemic is now a global health concern.Objectives: We compared the clinical characteristics, laboratory examinations, computed tomography images, and treatments of patients with COVID-19 from three different cities in China.Methods: A total of 476 patients were recruited from January 1, 2020, to February 15, 2020, at three hospitals in Wuhan, Shanghai, and Anhui. The patients were divided into four groups according to age and into three groups (moderate, severe, and critical) according to the fifth edition of the Guidelines on the Diagnosis and Treatment of COVID-19 issued by the National Health Commission of China.Measurements and Main Results: The incidence of comorbidities was higher in the severe (46.3%) and critical (67.1%) groups than in the moderate group (37.8%). More patients were taking angiotensin-converting enzyme inhibitors/angiotensin II receptor blockers in the moderate group than in the severe and critical groups. More patients had multiple lung lobe involvement and pleural effusion in the critical group than in the moderate group. More patients received antiviral agents within the first 4 days in the moderate group than in the severe group, and more patients received antibiotics and corticosteroids in the critical and severe groups. Patients >75 years old had a significantly lower survival rate than younger patients.Conclusions: Multiple organ dysfunction and impaired immune function were the typical characteristics of patients with severe or critical illness. There was a significant difference in the use of angiotensin-converting enzyme inhibitors/angiotensin II receptor blockers among patients with different severities of disease. Involvement of multiple lung lobes and pleural effusion were associated with the severity of COVID-19. Advanced age (≥75 yr) was a risk factor for mortality.