In the era of coronavirus disease 2019 (COVID-19) pandemic, imported COVID-19 cases pose great challenges to many countries. Chest CT examination is considered to be complementary to nucleic acid test for COVID-19 detection and diagnosis. We report the first community infected COVID-19 patient by an imported case in Beijing, which manifested as nodular lesions on chest CT imaging at the early stage. Deep Learning (DL)-based diagnostic systems quantitatively monitored the progress of pulmonary lesions in 6 days and timely made alert for suspected pneumonia, so that prompt medical isolation was taken. The patient was confirmed as COVID-19 case after nucleic acid test, for which the community transmission was prevented timely. The roles of DL-assisted diagnosis in helping radiologists screening suspected COVID cases were discussed.
Adult ; Beijing ; COVID-19/diagnostic imaging* ; COVID-19 Testing/methods* ; Community-Acquired Infections/diagnostic imaging* ; Deep Learning ; Humans ; Lung/diagnostic imaging* ; Male ; Tomography, X-Ray Computed/methods*

Humans ; COVID-19 ; Brain/diagnostic imaging* ; Magnetic Resonance Imaging ; Longitudinal Studies

Lung diseases such as lung cancer and COVID-19 seriously endanger human health and life safety, so early screening and diagnosis are particularly important. computed tomography (CT) technology is one of the important ways to screen lung diseases, among which lung parenchyma segmentation based on CT images is the key step in screening lung diseases, and high-quality lung parenchyma segmentation can effectively improve the level of early diagnosis and treatment of lung diseases. Automatic, fast and accurate segmentation of lung parenchyma based on CT images can effectively compensate for the shortcomings of low efficiency and strong subjectivity of manual segmentation, and has become one of the research hotspots in this field. In this paper, the research progress in lung parenchyma segmentation is reviewed based on the related literatures published at domestic and abroad in recent years. The traditional machine learning methods and deep learning methods are compared and analyzed, and the research progress of improving the network structure of deep learning model is emphatically introduced. Some unsolved problems in lung parenchyma segmentation were discussed, and the development prospect was prospected, providing reference for researchers in related fields.
COVID-19 ; Humans ; Lung/diagnostic imaging* ; Machine Learning ; SARS-CoV-2 ; Tomography, X-Ray Computed

INTRODUCTION: Chest radiographs (CXRs) are widely used for the screening and management of COVID-19. This article describes the radiographic features of COVID-19 based on an initial national cohort of patients. METHODS: This is a retrospective review of swab-positive patients with COVID-19 who were admitted to four different hospitals in Singapore between 22 January and 9 March 2020. Initial and follow-up CXRs were reviewed by three experienced radiologists to identify the predominant pattern and distribution of lung parenchymal abnormalities. RESULTS: In total, 347 CXRs of 96 patients were reviewed. Initial CXRs were abnormal in 41 (42.7%) out of 96 patients. The mean time from onset of symptoms to CXR abnormality was 5.3 ± 4.7 days. The predominant pattern of lung abnormality was ground-glass opacity on initial CXRs (51.2%) and consolidation on follow-up CXRs (51.0%). Multifocal bilateral abnormalities in mixed central and peripheral distribution were observed in 63.4% and 59.2% of abnormal initial and follow-up CXRs, respectively. The lower zones were involved in 90.2% of initial CXRs and 93.9% of follow-up CXRs. CONCLUSION In a cohort of swab-positive patients, including those identified from contact tracing, we found a lower incidence of CXR abnormalities than was previously reported. The most common pattern was ground-glass opacity or consolidation, but mixed central and peripheral involvement was more common than peripheral involvement alone.
COVID-19 ; Humans ; Lung/diagnostic imaging* ; Radiography, Thoracic ; Retrospective Studies ; SARS-CoV-2 ; Singapore

Corona virus disease 2019 (COVID-19) is an acute respiratory infectious disease with strong contagiousness, strong variability, and long incubation period. The probability of misdiagnosis and missed diagnosis can be significantly decreased with the use of automatic segmentation of COVID-19 lesions based on computed tomography images, which helps doctors in rapid diagnosis and precise treatment. This paper introduced the level set generalized Dice loss function (LGDL) in conjunction with the level set segmentation method based on COVID-19 lesion segmentation network and proposed a dual-path COVID-19 lesion segmentation network (Dual-SAUNet++) to address the pain points such as the complex symptoms of COVID-19 and the blurred boundaries that are challenging to segment. LGDL is an adaptive weight joint loss obtained by combining the generalized Dice loss of the mask path and the mean square error of the level set path. On the test set, the model achieved Dice similarity coefficient of (87.81 ± 10.86)%, intersection over union of (79.20 ± 14.58)%, sensitivity of (94.18 ± 13.56)%, specificity of (99.83 ± 0.43)% and Hausdorff distance of 18.29 ± 31.48 mm. Studies indicated that Dual-SAUNet++ has a great anti-noise capability and it can segment multi-scale lesions while simultaneously focusing on their area and border information. The method proposed in this paper assists doctors in judging the severity of COVID-19 infection by accurately segmenting the lesion, and provides a reliable basis for subsequent clinical treatment.
Humans ; COVID-19/diagnostic imaging* ; Respiratory Rate ; Tomography, X-Ray Computed

Objective To analyze the CT characteristics of consolidation type of pulmonary cryptococcosis in immunocompetent patients,and thus improve the diagnosis of this disease. Methods A total of 20 cases with consolidation-type pulmonary cryptococcosis confirmed by pathological examinations were studied.Each patient underwent breath-hold multislice spiral CT,and 10 patients underwent contrast enhanced CT.The data including lesion number,lesion distribution,lesion density,performance of enhanced CT scan,accompanying signs,and prognosis were analyzed. Results The occurrence rates of single and multiple lesions were 80.0%(n=16)and 20.0%(n=4),respectively.In all the 16 multiple-lesion patients,the occurrence rate of unilateral lobar distribution was 56.0%(n=9).The 76 measurable lesions mainly presented subpleural distribution(71.1%,n=54)and lower pulmonary distribution(75.0%,n=57).A total of 39 lesions were detected in the 10 patients received contrast enhanced CT,in which 31 lesions(79.5%)showed homogeneous enhancement,34 lesions(87.2%)showed moderate enhancement,and all the lesions manifested angiogram sign.Consolidation lesions were accompanied by many CT signs,of which air bronchogram sign had the occurrence rate of 63.2%(n=48),including types Ⅲ(n =37)and Ⅳ(n=11).Other signs included halo signs(43/76,56.6%),vacuoles or cavities(9/76,11.8%),pleural thickening(14/20,70.0%),and pleural effusion(2/20,10.0%).After treatment,the lesions of 7 patients were basically absorbed and eventually existed in the form of fibrosis. Conclusions The lesions in the immunocompetent patients with consolidation type of pulmonary cryptococcosis usually occur in the lower lobe and close to the pleura,mainly presenting unilateral distribution.The CT angiogram signs,proximal air bronchogram signs,and halo signs are the main features of this disease,which contribute to the diagnosis.
COVID-19 ; Cryptococcosis/diagnostic imaging* ; Humans ; Lung ; Lung Diseases, Fungal/diagnostic imaging* ; Retrospective Studies ; Tomography, X-Ray Computed

To investigate the computed tomography (CT) characteristics and differential diagnosis of high altitude pulmonary edema (HAPE) and COVID-19, CT findings of 52 cases of HAPE confirmed in Medical Station of Sanshili Barracks, PLA 950 Hospital from May 1, 2020 to May 30, 2020 were collected retrospectively. The size, number, location, distribution, density and morphology of the pulmonary lesions of these CT data were analyzed and compared with some already existed COVID-19 CT images which come from two files, "Radiological diagnosis of COVID-19: expert recommendation from the Chinese Society of Radiology (First edition)" and "A rapid advice guideline for the diagnosis and treatment of 2019 novel corona-virus (2019-nCoV) infected pneumonia (standard version)". The simple or multiple ground-glass opacity (GGO) lesions are located both in the HAPE and COVID-19 at the early stage, but only the thickening of interlobular septa, called "crazy paving pattern" belongs to COVID-19. At the next period, some increased cloudy shadows are located in HAPE, while lesions of COVID-19 are more likely to develop parallel to the direction of the pleura, and some of the lesions show the bronchial inflation. At the most serious stage, both the shadows in HAPE and COVID-19 become white, but the lesions of HAPE in the right lung are more serious than that of left lung. In summary, some cloudy shadows are the feature of HAPE CT image, and "crazy paving pattern" and "pleural parallel sign" belong to the COVID-19 CT, which can be used for differential diagnosis.
Altitude ; COVID-19/diagnostic imaging* ; China ; Diagnosis, Differential ; Humans ; Lung/diagnostic imaging* ; Pulmonary Edema/diagnostic imaging* ; Retrospective Studies ; Tomography, X-Ray Computed

INTRODUCTION: We aimed to compare the early clinical manifestations, laboratory results and chest computed tomography (CT) images of COVID-19 patients with those of other community-acquired pneumonia (CAP) patients to differentiate CAP from COVID-19 before reverse transcription-polymerase chain reaction results are obtained. METHODS: The clinical and laboratory data and chest CT images of 51 patients were assessed in a fever observation ward for evidence of COVID-19 between January and February 2020. RESULTS: 24 patients had laboratory-confirmed COVID-19, whereas 27 individuals had negative results. No statistical difference in clinical features was found between COVID-19 and CAP patients, except for diarrhoea. There was a significant difference in lymphocyte and eosinophil counts between COVID-19 and CAP patients. In total, 22 (91.67%) COVID-19 patients had bilateral involvement and multiple lesions according to their lung CT images; the left lower lobe (87.50%) and right lower lobe (95.83%) were affected most often, and all lesions were located in the peripheral zones of the lung. The most common CT feature of COVID-19 was ground-glass opacity, found in 95.83% of patients, compared to 66.67% of CAP patients. CONCLUSION Diarrhoea, lymphocyte counts, eosinophil counts and CT findings (e.g. ground-glass opacity) could help to distinguish COVID-19 from CAP at an early stage of infection, based on findings from our fever observation ward.
COVID-19/diagnostic imaging* ; China ; Community-Acquired Infections/diagnostic imaging* ; Diarrhea/pathology* ; Fever ; Humans ; Lung/diagnostic imaging* ; Retrospective Studies ; SARS-CoV-2 ; Tomography, X-Ray Computed/methods*

ObjectiveTo describe the epidemiologic, clinical, laboratory, and radiological characteristics and prognoses of COVID-19 confirmed patients in a single center in Beijing, China. Methods The study retrospectively included 19 patients with nucleic acid-confirmed SARS-CoV-2 infection at our hospital from January 20 to March 5, 2020. The final follow-up date was March 14, 2020. The epidemiologic and clinical information was obtained through direct communication with the patients or their family members. Laboratory results retrieved from medical records and radiological images were analyzed both qualitatively by two senior chest radiologists as well as quantitatively via an artificial intelligence software. Results We identified 5 family clusters (13/19, 68.4%) from the study cohort. All cases had good clinical prognoses and were either mild (3/19) or moderate (16/19) clinical types. Fever (15/19, 78.9%) and dry cough (11/19, 57.9%) were common symptoms. Two patients received negative results for more than three consecutive viral nucleic acid tests. The longest interval between an initial CT abnormal finding and a confirmed diagnosis was 30 days. One patient's nucleic acid test turned positive on the follow-up examination after discharge. The presence of radiological abnormalities was non-specific for the diagnosis of COVID-19. Conclusions COVID-19 patients with mild or no clinical symptoms are common in Beijing, China. Radiological abnormalities are mostly non-specific and massive CT examinations for COVID-19 screening should be avoided. Analyses of the contact histories of diagnosed cases in combination with clinical, radiological and laboratory findings are crucial for the early detection of COVID-19. Close monitoring after discharge is also recommended.
Adult ; COVID-19/diagnostic imaging* ; COVID-19 Nucleic Acid Testing ; Child ; China ; Female ; Humans ; Lung/diagnostic imaging* ; Male ; Middle Aged ; Retrospective Studies ; SARS-CoV-2 ; Tomography, X-Ray Computed

In December 2019, coronavirus disease 2019 (COVID-19), a new de novo infectious disease, was first identified in Wuhan, China and quickly spread across China and around the world. The etiology was a novel betacoronavirus, the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) (Lu et al., 2020). On Mar. 11, 2020, World Health Organization (WHO) characterized COVID-19 as a global pandemic. As of Mar. 22, 2020, over 292 000 confirmed COVID-19 cases have been reported globally. To date, COVID-19, with its high infectivity, has killed more people than severe acute respiratory syndrome (SARS) and Middle East respiratory syndrome (MERS) combined (Wu and McGoogan, 2020).
Adult ; Betacoronavirus ; COVID-19 ; COVID-19 Testing ; China ; Clinical Laboratory Techniques ; Coronavirus Infections/diagnostic imaging* ; Female ; Fever/virology* ; Humans ; Lymphocyte Count ; Male ; Middle Aged ; Pandemics ; Pneumonia, Viral/diagnostic imaging* ; Radiography, Thoracic ; SARS-CoV-2 ; Tomography, X-Ray Computed ; Treatment Outcome