OBJECTIVE: To explore the quantitative analysis results of different patterns of chest computed tomography (CT) in patients with coronavirus infection and its relationship with viral load and pathophysiological status. METHODS: A retrospective clinical cohort study was conducted. Patients with coronavirus infection admitted to Qingdao Municipal Hospital from June 9 to 15, 2023 (all patients underwent chest CT examination within 24 hours after diagnosis) were enrolled. The patients were divided into coronavirus infection non-pneumonia group and coronavirus infection associated pneumonia group according to CT findings. Relevant baseline data, such as demographic characteristics, chest CT characteristics, and laboratory indicators within 12 hours before and after CT examination were collected from each group. Spearman correlation test was used to quantitatively analyze the correlation between CT features and laboratory indicators. The receiver operator characteristic curve (ROC curve) was drawn to evaluate the predictive value of each laboratory index for pneumonia in patients infected with coronavirus. Multiple linear regression analysis was used to explore the relationship between different CT patterns such as ground-glass opacity (GGO) and consolidation and ventilatory oxygenation status. RESULTS: A total of 171 patients were enrolled, including 44 patients in the coronavirus infection non-pneumonia group and 127 patients in the coronavirus infection associated pneumonia group (the incidence of pneumonia was 74.3%). Compared with patients with coronavirus infection alone, patients with coronavirus infection associated pneumonia had significantly lower lymphocyte count (LYM), oxygenation index (PaO₂/FiO₂), total lung capacity, GGO volume and GGO ratio, and significantly higher C-reactive protein (CRP), neutrophil/lymphocyte ratio (NLR), D-dimer, fraction of inspired oxygen (FiO₂) level, real volume variation and consolidation ratio, the differences were all statistically significant. There were no statistically significant differences in the nucleocapin protein (N) gene cycle threshold (Ct) value and open reading frame (ORF) gene Ct value between the two groups. ROC curve analysis showed that, after adjusting for age, gender, CRP level and other related factors, compared with N gene Ct value, ORF gene Ct value, N gene Ct value+LYM, ORF gene Ct value+LYM, the LYM had the most potential diagnosis power for coronavirus infection associated pneumonia. The area under the ROC curve (AUC) of LYM for predicting coronavirus infection was 0.703. When the cut-off value of LYM was 0.7×10⁹/L, the sensitivity was 55.5%, and the specificity was 79.5%, respectively. Multiple linear regression analysis showed that, when adjusted for consolidation ratio, age, gender, Hb and D-dimer levels, the GGO ratio in patients with coronavirus infection associated pneumonia was correlated with PaO₂/FiO₂ (β = -2.18, P < 0.001). When adjusted for GGO ratio, age, sex, Hb and D-dimer levels, the proportion of consolidation in patients with coronavirus infection associated pneumonia was correlated with PaCO₂ (β = 0.36, P = 0.004). When adjusted for GGO ratio, the proportion of consolidation in patients with coronavirus infection associated pneumonia was also associated with NLR (β = 0.79, P = 0.006). CONCLUSIONS LYM could be a potential marker for predicting coronavirus associated pneumonia, and the correlation seems to be independent of viral load. In addition, in the analysis of imaging features, GGO is associated with hypoxia, while consolidation is associated with PaCO₂ level and inflammation. The increased proportion of consolidation in the whole lung may be detrimental to lung ventilation.
Humans ; Tomography, X-Ray Computed/methods* ; Retrospective Studies ; COVID-19/diagnostic imaging* ; Viral Load ; Coronavirus Infections/diagnostic imaging* ; ROC Curve ; Male ; Lung/diagnostic imaging* ; Female ; Middle Aged ; C-Reactive Protein/analysis*

OBJECTIVE: To summarize clinical predictors and imaging characteristics of critically ill children infected with SARS-CoV-2 Omicron with neurological complications in Shenzhen during the peak of the first round of infections. METHODS: The clinical data of 11 critically ill children with neurological complications infected with SARS-CoV-2 Omicron in Shenzhen Children's Hospital from December 12 to 31, 2022, were retrospectively collected and analyzed. Laboratory test results related to liver parenchymal injury, histiocytic injury, inflammation, and coagulation function were collected, and imaging characteristics including CT and/or magnetic resonance imaging (MRI) were analyzed. The differences in CT/MRI score, acute necrotizing encephalopathy severity scale (ANE-SS) score and total score (CT/MRI score + ANE-SS score) were compared between the two groups with different prognosis during hospitation. RESULTS: Among 11 children, 7 were male and 4 were female. The age ranged from 10 months to 16 years. There were 5 cases of acute necrotizing encephalopathy (ANE) and 6 cases of acute fulminant cerebral edema (AFCE). During hospitalization, 3 patients survived and 8 patients died of multiple organ dysfunction syndrome (MODS), including 2 cases of ANE and 6 cases of AFCE. All cases had fever (> 38.5 centigrade), and 3 cases had ultra-high fever (> 41 centigrade). Within 48 hours of onset, all cases had disorders of consciousness and 9 cases had seizures. The 8 dead children had complications with multisystem involvement, including shock, respiratory failure, disseminated intravascular coagulation (DIC), liver failure, renal failure or myocardial damage, and the laboratory predictors related to hepatocellular injury [alanine aminotransferase (ALT), aspartate aminotransferase (AST)], histocyte injury [creatine kinase (CK), lactate dehydrogenase (LDH)], inflammation [procalcitonin (PCT), interleukin-6 (IL-6), serum ferritin (SF)], coagulation function (D-dimer) and blood glucose (Glu) increased in different quantities, of which PCT was specifically increased in 6 cases with AFCE, PLT was specifically decreased in 3 cases with AFCE, and ALT and LDH were significantly increased in 2 cases with ANE. Imaging analysis showed subarachnoid hemorrhage, basal ganglia and thalamus lesions in all 6 cases with AFCE, while thalamus lesions in all 5 cases with ANE. The ANE-SS score of 8 deceased children ranged from 2 to 7 (of which 6 cases were ≥ 5), and the ANE-SS score of 3 surviving children ranged from 0 to 2. Eight dead children had a CT/MRI score of 1-4 (of which 6 cases were 4), and 3 surviving children had a CT/MRI score of 1-2 (of which 2 cases were 1). The total score of 8 deceased children was 6-10 (of which 6 cases ≥ 8), and 3 surviving children was 1-4. CONCLUSIONS The neurological complications of critically ill children infected with SARS-CoV-2 Omicron in Shenzhen progressed rapidly to ANE and AFCE, with high mortality. High fever (> 40 centigrade), convulsion/disturbance of consciousness, and multiple organ failure were the most common symptoms in ANE and AFCE cases. PCT increased and PLT decreased specifically in AFCE cases. Poor prognosis (death) was more common in age < 4 years old, predictors of ALT, AST, CK, LDH, PCT, D-dimer, Glu, IL-6 increased significantly, PLT decreased significantly. The common imaging feature of ANE and AFCE is the involvement of dorsal thalamus, a new imaging sign of AFCE (subarachnoid hemorrhage) was found. The higher the ANE-SS score, CT/MRI score and total score, the greater the risk of death.
Humans ; Male ; Child ; Female ; Infant ; Child, Preschool ; SARS-CoV-2 ; Interleukin-6 ; Retrospective Studies ; Critical Illness ; COVID-19/complications* ; Procalcitonin ; Inflammation ; Brain Diseases/diagnostic imaging*

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

PROPOSE: In this study, we re-assessed the criteria defined by the radiological society of North America (RSNA) to determine novel radiological findings helping the physicians differentiating COVID-19 from pulmonary contusion. METHODS: All trauma patients with blunt chest wall trauma and subsequent pulmonary contusion, COVID-19-related signs and symptoms before the trauma were enrolled in this retrospective study from February to May 2020. Included patients (Group P) were then classified into two groups based on polymerase chain reaction tests (Group Pa for positive patients and Pb for negative ones). Moreover, 44 patients from the pre-pandemic period (Group PP) were enrolled. They were matched to Group P regarding age, sex, and trauma-related scores. Two radiologists blindly reviewed the CT images of all enrolled patients according to criteria defined by the RSNA criteria. The radiological findings were compared between Group P and Group PP; statistically significant ones were re-evaluated between Group Pa and Group Pb thereafter. Finally, the sensitivity and specificity of each significant findings were calculated. The Chi-square test was used to compare the radiological findings between Group P and Group PP. RESULTS: In the Group PP, 73.7% of all ground-glass opacities (GGOs) and 80% of all multiple bilateral GGOs were detected (p < 0.001 and p = 0.25, respectively). Single bilateral GGOs were only seen among the Group PP. The Chi-square tests showed that the prevalence of diffused GGOs, multiple unilateral GGOs, multiple consolidations, and multiple bilateral consolidations were significantly higher in the Group P (p = 0.001, 0.01, 0.003, and 0.003, respectively). However, GGOs with irregular borders and single consolidations were more significant among the Group PP (p = 0.01 and 0.003, respectively). Of note, reticular distortions and subpleural spares were exclusively detected in the Group PP. CONCLUSION We concluded that the criteria set by RSNA for the diagnosis of COVID-19 are not appropriate in trauma patients. The clinical signs and symptoms are not always useful either. The presence of multiple unilateral GGOs, diffused GGOs, and multiple bilateral consolidations favor COVID-19 with 88%, 97.62%, and 77.7% diagnostic accuracy.
COVID-19 ; Contusions/diagnostic imaging* ; Humans ; Lead ; Lung/diagnostic imaging* ; Lung Injury/etiology* ; Retrospective Studies ; SARS-CoV-2 ; Tomography, X-Ray Computed/methods*

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*

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

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

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

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*

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