A deep learning integrated radiomics model for identification of coronavirus disease 2019 using computed tomography.

Since its first outbreak, Coronavirus Disease 2019 (COVID-19) has been rapidly spreading worldwide and caused a global pandemic. Rapid and early detection is essential to contain COVID-19. Here, we first developed a deep learning (DL) integrated radiomics model for end-to-end identification of COVID-19 using CT scans and then validated its clinical feasibility. We retrospectively collected CT images of 386 patients (129 with COVID-19 and 257 with other community-acquired pneumonia) from three medical centers to train and externally validate the developed models. A pre-trained DL algorithm was utilized to automatically segment infected lesions (ROIs) on CT images which were used for feature extraction. Five feature selection methods and four machine learning algorithms were utilized to develop radiomics models. Trained with features selected by L1 regularized logistic regression, classifier multi-layer perceptron (MLP) demonstrated the optimal performance with AUC of 0.922 (95% CI 0.856-0.988) and 0.959 (95% CI 0.910-1.000), the same sensitivity of 0.879, and specificity of 0.900 and 0.887 on internal and external testing datasets, which was equivalent to the senior radiologist in a reader study. Additionally, diagnostic time of DL-MLP was more efficient than radiologists (38 s vs 5.15 min). With an adequate performance for identifying COVID-19, DL-MLP may help in screening of suspected cases.

Clinical and imaging features of pediatric COVID-19.

BACKGROUND: Pediatric COVID-19 is relatively mild and may vary from that in adults. This study was to investigate the epidemic, clinical, and imaging features of pediatric COVID-19 pneumonia for early diagnosis and treatment. METHODS: Forty-one children infected with COVID-19 were analyzed in the epidemic, clinical and imaging data. RESULTS: Among 30 children with mild COVID-19, seven had no symptoms, fifteen had low or mediate fever, and eight presented with cough, nasal congestion, diarrhea, headache, or fatigue. Among eleven children with moderate COVID-19, nine presented with low or mediate fever, accompanied with cough and runny nose, and two had no symptoms. Significantly (P < 0.05) more children had a greater rate of cough in moderate than in mild COVID-19. Thirty children with mild COVID-19 were negative in pulmonary CT imaging, whereas eleven children with moderate COVID-19 had pulmonary lesions, including ground glass opacity in ten (90.9%), patches of high density in six (54.5%), consolidation in three (27.3%), and enlarged bronchovascular bundles in seven (63.6%). The lesions were distributed along the bronchus in five patients (45.5%). The lymph nodes were enlarged in the pulmonary hilum in two patients (18.2%). The lesions were presented in the right upper lobe in two patients (18.1%), right middle lobe in one (9.1%), right lower lobe in six (54.5%), left upper lobe in five (45.5%), and left lower lobe in eight (72.7%). CONCLUSIONS: Children with COVID-19 have mild or moderate clinical and imaging presentations. A better understanding of the clinical and CT imaging helps ascertaining those with negative nucleic acid and reducing misdiagnosis rate for those with atypical and concealed symptoms.

Persistence of SARS-CoV-2 virus RNA in feces: A case series of children.

AIMS: To determine how long SARS-CoV-2 virus RNA persists in fecal specimens in children with COVID-19. METHODS: Retrospectively, ten children with confirmed COVID-19 in the Jinan Infectious Disease Hospital Affiliated to Shandong University were enrolled between January 23, 2020 to March 9, 2020. Epidemiological, clinical, laboratory, and radiological characteristics of the children were analyzed. RT-PCR assays were performed to detect the SARS-CoV-2 virus RNA in the respiratory tract and fecal specimens in the follow-up after discharge. RESULTS: Among ten patients, five (50%) were asymptomatic and five (50%) showed mild symptoms of respiratory illness. The average age of asymptomatic children was younger than that of symptomatic children (p = 0.03). The decreases in white blood cell (WBC) (p = 0.03) and lymphocyte (p = 0.03) counts were more severe in symptomatic patients than those in asymptomatic patients. During the follow-up examination after discharge, seven out of ten patients contained SARS-CoV-2 virus RNA in their fecal specimens, despite all patients showed negative results in respiratory tract specimens. One out of those seven patients relapsed. The median time from onset to being negative results in respiratory tract and fecal specimens was 9 days and 34.43 days, respectively. CONCLUSIONS: SARS-CoV-2 virus RNA persists much longer in the gastrointestinal (GI) tract than that in respiratory tract.

Intravoxel Incoherent Motion (IVIM) Diffusion-Weighted Imaging (DWI) in Patients with Liver Dysfunction of Chronic Viral Hepatitis: Segmental Heterogeneity and Relationship with Child-Turcotte-Pugh Class at 3 Tesla.

BACKGROUND: Few studies focused on the region of interest- (ROI-) related heterogeneity of liver intravoxel incoherent motion (IVIM) diffusion-weighted imaging (DWI). The aim of the study was to evaluate the differences of liver IVIM parameters among liver segments in cirrhotic livers (chronic viral hepatitis). MATERIAL AND METHODS: This was a retrospective study of 82 consecutive patients with chronic liver disease who underwent MRI examination at the Jinan Infectious Diseases Hospital between January 2015 and December 2016. IVIM DWI (seven different b values) was performed on a Siemens 3.0-T MRI scanner. Pure molecular diffusion (D), pseudodiffusion (D ∗), and perfusion fraction (f) in different liver segments were evaluated. RESULTS: f, D, and D ∗ were different among the liver segments (all p < 0.05), indicating heterogeneity in IVIM parameters among liver segments. f was consistently higher in Child-Turcotte-Pugh (CTP) class A compared with CTP class B + C (p < 0.01). D and D ∗ were higher in CTP class A compared with CTP class B + C (p < 0.05). In patients with mean f value of >0.29, the AUC was 0.88 (95% CI: 0.81-0.96), with 86.8% sensitivity and 81.8% specificity for predicting CTP class A from CTP class B + C. CONCLUSION: Liver IVIM could be a promising method for classifying the severity of segmental liver dysfunction of chronic viral hepatitis as evaluated by the CTP class, which provides a noninvasive alternative for evaluating segmental liver dysfunction with accurate selection of ROIs. Potentially it can be used to monitor the progression of CLD and LC in the future.