ABSTRACT
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.
Subject(s)
COVID-19/diagnostic imaging , COVID-19/virology , Deep Learning , Models, Biological , SARS-CoV-2/physiology , Tomography, X-Ray Computed , Adult , Algorithms , Female , Humans , Male , Middle Aged , ROC Curve , RadiologistsABSTRACT
BACKGROUND: The 2019 novel coronavirus (COVID-19) presents a major threat to public health and has rapidly spread worldwide since the outbreak in Wuhan, Hubei Province, China in 2019. To date, there have been few reports of the varying degrees of illness caused by the COVID-19. CASE PRESENTATION: A case of 68-year-old female with COVID-19 pneumonia who had constant pain in the right upper quadrant of her abdomen during her hospitalization that was finally diagnosed as acute cholecystitis. Ultrasound-guided percutaneous transhepatic gallbladder drainage (PTGD) was performed, and the real-time fluorescence polymerase chain reaction (RT-PCR) COVID-19 nucleic acid assay of the bile was found to be negative. PTGD, antibacterial and anti-virus combined with interferon inhalation treatment were successful. CONCLUSION: The time course of chest CT findings is typical for COVID-19 pneumonia. PTGD is useful for acute cholecystitis in COVID-19 patients. Acute cholecystitis is likely to be caused by COVID-19 .