Coronavirus Disease 2019 (COVID-19) is a global pandemic that poses significant health risks. The sensitivity of diagnostic tests for COVID-19 is low due to irregularities in the han- dling of the specimens. We propose a deep learning framework that identifies COVID-19 from medical images as an effective auxiliary testing method to improve diagnostic sensitiv- ity. We use pseudo-coloring methods and a platform for annotating X-ray and computed tomography (CT) images to train and evaluate the convolutional neural network (CNN). The CNN achieves a performance similar to that of experts and provides high scores for multiple statistical indices, with F1 scores above 96% and specificity over 99%. Heatmaps are used to visualize the salient features extracted by the CNN. The CNN-based regression provides strong correlations between the lesion areas in the images and five clinical indicators, im- proving the interpretation accuracy of the classification framework. The proposed method represents a potential computer-aided diagnosis method for COVID-19 in clinical practice.
Purpose: The incidence of venous thromboembolism (VTE) in Cushing’s disease (CD) is about ten times higher than that in general population, which tends to be underestimated due to the missed detection of asymptomatic VTE events. VTE can occur at any stage of CD, mainly during the postoperative period. We aim to investigate the incidence and prothrombotic risk factors of postoperative VTE in CD patients and to further develop an assessment model to identify those at high risk of postoperative VTE events. Methods: We performed a retrospective study in 82 CD patients by evaluating their clinical, hormonal, and coagulation parameters, as well as ultrasonography and pulmonary angio-CT when necessary. Results: Nineteen patients (23.2%) developed VTE events, of which 14 developed VTE after endoscopic transsphenoidal surgery (ETS). The group of CD patients with postoperative VTE were elder (p<0.001), had more infection (p<0.05) and reduced mobility (p<0.05), higher HbA1c, and more severe impairment of glucose tolerance than those without. By using stepwise regression analysis, we obtained 4 independent risk factors for postoperative VTE: age, 2-h insulin in OGTT, current infection, and postoperative bedtime. Then a VTE risk assessment nomogram model was established to predict the patients at high risk of VTE. In this nomogram model, 70 patients (85.7%) were classified correctly, and area under the curve was 0.899 (95%CI, 0.787-0.999). Conclusion: Advanced perioperative assessment needs to be taken to screen those with high VTE risks in CD patients. Moreover, physical movement and antithrombotic prophylaxis seems to be warranted during perioperative period.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.