RESUMEN
BACKGROUND: The coronavirus disease 2019 (COVID-19) has rapidly become a pandemic worldwide. The value of chest computed tomography (CT) is debatable during the treatment of COVID-19 patients. Compared with traditional chest X-ray radiography, quantitative CT may supply more information, but its value on COVID-19 patients was still not proven. METHODS: An automatic quantitative analysis model based on a deep network called VB-Net for infection region segmentation was developed. A quantitative analysis was performed for patients diagnosed as severe COVID 19. The quantitative assessment included volume and density among the infectious area. The primary clinical outcome was the existence of acute respiratory distress syndrome (ARDS). A univariable and multivariable logistic analysis was done to explore the relationship between the quantitative results and ARDS existence. RESULTS: The VB-Ne model was sensitive and stable for pulmonary lesion segmentation, and quantitative analysis indicated that the total volume and average density of the lung lesions were not related to ARDS. However, lesions with specific density changes showed some influence on the risk of ARDS. The proportion of lesion density from -549 to -450 Hounsfield unit (HU) was associated with increased risk of ARDS, while the density was ranging from -149 to -50 HU was related to a lowered risk of ARDS. CONCLUSIONS: The automatic quantitative model based on VB-Ne can supply useful information for ARDS risk stratification in COVID-19 patients during treatment.
RESUMEN
RATIONALE AND OBJECTIVES: We aimed to assess the prevalence of significant computed tomographic(CT) manifestations and describe some notable features based on chest CT images, as well as the main clinical features of patients with coronavirus disease 2019(COVID-19). MATERIALS AND METHODS: A systematic literature search of PubMed, EMBASE, the Cochrane Library, and Web of Science was performed to identify studies assessing CT features, clinical, and laboratory results of COVID-19 patients. A single-arm meta-analysis was conducted to obtain the pooled prevalence and 95% confidence interval (95% CI). RESULTS: A total of 14 articles (including 1115 patients) based on chest CT images were retrieved. In the lesion patterns on chest CTs, we found that pure ground-glass opacities (GGO) (69%, 95% CI 58-80%), consolidation (47%, 35-60%) and "air bronchogram sign" (46%, 25-66%) were more common than the atypical lesion of "crazy-paving pattern" (15%, 8-22%). With regard to disease extent and involvement, 70% (95% CI 46-95%) of cases showed a location preference for the right lower lobe, 65% (58-73%) of patients presented with ≥3 lobes involvement, and meanwhile, 42% (32-53%) of patients had involvement of all five lobes, while 67% (55-78%) of patients showed a predominant peripheral distribution. An understanding of some important CT features might be helpful for medical surveillance and management. In terms of clinical features, muscle soreness (21%, 95% CI 15-26%) and diarrhea (7%, 4-10%) were minor symptoms compared to fever (80%, 74-87%) and cough (53%, 33-72%). CONCLUSION: Chest CT manifestations in patients with COVID-19, as well as its main clinical characteristics, might be helpful in disease evolution and management.