Diagnostic performance of CO-RADS for COVID-19: a systematic review and meta-analysis.

OBJECTIVES: To investigate the diagnostic performance of the coronavirus disease 2019 (COVID-19) Reporting and Data System (CO-RADS) for detecting COVID-19. METHODS: We searched PubMed, EMBASE, MEDLINE, Web of Science, Cochrane Library, and Scopus database until September 21, 2021. Statistical analysis included data pooling, forest plot construction, heterogeneity testing, meta-regression, and subgroup analyses. RESULTS: We included 24 studies with 8382 patients. The pooled sensitivity and specificity and the area under the curve (AUC) of CO-RADS ≥ 3 for detecting COVID-19 were 0.89 (95% confidence interval (CI) 0.85-0.93), 0.68 (95% CI 0.60-0.75), and 0.87 (95% CI 0.84-0.90), respectively. The pooled sensitivity and specificity and AUC of CO-RADS ≥ 4 were 0.83 (95% CI 0.79-0.87), 0.84 (95% CI 0.78-0.88), and 0.90 (95% CI 0.87-0.92), respectively. Cochran's Q test (p < 0.01) and Higgins I2 heterogeneity index revealed considerable heterogeneity. Studies with both symptomatic and asymptomatic patients had higher specificity than those with only symptomatic patients using CO-RADS ≥ 3 and CO-RADS ≥ 4. Using CO-RADS ≥ 4, studies with participants aged < 60 years had higher sensitivity (0.88 vs. 0.80, p = 0.02) and lower specificity (0.77 vs. 0.87, p = 0.01) than studies with participants aged > 60 years. CONCLUSIONS: CO-RADS has favorable performance in detecting COVID-19. CO-RADS ≥ 3/4 might be applied as cutoff values given their high sensitivity and specificity. However, there is a need for more well-designed studies on CO-RADS. KEY POINTS: • CO-RADS shows a favorable performance in detecting COVID-19. • CO-RADS ≥ 3 had a high sensitivity 0.89 (95% CI 0.85-0.93), and it may prove advantageous in screening the potentially infected people to prevent the spread of COVID-19. • CO-RADS ≥ 4 had high specificity 0.84 (95% CI 0.78-0.88) and may be more suitable for definite diagnosis of COVID-19.

A Quantitative and Radiomics approach to monitoring ARDS in COVID-19 patients based on chest CT: a retrospective cohort study.

Rationale: Acute respiratory distress syndrome (ARDS) is one of the major reasons for ventilation and intubation management of COVID-19 patients but there is no noninvasive imaging monitoring protocol for ARDS. In this study, we aimed to develop a noninvasive ARDS monitoring protocol based on traditional quantitative and radiomics approaches from chest CT. Methods: Patients diagnosed with COVID-19 from Jan 20, 2020 to Mar 31, 2020 were enrolled in this study. Quantitative and radiomics data were extracted from automatically segmented regions of interest (ROIs) of infection regions in the lungs. ARDS existence was measured by Pa02/Fi02 <300 in artery blood samples. Three different models were constructed by using the traditional quantitative imaging metrics, radiomics features and their combinations, respectively. Receiver operating characteristic (ROC) curve analysis was used to assess the effectiveness of the models. Decision curve analysis (DCA) was used to test the clinical value of the proposed model. Results: The proposed models were constructed using 352 CT images from 86 patients. The median age was 49, and the male proportion was 61.9%. The training dataset and the validation dataset were generated by randomly sampling the patients with a 2:1 ratio. Chi-squared test showed that there was no significant difference in baseline of the enrolled patients between the training and validation datasets. The areas under the ROC curve (AUCs) of the traditional quantitative model, radiomics model and combined model in the validation dataset was 0.91, 0.91 and 0.94, respectively. Accordingly, the sensitivities were 0.55, 0.82 and 0.58, while the specificities were 0.97, 0.86 and 0.98. The DCA curve showed that when threshold probability for a doctor or patients is within a range of 0 to 0.83, the combined model adds more net benefit than "treat all" or "treat none" strategies, while the traditional quantitative model and radiomics model could add benefit in all threshold probability. Conclusions: It is feasible to monitor ARDS from CT images using radiomics or traditional quantitative analysis in COVID-19. The radiomics model seems to be the most practical one for possible clinical use. Multi-center validation with a larger number of samples is recommended in the future.

Quantitative analysis of chest CT imaging findings with the risk of ARDS in COVID-19 patients: a preliminary study.

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.