ABSTRACT
Chest computed tomography (CT) imaging was widely used for diagnosis and staging of severe acute respiratory syndrome coronavirus (SARS-CoV-2). CT can be utilized for initial diagnosis, severity scoring, serial monitoring, and patient status follow-up. For serial monitoring and follow-up, patients need to be scanned multiple times. The tendency in CT imaging is to minimize patient radiation dose. However, CT imaging is still considered as a high radiation dose modality. In this work, we proposed a deep residual neural network-based high quality (full dose) generation from ultra low-dose CT images to decrease the radiation dose for COVID-19 patients. In this multicenter study, we enrolled 1140 subjects with 313 PCR positive COVID-19 patients. The ultra low-dose CT images were analytically simulated, and then a deep residual neural network employed to estimate/generate full-dose images from the corresponding ultra-low-dose images. Various quantitative parameters, including the root mean square error (RMSE), structural similarity index (SSIM), and qualitative visual scoring were implemented to evaluate image quality of the generated CT images. The mean CTDIvol for full-dose images were 6.5 Gy (4.16-10.5 mGy), while, the simulated low-dose images were intended for a mean CTDIvol of 0.72 mGy (0.66-1.02 mGy). Regarding the external validation set (test set), the RMSE declined from 0.16±0.06 to 0.08±0.02 in low-dose and predicted standard-dose CT images, while the SSIM metric increased from 0.89±0.07 to 0.97±0.01, respectively. The highest visual scores (out of 5) were achieved by full-dose images (4.72±0.57) and predicted full-dose images (4.42±0.08). Conversely, ultra-low-dose images received the lowest score (2.78±0.9). In can be concluded that the proposed deep residual network improved image quality of ultra low-dose CT images, thus recovering their diagnostic value. © 2020 IEEE
ABSTRACT
Background: Routine blood testing consists of Complete Blood Count (CBC) indices together with Comprehensive Metabolic Panel (CMP) which have significant roles in both diagnosis and prognosis of the novel coronavirus disease 2019 (COVID-19). Methods: A total number of 942 COVID-19 patients and 400 healthy persons as the control group were enrolled in this study. All patients were admitted to a single center and were divided into two groups according to disease severity (severe or non-severe). Routine laboratory findings of peripheral blood sample were collected and then analyzed. Results: Neutrophil-Lymphocyte Ratio (NLR) had the highest sensitivity and specificity value for COVID-19 diagnosis. Among patients with different severities of COVID-19, the amount of neutrophil, NLR, platelet, hemoglobin, Red cell Distribution Width (RDW) and total bilirubin was significantly different (p<0.01). Conclusion: Some indices of complete blood count and comprehensive metabolic panel have diagnostic and prognostic roles in COVID-19 patients, which are helpful in early diagnosis, predicting severity and adverse outcomes of patients with COVID-19. © 2021 Islamic Republic of Iran Medical Council. All Rights Reserved.
ABSTRACT
Background: Studies have shown that CT could be valuable for prognostic issues in COVID-19. Objectives: To investigate the prognostic factors of early chest CT findings in COVID-19 patients. Methods: This retrospective study included 91 patients (34 women, and 57 men) of real-time reverse transcription polymerase chain reaction (RT-PCR) positive COVID-19 from three hospitals in Iran between February 25, 2020, to March 15, 2020. Patients were divided into two groups as good prognosis, discharged from the hospital and alive without symptoms (48 patients), and poor prognosis, died or needed ICU care (43 patients). The first CT images of both groups that were obtained during the first 8 days of the disease presentation were evaluated considering the pattern, distribution, and underlying disease. The total CT-score was calculated for each patient. Univariate and multivariate analysis with IBM SPSS Statistics v.26 was used to find the prognostic factors. Results: There was a significant correlation between poor prognosis and older ages, dyspnea, presence of comorbidities, especially cardiovascular and comorbidities. Considering CT features, peripheral and diffuse distribution, anterior and paracardiac involve-ment, crazy paving pattern, and pleural effusion were correlated with poor prognosis. There was a correlation between total CT-score and prognosis and an 11.5 score was suggested as a cut-off with 67.4% sensitivity and 68.7% specificity in differentiation of poor prognosis patients (patients who needed ICU admission or died). Multivariate analysis revealed that a model consisting of age, male gender, underlying comorbidity, diffused lesions, total CT-score, and dyspnea would predict the prognosis better. Conclusions: Total chest CT-score and chest CT features can be used as prognostic factors in COVID-19 patients. A multidisciplinary approach would be more accurate in predicting the prognosis.