Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 2 de 2
Add filters

Document Type
Main subject
Year range
Diagnostics ; 11(11):1942, 2021.
Article in English | MDPI | ID: covidwho-1480630


(1) Background: COVID-19 has been global epidemic. This work aims to extract 3D infection from COVID-19 CT images;(2) Methods: Firstly, COVID-19 CT images are processed with lung region extraction and data enhancement. In this strategy, gradient changes of voxels in different directions respond to geometric characteristics. Due to the complexity of tubular tissues in lung region, they are clustered to the lung parenchyma center based on their filtered possibility. Thus, infection is improved after data enhancement. Then, deep weighted UNet is established to refining 3D infection texture, and weighted loss function is introduced. It changes cost calculation of different samples, causing target samples to dominate convergence direction. Finally, the trained network effectively extracts 3D infection from CT images by adjusting driving strategy of different samples. (3) Results: Using Accuracy, Precision, Recall and Coincidence rate, 20 subjects from a private dataset and eight subjects from Kaggle Competition COVID-19 CT dataset tested this method in hold-out validation framework. This work achieved good performance both in the private dataset (99.94–00.02%, 60.42–11.25%, 70.79–09.35% and 63.15–08.35%) and public dataset (99.73–00.12%, 77.02–06.06%, 41.23–08.61% and 52.50–08.18%). We also applied some extra indicators to test data augmentation and different models. The statistical tests have verified the significant difference of different models. (4) Conclusions: This study provides a COVID-19 infection segmentation technology, which provides an important prerequisite for the quantitative analysis of COVID-19 CT images.

BMC Infect Dis ; 21(1): 1040, 2021 Oct 07.
Article in English | MEDLINE | ID: covidwho-1455942


BACKGROUND: Coronavirus disease 2019 (COVID-19) is a declared global pandemic, causing a lot of death. How to quickly screen risk population for severe patients is essential for decreasing the mortality. Many of the predictors might not be available in all hospitals, so it is necessary to develop a simpler screening tool with predictors which can be easily obtained for wide wise. METHODS: This retrospective study included all the 813 confirmed cases diagnosed with COVID-19 before March 2nd, 2020 in a city of Hubei Province in China. Data of the COVID-19 patients including clinical and epidemiological features were collected through Chinese Disease Control and Prevention Information System. Predictors were selected by logistic regression, and then categorized to four different level risk factors. A screening tool for severe patient with COVID-19 was developed and tested by ROC curve. RESULTS: Seven early predictors for severe patients with COVID-19 were selected, including chronic kidney disease (OR 14.7), age above 60 (OR 5.6), lymphocyte count less than < 0.8 × 109 per L (OR 2.5), Neutrophil to Lymphocyte Ratio larger than 4.7 (OR 2.2), high fever with temperature ≥ 38.5℃ (OR 2.2), male (OR 2.2), cardiovascular related diseases (OR 2.0). The Area Under the ROC Curve of the screening tool developed by above seven predictors was 0.798 (95% CI 0.747-0.849), and its best cut-off value is > 4.5, with sensitivity 72.0% and specificity 75.3%. CONCLUSIONS: This newly developed screening tool can be a good choice for early prediction and alert for severe case especially in the condition of overload health service.

COVID-19 , Humans , Male , Mass Screening , Retrospective Studies , Risk Factors , SARS-CoV-2