Dataset Information

CT radiomics can help screen the Coronavirus disease 2019 (COVID-19): a preliminary study.

ABSTRACT: The Coronavirus disease 2019 (COVID-19) is raging across the world. The radiomics, which explores huge amounts of features from medical image for disease diagnosis, may help the screen of the COVID-19. In this study, we aim to develop a radiomic signature to screen COVID-19 from CT images. We retrospectively collect 75 pneumonia patients from Beijing Youan Hospital, including 46 patients with COVID-19 and 29 other types of pneumonias. These patients are divided into training set (n = 50) and test set (n = 25) at random. We segment the lung lesions from the CT images, and extract 77 radiomic features from the lesions. Then unsupervised consensus clustering and multiple cross-validation are utilized to select the key features that are associated with the COVID-19. In the experiments, while twenty-three radiomic features are found to be highly associated with COVID-19, four key features are screened and used as the inputs of support vector machine to build the radiomic signature. We use area under the receiver operating characteristic curve (AUC) and calibration curve to assess the performance of our model. It yields AUCs of 0.862 and 0.826 in the training set and the test set respectively. We also perform the stratified analysis and find that its predictive ability is not affected by gender, age, chronic disease and degree of severity. In conclusion, we investigate the value of radiomics in screening COVID-19, and the experimental results suggest the radiomic signature could be a potential tool for diagnosis of COVID-19.

SUBMITTER: Fang M

PROVIDER: S-EPMC7166002 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivesTo develop and validate a radiomic model to predict the rapid progression (defined as volume growth of pneumonia lesions > 50% within seven days) in patients with coronavirus disease 2019 (COVID-19).MethodsPatients with laboratory-confirmed COVID-19 who underwent longitudinal chest CT between January 01 and February 18, 2020 were included. A total of 1316 radiomic features were extracted from the lung parenchyma window for each CT. The least absolute shrinkage and selection operator (LASSO), Relief, Las Vegas Wrapper (LVW), L1-norm-Support Vector Machine (L1-norm-SVM), and recursive feature elimination (RFE) were applied to select the features that associated with rapid progression. Four machine learning classifiers were used for modeling, including Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), and Decision Tree (DT). Accordingly, 20 radiomic models were developed on the basis of 296 CT scans and validated in 74 CT scans. Model performance was determined by the receiver operating characteristic curve.ResultsA total of 107 patients (median age, 49.0 years, interquartile range, 35-54) were evaluated. The patients underwent a total of 370 chest CT scans with a median interval of 4 days (interquartile range, 3-5 days). The combination methods of L1-norm SVM and SVM with 17 radiomic features yielded the highest performance in predicting the likelihood of rapid progression of pneumonia lesions on next CT scan, with an AUC of 0.857 (95% CI: 0.766-0.947), sensitivity of 87.5%, and specificity of 70.7%.ConclusionsOur radiomic model based on longitudinal chest CT data could predict the rapid progression of pneumonia lesions, which may facilitate the CT follow-up intervals and reduce the radiation.Advances in knowledgeRadiomic features extracted from the current chest CT have potential in predicting the likelihood of rapid progression of pneumonia lesions on the next chest CT, which would improve clinical decision-making regarding timely treatment.

Project description:OBJECTIVE:The objective of this systematic review was to evaluate the key imaging manifestations of COVID-19 on chest CT in adult patients by providing a comprehensive review of the published literature. METHODS:We performed a systematic literature search from the PubMed, Google Scholar, Embase, and WHO databases for studies mentioning the chest CT imaging findings of adult COVID-19 patients. RESULTS:A total of 45 studies comprising 4410 patients were included. Ground glass opacities (GGO), in isolation (50.2%) or coexisting with consolidations (44.2%), were the most common lesions. Distribution of GGOs was most commonly bilateral, peripheral/subpleural, and posterior with predilection for lower lobes. Common ancillary findings included pulmonary vascular enlargement (64%), intralobular septal thickening (60%), adjacent pleural thickening (41.7%), air bronchograms (41.2%), subpleural lines, crazy paving, bronchus distortion, bronchiectasis, and interlobular septal thickening. CT in early follow-up period generally showed an increase in size, number, and density of GGOs, with progression into mixed areas of GGOs plus consolidations and crazy paving, peaking at 10-11 days, before gradually resolving or persisting as patchy fibrosis. While younger adults more commonly had GGOs, extensive/multilobar involvement with consolidations was prevalent in the older population and those with severe disease. CONCLUSION:This review describes the imaging features for diagnosis, stratification, and follow-up of COVID-19 patients. The most common CT manifestations are bilateral, peripheral/subpleural, posterior GGOs with or without consolidations with a lower lobe predominance. It is pertinent to be familiar with the various imaging findings to positively impact the management of these patients. KEY POINTS:• Ground glass opacities (GGOs), whether isolated or coexisting with consolidations, in bilateral and subpleural distribution, are the most prevalent chest CT findings in adult COVID-19 patients. • Follow-up CT shows a progression of GGOs into a mixed pattern, reaching a peak at 10-11 days, before gradually resolving or persisting as patchy fibrosis. • Younger people tend to have more GGOs. Older or sicker people tend to have more extensive involvement with consolidations.

Dataset Information

CT radiomics can help screen the Coronavirus disease 2019 (COVID-19): a preliminary study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets