Staging and typing of chest CT images: A quantitative analysis based on an ambispective observational cohort study of 125 patients with COVID-19 in Xiangyang, China
Huang, G.; Wang, Y.; Wu, X.; Qu, G.; Chen, J.; Yu, H.; Zhang, M.; Wang, L.; Ai, J.; Zhu, H.; Chen, L.; Pei, B.
Show abstract
BackgroundThe stage of CT images was rarely studied and the relationship between the severity of Coronavirus Disease 2019 (COVID-19) and CT images has not been studied based on systematic quantitative analysis currently. PurposeTo investigate the staging duration and classification of CT images of patients with COVID-19 based on quantitative analysis. Materials and MethodsThis is an ambispective observational cohort study based on 125 patients with COVID-19 from Jan 23 to Feb 28, 2020. The stage of CT and pulmonary lesion size were quantitatively analyzed. The categorical regression analysis based on optimal scale (CATREG) was performed to evaluate the association of CT score, age, and gender with the clinical type. ResultsThe CT images of 125 patients with COVID-19 (50.13 {+/-} 16.91 years, 66 women) were analyzed in this study. Except for pre-early stage, the duration of early, progression-consolidation, and dissipation stage of CT images was 3.40 {+/-} 2.31, 10.07 {+/-} 4.91, and 20.60 {+/-} 7.64 days, respectively. The median CT score was 5.00 (2.00-8.50) during the first 30 days, which reached a peak on the 11th day. Significant differences were found between the median CT scores of different clinical types (P<0.05). Besides, the age was correlated with the clinical type (P<0.001), the CT scores of 0.00-11.50, 11.50-16.00, and 16.00-20.00 were separately correlated with the moderate, severe, and critical type with the output accuracy 69.60%. ConclusionThe four-stage staging method based on quantitative analysis is consistent with the change rules of staging features and COVID-19. Quantitative study by scoring pulmonary lesion sizes accurately revealed the evolvement of pulmonary lesions and differences between different clinical types. SummaryQuantitative study of the stage duration and classification of chest CT images can objectively reveal the relationship between Coronavirus Disease 2019 (COVID-19) and chest CT images. Key Results1. A four-stage staging method was proposed. Except for pre-early stage, the duration of early, progression-consolidation, and dissipation stage of CT images was 3.40 {+/-} 2.31, 10.07 {+/-} 4.91, and 20.60 {+/-} 7.64 days, respectively. 2. The severer the disease, the higher the median CT scores and their peak value. 3. The CT scores of 0.00-11.50, 11.50-16.00, and 16.00-20.00 were separately correlated with the moderate, severe, and critical type.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Quantitative analysis of chest computed tomography of COVID-19 pneumonia using a software widely used in Japan 98%
- Accuracy of deep learning based computed tomography diagnostic system of COVID-19: a consecutive sampling external validation cohort study 96%
- Survival analysis of hospital length of stay of novel coronavirus (COVID-19) pneumonia patients in Sichuan, China 95%
Similar papers in this journal
- Upregulation of ARHGAP9 is correlated with poor prognosis and immune infiltration in clear cell renal cell carcinoma 93%
- Effect of Tai Ji and/or Qigong on Patients with Stable Chronic Obstructive Pulmonary Disease A protocol for meta-analysis and systematic review 92%
- The PBL teaching method in Neurology Education in the Traditional Chinese Medicine undergraduate students: An Observational Study 92%
Similar papers in this journal
- A Novel Triage Tool of Artificial Intelligence-Assisted Diagnosis Aid System for Suspected COVID-19 Pneumonia in Fever Clinics 96%
- Changes in the expression of interleukin-10 in myocardial infarction and its relationship with macrophage activation and cell apoptosis 94%
- A follow-up study of children infected with SARS-CoV-2 from Western China 92%
Similar papers in this journal
- Predicting EGFR mutation status in lung adenocarcinoma presenting as ground-glass opacity: utilizing radiomics model in clinical translation 97%
- Automated airway quantification associates with mortality in idiopathic pulmonary fibrosis 91%
- Prediction of oncogene mutation status in non-small cell lung cancer: A systematic review and meta-analysis with a special focus on artificial-intelligence-based methods 91%
Similar papers in this journal
- Patients at risk of pulmonary fibrosis Post Covid-19: Epidemiology, pulmonary sequelaes and humoral response 93%
- Normalized Semi-Covariance Co-Efficiency Analysis of Spike Proteins from SARS-CoV-2 variant Omicron and Other Coronaviruses for their Infectivity and Virulence 91%
- Adverse events following COVID-19 virus vaccination in Japanese young population: The first cross-sectional study conducted by a questionnaire survey after the first-time-injection 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.