Related Experiment Video
Updated: Dec 5, 2025
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
A model based on CT radiomic features for predicting RT-PCR becoming negative in coronavirus disease 2019 (COVID-19)
Quan Cai1, Si-Yao Du2, Si Gao2
1Department of Emergency Medicine, The First Affiliated Hospital of China Medical University, Nanjing North Street 155, Shenyang, 110001, Liaoning Province, China.
Insights
A new model using chest CT radiomic features and clinical data can predict negative reverse transcription-polymerase chain reaction (RT-PCR) results in COVID-19 patients. This approach aids in determining the optimal timing for repeat RT-PCR testing, reducing hospital stays and medical waste.
Area of Science:
- Radiology
- Medical Imaging
- Artificial Intelligence in Medicine
Background:
- Coronavirus disease 2019 (COVID-19) became a global pandemic.
- Negative reverse transcription-polymerase chain reaction (RT-PCR) is crucial for patient discharge.
- Repeated RT-PCR testing causes medical waste and prolonged hospital stays.
Purpose of the Study:
- To assess a predictive model for RT-PCR negativity in COVID-19 patients.
- The model integrates chest computed tomography (CT) radiomic features and clinical data.
- To optimize RT-PCR retesting timing during clinical treatment.
Main Methods:
- Retrospective study of 203 mild COVID-19 patients (141 training, 62 testing).
- Deep learning for lung abnormality segmentation on CT scans.
- Extraction of CT quantitative and radiomic features.
- Multivariate logistic regression model development using selected features and clinical data.
Main Results:
- The RT-PCR-negative group showed a longer time from symptom onset to CT exam (median 23 vs. 16 days).
- Nine CT radiomic features and time interval were selected for the model.
- The model achieved Area Under the Curve (AUC) values of 0.811 (training) and 0.812 (testing).
- Sensitivity/specificity were 76.5%/62.5% (training) and 78.4%/60.0% (testing).
Conclusions:
- A combined model of CT radiomic features and clinical data effectively predicts RT-PCR negativity.
- This model can guide the timing for repeat RT-PCR testing in COVID-19 patients.
- Potential to improve patient management and reduce healthcare resource utilization.
Background:
Coronavirus disease 2019 (COVID-19) has emerged as a global pandemic. According to the diagnosis and treatment guidelines of China, negative reverse transcription-polymerase chain reaction (RT-PCR) is the key criterion for discharging COVID-19 patients. However, repeated RT-PCR tests lead to medical waste and prolonged hospital stays for COVID-19 patients during the recovery period. Our purpose is to assess a model based on chest computed tomography (CT) radiomic features and clinical characteristics to predict RT-PCR negativity during clinical treatment.
Methods:
From February 10 to March 10, 2020, 203 mild COVID-19 patients in Fangcang Shelter Hospital were retrospectively included (training: n = 141; testing: n = 62), and clinical characteristics were collected. Lung abnormalities on chest CT images were segmented with a deep learning algorithm. CT quantitative features and radiomic features were automatically extracted. Clinical characteristics and CT quantitative features were compared between RT-PCR-negative and RT-PCR-positive groups. Univariate logistic regression and Spearman correlation analyses identified the strongest features associated with RT-PCR negativity, and a multivariate logistic regression model was established. The diagnostic performance was evaluated for both cohorts.
Results:
The RT-PCR-negative group had a longer time interval from symptom onset to CT exams than the RT-PCR-positive group (median 23 vs. 16 days, p < 0.001). There was no significant difference in the other clinical characteristics or CT quantitative features. In addition to the time interval from symptom onset to CT exams, nine CT radiomic features were selected for the model. ROC curve analysis revealed AUCs of 0.811 and 0.812 for differentiating the RT-PCR-negative group, with sensitivity/specificity of 0.765/0.625 and 0.784/0.600 in the training and testing datasets, respectively.
Conclusion:
The model combining CT radiomic features and clinical data helped predict RT-PCR negativity during clinical treatment, indicating the proper time for RT-PCR retesting.
