CT radiomics facilitates more accurate diagnosis of COVID-19 pneumonia: compared with CO-RADS
Limited data was available for rapid and accurate detection of COVID-19 using CT-based machine learning model. This study aimed to investigate the value of chest CT radiomics for diagnosing COVID-19 pneumonia compared with clinical model and COVID-19 reporting and data system (CO-RADS), and develop an open-source diagnostic tool with the constructed radiomics model.
This study enrolled 115 laboratory-confirmed COVID-19 and 435 non-COVID-19 pneunomia patients (training dataset, n = 379; validation dataset, n = 131; testing dataset, n = 40). Key radiomics features extracted from chest CT images were selected to build a radiomics signature using least absolute shrinkage and selection operator (LASSO) regression. Clinical and clinico-radiomics combined models were constructed. The combined model was further validated in the viral pneumonia cohort, and compared with performance of two radiologists with CO-RADS. The diagnostic performance was assessed by receiver operating characteristics curve (ROC) analysis, calibration curve, and decision curve analysis (DCA).
Eight radiomics features and 5 clinical variables were selected to construct the combined radiomics model, which outperformed the clinical model in diagnosing COVID-19 pneumonia with an area under the ROC (AUC) of 0.98 and good calibration in the validation cohort. The combined model also performed better in distinguishing COVID-19 from other viral pneumonia with an AUC of 0.93 compared with 0.75 (P = 0.03) for clinical model, and 0.69 (P = 0.008) or 0.82 (P = 0.15) for two trained radiologists using CO-RADS. The sensitivity and specificity of the combined model can be achieved to 0.85 and 0.90. The DCA confirmed the clinical utility of the combined model. An easy-to-use open-source diagnostic tool was developed using the combined model.
The combined radiomics model outperformed clinical model and CO-RADS for diagnosing COVID-19 pneumonia, which can facilitate more rapid and accurate detection.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
This is a list of supplementary files associated with this preprint. Click to download.
Radiomics feature selection using LASSO logistic regression model. (a) The hyper parameter (λ) was selected via ten-fold cross-validation based on minimum criteria. Log (λ) is plotted on the x-axis, and binomial deviance is plotted on the y-axis. The dotted vertical lines indicate optimal values determined using the minimum criteria and one standard error of the minimum criteria (1-SE). log (λ)=-6.71. (b) LASSO coefficient profiles of the radiomics features. Coefficient profiles are plotted against log (λ). The optimal 8 non-zero coefficients were generated at the value selected using ten-fold cross-validation.
The selected radiomics features and their coefficients.
Calibration curves of the clinical and combined radiomics model in the training cohort (a) and validation cohort (b).
Posted 22 Sep, 2020
On 07 Jan, 2021
Received 05 Dec, 2020
On 05 Dec, 2020
On 30 Nov, 2020
Received 30 Nov, 2020
On 12 Nov, 2020
Invitations sent on 27 Sep, 2020
On 25 Sep, 2020
On 24 Sep, 2020
On 16 Sep, 2020
On 12 Sep, 2020
CT radiomics facilitates more accurate diagnosis of COVID-19 pneumonia: compared with CO-RADS
Posted 22 Sep, 2020
On 07 Jan, 2021
Received 05 Dec, 2020
On 05 Dec, 2020
On 30 Nov, 2020
Received 30 Nov, 2020
On 12 Nov, 2020
Invitations sent on 27 Sep, 2020
On 25 Sep, 2020
On 24 Sep, 2020
On 16 Sep, 2020
On 12 Sep, 2020
Limited data was available for rapid and accurate detection of COVID-19 using CT-based machine learning model. This study aimed to investigate the value of chest CT radiomics for diagnosing COVID-19 pneumonia compared with clinical model and COVID-19 reporting and data system (CO-RADS), and develop an open-source diagnostic tool with the constructed radiomics model.
This study enrolled 115 laboratory-confirmed COVID-19 and 435 non-COVID-19 pneunomia patients (training dataset, n = 379; validation dataset, n = 131; testing dataset, n = 40). Key radiomics features extracted from chest CT images were selected to build a radiomics signature using least absolute shrinkage and selection operator (LASSO) regression. Clinical and clinico-radiomics combined models were constructed. The combined model was further validated in the viral pneumonia cohort, and compared with performance of two radiologists with CO-RADS. The diagnostic performance was assessed by receiver operating characteristics curve (ROC) analysis, calibration curve, and decision curve analysis (DCA).
Eight radiomics features and 5 clinical variables were selected to construct the combined radiomics model, which outperformed the clinical model in diagnosing COVID-19 pneumonia with an area under the ROC (AUC) of 0.98 and good calibration in the validation cohort. The combined model also performed better in distinguishing COVID-19 from other viral pneumonia with an AUC of 0.93 compared with 0.75 (P = 0.03) for clinical model, and 0.69 (P = 0.008) or 0.82 (P = 0.15) for two trained radiologists using CO-RADS. The sensitivity and specificity of the combined model can be achieved to 0.85 and 0.90. The DCA confirmed the clinical utility of the combined model. An easy-to-use open-source diagnostic tool was developed using the combined model.
The combined radiomics model outperformed clinical model and CO-RADS for diagnosing COVID-19 pneumonia, which can facilitate more rapid and accurate detection.
Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6