Radiomics Signatures of Computed Tomography Imaging for Predicting Risk Categorization and Clinical Stage of Thymomas

<p>The top 10 features contributed to radiomics signatures based on NECT images (a) and CECT images (b) weighted by standardized regression coefficients according to LASSO logistic regression model to differentiate high risk thymomas from low risk thymomas.</p>

BioMed Research International

fig3

Figure 3

Figure 3: Radiomics Signatures of Computed Tomography Imaging for Predicting Risk Categorization and Clinical Stage of Thymomas 