A Clinical Radiomics Nomogram Was Developed by Integrating Radiomics Signatures and Clinical Variables to Distinguish High-Grade ccRCC from Type 2 pRCC

<div>Radiomics features were selected using a minor absolute shrinkage and selection operator (LASSO) regression model. (a). The LASSO model’s tuning parameter (<i>λ</i>) was determined using a minimum criterion 10-fold cross-validation criterion. The dotted vertical lines indicate the optimal values of the LASSO tuning parameter (<i>λ</i>), and a value <i>λ</i> of 0.082 with ln (<i>λ</i>) = −2.501 was chosen. (b). LASSO coefficient of the 427 radiomics features. A coefficient profile plot was generated versus the selected ln (<i>λ</i>) value using 10-fold cross-validation; the vertical line was plotted with eight chosen radiomics features.</div>

Journal of Oncology

fig3

Figure 3

Figure 3: A Clinical Radiomics Nomogram Was Developed by Integrating Radiomics Signatures and Clinical Variables to Distinguish High-Grade ccRCC from Type 2 pRCC 

Figure 3 | A Clinical Radiomics Nomogram Was Developed by Integrating Radiomics Signatures and Clinical Variables to Distinguish High-Grade ccRCC from Type 2 pRCC 