Clinical Data-CT Radiomics-Based Model for Predicting Prognosis of Patients with Gastrointestinal Pancreatic Neuroendocrine Neoplasms (GP-NENs)

<div>Schematic diagram of radiomics texture feature extraction based on R Studio software (Lasso regression method), a total of 6 groups of available texture data are extracted; (a) the method of k-fold cross-verification by adjusting different parameters lambda (<i>λ</i>) filter out the characteristic parameter groups with the best performance. (b) The compression diagram of k-fold cross-validation method for screening characteristic parameters. The vertical black line is the best lambda value when the model performance is optimized. Notes: Radiomics scoring (Radscore) refers to the comprehensive expression and scoring of the extracted valuable radiomics texture parameters.</div>

Computational and Mathematical Methods in Medicine

fig4

Figure 4

Figure 4: Clinical Data-CT Radiomics-Based Model for Predicting Prognosis of Patients with Gastrointestinal Pancreatic Neuroendocrine Neoplasms (GP-NENs) 

Figure 4 | Clinical Data-CT Radiomics-Based Model for Predicting Prognosis of Patients with Gastrointestinal Pancreatic Neuroendocrine Neoplasms (GP-NENs) 