Skip to main content

Table 3 Diagnostic performances of the radiomics model for differentiating pseudoprogression from true progression versus the radiologists’ assessment

From: Differentiation of Pseudoprogression from True Progressionin Glioblastoma Patients after Standard Treatment: A Machine Learning Strategy Combinedwith Radiomics Features from T1-weighted Contrast-enhanced Imaging

  ACC Sensitivity Specificity
Radiomics 72.78%(95% CI: 0.45,0.91) 78.36%(95% CI: 0.56,1.00) 61.33%(95% CI: 0.20,0.82)
Radiologist 1 66.23%(95% CI: 0.55,0.76) 61.50%(95% CI: 0.43,0.78) 68.62%(95% CI: 0.55,0.80)
Radiologist 2 55.84%(95% CI: 0.45,0.66) 69.25%(95% CI: 0.50,0.84) 49.13%(95% CI: 0.36,0.62)
Radiologist 3 55.84%(95% CI: 0.45,0.66) 69.23%(95% CI: 0.50,0.84) 47.06%(95% CI: 0.34,0.61)