Skip to main content

Table 2 Results of each algorithm model after NRS dimensionality reduction

From: Radiomics models for diagnosing microvascular invasion in hepatocellular carcinoma: which model is the best model?

  TP FN FP TN Accuracy Sensitivity Specificity
NRS + DT 21 6 11 20 70.69% 77.78% 64.52%
NRS + Bayes 17 11 7 23 68.97% 60.71% 76.67%
NRS + BPnet 21 5 11 21 72.41% 80.77% 65.63%
NRS + K-NN 18 10 6 24 72.41% 64.29% 80.00%
NRS + SVM 23 5 6 24 70.69% 82.14% 80.00%
NRS + RF 19 7 5 27 79.31% 73.08% 84.38%
NRS + GBDT 23 5 7 23 79.31% 82.14% 76.67%
  1. *FN False Negative, FP False Positive, TN True Negative, TP True Positive