Table 2 10 most important extracted radiomics features, ordered by importance
From: Tumor classification of gastrointestinal liver metastases using CT-based radiomics and deep learning
Feature | Permutation importance | |
|---|---|---|
1 | original_firstorder_90Percentile | 0.053969 |
2 | original_firstorder_Mean | 0.048406 |
3 | original_glszm_GrayLevelNonUniformityNormalized | 0.040987 |
4 | original_glcm_Correlation | 0.038470 |
5 | original_ngtdm_Complexity | 0.037156 |
6 | original_glszm_GrayLevelVariance | 0.036443 |
7 | original_glcm_Imc1 | 0.036336 |
8 | original_firstorder_10Percentile | 0.035691 |
9 | original_shape_Flatness | 0.035509 |
10 | original_gldm_HighGrayLevelEmphasis | 0.034498 |