Skip to main content
. 2023 Jun 20;36(5):2075–2087. doi: 10.1007/s10278-023-00860-7

Table 2.

DSC between models trained on fixed, limited subset of inputs versus dropout model

MRI sequences Enhancing tumor (ET) Tumor core (TC) Whole tumor (WT)
Flair T1 T1Gd T2 Fixed input Dropout Fixed input Dropout Fixed input Dropout
0.822 ± 0.198 0.748 ± 0.222 0.853 ± 0.203 0.771 ± 0.227 0.839 ± 0.150 0.762 ± 0.157
0.829 ± 0.169 0.803 ± 0.186 0.861 ± 0.190 0.844 ± 0.177 0.896 ± 0.097 0.879 ± 0.106

T1Gd p-values comparing ET, TC, and WT, respectively:<  0.001, 0.002,<  0.001. T1Gd, T2 p-values: 0.017, 0.405, 0.017