Table 2.

Ablation studies of our segmentation network in terms of dice score. Best results are shown in bold. Note: we did not compute confidence intervals on these scores as they are obtained from a very large set of CT voxels.

Model	Lung segmentation	Lobe segmentation
Baseline Tiramisu [31]	89.41 ± 0.45	77.97 ± 0.31
Baseline + Res-SE	91.78 ± 0.52	80.12 ± 0.28
Baseline + C-LSTM	91.49 ± 0.57	79.47 ± 0.38
Baseline + Res-SE + C-LSTM	94.01 ± 0.52	83.05 ± 0.27