Table 1 Evaluation on the test set of the BRATS 2015 (110 testing cases), with comparisons with the most recent results reported in [1, 2]
From: Brain SegNet: 3D local refinement network for brain lesion segmentation
Dice | Specificity | Sensitivity | |||||||
|---|---|---|---|---|---|---|---|---|---|
Whole | Core | Enh. | Whole | Core | Enh. | Whole | Core | Enh. | |
Zhao et. al.[1] + CRF | 82.0 | 72.0 | 62.0 | 84.0 | 78.0 | 60.0 | 83.0 | 73.0 | 69.0 |
Zhao et. al.+3D CRF [1] | 84.0 | 73.0 | 62.0 | 89.0 | 76.0 | 63.0 | 82.0 | 76.0 | 67.0 |
DeepMedic [2] | 83.6 | 67.4 | 62.9 | 82.3 | 84.6 | 64.0 | 88.5 | 61.6 | 65.6 |
DeepMedic+CRF [2] | 84.7 | 67.0 | 62.9 | 85.0 | 84.8 | 63.4 | 87.6 | 60.7 | 66.2 |
Brain SegNet_no_FL | 85.0 | 69.0 | 64.0 | 88.0 | 86.0 | 63.0 | 85.0 | 63.0 | 69.0 |
Brain SegNet | 86.0 | 72.0 | 64.0 | 87.0 | 85.0 | 64.0 | 87.0 | 68.0 | 66.0 |