From: DCAU-Net: dense convolutional attention U-Net for segmentation of intracranial aneurysm images
Model | Dice | Sensitivity | Specificity | Precision |
---|---|---|---|---|
  MIP + 2D CNN | 0.6642 | 0.7201 | 0.9993 | 0.5865 |
  HeadXNet [29] | 0.6462 | 0.7473 | 0.9994 | 0.6771 |
  DeepMedic [32] | 0.7421 | 0.7247 | 0.9997 | 0.7521 |
  GLIA-Net [33] | 0.7443 | 0.7195 | 0.9997 | 0.7615 |
  DAResUNet [30] | 0.7376 | 0.7014 | 0.9995 | 0.7553 |
  3D U-Net [37] | 0.6544 | 0.7181 | 0.9993 | 0.6036 |
  Ours | 0.7455 | 0.7881 | 0.9996 | 0.7881 |