U-Net + FTL

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Medical Image SegmentationonISIC 2018
mean Dice· 2018-10-18
0.829
best: 0.9253 (Polar Res-U-Net++)
A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation arXiv:1810.07842
Medical Image SegmentationonBUS 2017 Dataset B
Dice Score· 2018-10-18
0.669
best: 0.804 (Attn U-Net + Multi-Input + FTL)
A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation arXiv:1810.07842