A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation

18 Oct 2018Nabila AbrahamNaimul Mefraz Khan

We propose a generalized focal loss function based on the Tversky index to address the issue of data imbalance in medical image segmentation. Compared to the commonly used Dice loss, our loss function achieves a better trade off between precision and recall when training on small structures such as lesions... (read more)

PDF Abstract

Evaluation Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK COMPARE
Lesion Segmentation BUS 2017 Dataset B Attn U-Net + Multi-Input + FTL Dice Score 0.804 # 1
Lesion Segmentation BUS 2017 Dataset B Attn U-Net + DL Dice Score 0.615 # 3
Lesion Segmentation BUS 2017 Dataset B U-Net + FTL Dice Score 0.669 # 2
Lesion Segmentation ISIC 2018 U-Net + FTL Dice Score 0.829 # 2
Lesion Segmentation ISIC 2018 Attn U-Net + Multi-Input + FTL Dice Score 0.856 # 1
Lesion Segmentation ISIC 2018 Attn U-Net + DL Dice Score 0.806 # 3