A Novel Focal Tversky loss function with improved Attention U-Net for lesion segmentation
This addresses the problem of segmenting small lesions in medical images for healthcare applications, representing an incremental advance with specific gains.
The paper tackles data imbalance in medical image segmentation by proposing a novel focal Tversky loss function, achieving improvements of 25.7% and 3.6% in segmentation accuracy on two datasets compared to standard U-Net.
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. To evaluate our loss function, we improve the attention U-Net model by incorporating an image pyramid to preserve contextual features. We experiment on the BUS 2017 dataset and ISIC 2018 dataset where lesions occupy 4.84% and 21.4% of the images area and improve segmentation accuracy when compared to the standard U-Net by 25.7% and 3.6%, respectively.