Style Augmentation improves Medical Image Segmentation
This work addresses texture over-fitting in medical image segmentation, which is an incremental improvement for the medical imaging domain.
The paper tackled the problem of texture bias in medical image segmentation by applying style augmentation, which improved segmentation performance on the MoNuSeg dataset.
Due to the limitation of available labeled data, medical image segmentation is a challenging task for deep learning. Traditional data augmentation techniques have been shown to improve segmentation network performances by optimizing the usage of few training examples. However, current augmentation approaches for segmentation do not tackle the strong texture bias of convolutional neural networks, observed in several studies. This work shows on the MoNuSeg dataset that style augmentation, which is already used in classification tasks, helps reducing texture over-fitting and improves segmentation performance.