Boundary-aware Information Maximization for Self-supervised Medical Image Segmentation
This work addresses the problem of limited labeled data for medical image segmentation, offering an incremental improvement over existing unsupervised methods.
The paper tackles the challenge of unsupervised pre-training for medical image segmentation by proposing a framework that avoids contrastive learning drawbacks, using mutual information maximization and boundary-aware learning, and shows effectiveness on two benchmark datasets with few annotated images.
Unsupervised pre-training has been proven as an effective approach to boost various downstream tasks given limited labeled data. Among various methods, contrastive learning learns a discriminative representation by constructing positive and negative pairs. However, it is not trivial to build reasonable pairs for a segmentation task in an unsupervised way. In this work, we propose a novel unsupervised pre-training framework that avoids the drawback of contrastive learning. Our framework consists of two principles: unsupervised over-segmentation as a pre-train task using mutual information maximization and boundary-aware preserving learning. Experimental results on two benchmark medical segmentation datasets reveal our method's effectiveness in improving segmentation performance when few annotated images are available.