SemiSAM: Enhancing Semi-Supervised Medical Image Segmentation via SAM-Assisted Consistency Regularization

TL;DR

This paper introduces SemiSAM, a strategy that leverages the Segment Anything Model (SAM) to improve semi-supervised medical image segmentation, especially under scenarios with very limited labeled data, by generating pseudo-labels for enhanced learning.

Contribution

The paper proposes a novel SAM-assisted approach that enhances semi-supervised segmentation by using SAM-generated pseudo-labels, demonstrating significant performance gains with minimal labeled data.

Findings

SemiSAM improves segmentation accuracy with few labeled images.

The method is effective as a plug-and-play enhancement.

Significant performance gains over existing semi-supervised methods.

Abstract

Semi-supervised learning has attracted much attention due to its less dependence on acquiring abundant annotations from experts compared to fully supervised methods, which is especially important for medical image segmentation which typically requires intensive pixel/voxel-wise labeling by domain experts. Although semi-supervised methods can improve the performance by utilizing unlabeled data, there are still gaps between fully supervised methods under extremely limited annotation scenarios. In this paper, we propose a simple yet efficient strategy to explore the usage of the Segment Anything Model (SAM) for enhancing semi-supervised medical image segmentation. Concretely, the segmentation model trained with domain knowledge provides information for localization and generating input prompts to the SAM. Then the generated pseudo-labels of SAM are utilized as additional supervision to assist in the learning procedure of the semi-supervised framework. Extensive experiments demonstrate that SemiSAM significantly improves the performance of existing semi-supervised frameworks when only one or a few labeled images are available and shows strong efficiency as a plug-and-play strategy for semi-supervised medical image segmentation.