Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Yichi Zhang, Jin Yang, Yuchen Liu, Yuan Cheng, Yuan Qi

TL;DR

This paper proposes a simple yet efficient strategy to explore the usage of the Segment Anything Model (SAM) for enhancing semi-supervised medical image segmentation and shows strong efficiency as a plug-and-play strategy for semi-supervised medical image segmentation.

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.

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

TL;DR

This paper proposes a simple yet efficient strategy to explore the usage of the Segment Anything Model (SAM) for enhancing semi-supervised medical image segmentation and shows strong efficiency as a plug-and-play strategy for semi-supervised medical image segmentation.

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.
Paper Structure (8 sections, 3 equations, 2 figures, 2 tables)

This paper contains 8 sections, 3 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Methodology
  3. Semi-Supervised Framework
  4. SAM-Assisted Consistency Regularization
  5. Experiments
  6. Dataset and Implementation Details
  7. Comparison with Other Segmentation Methods
  8. Conclusion and Discussion

Figures (2)

  • Figure 1: The structure of our proposed SAM-Assisted Consistency Regularization framework for semi-supervised medical image segmentation. The illustration in the figure is SemiSAM-MT based on the mean teacher framework tarvainen2017mean.
  • Figure 2: Visual comparison of 3D reconstruction results and 2D segmentation results of semi-supervised mean teacher frameworks with (w/) and without (w/o) SemiSAM on LA dataset.