SSL-MedSAM2: A Semi-supervised Medical Image Segmentation Framework Powered by Few-shot Learning of SAM2

TL;DR

SSL-MedSAM2 is a semi-supervised medical image segmentation framework that leverages few-shot learning with the pretrained SAM2 model and iterative refinement, achieving high accuracy with limited annotations.

Contribution

It introduces a novel semi-supervised framework combining a training-free few-shot SAM2-based branch with an iterative fully-supervised branch for improved segmentation with limited data.

Findings

Achieved Dice scores of 0.9710 and 0.9648 on MICCAI2025 challenge datasets.

Outperformed other methods in liver segmentation tasks.

Demonstrated effective pseudo label generation and refinement.

Abstract

Despite the success of deep learning based models in medical image segmentation, most state-of-the-art (SOTA) methods perform fully-supervised learning, which commonly rely on large scale annotated training datasets. However, medical image annotation is highly time-consuming, hindering its clinical applications. Semi-supervised learning (SSL) has been emerged as an appealing strategy in training with limited annotations, largely reducing the labelling cost. We propose a novel SSL framework SSL-MedSAM2, which contains a training-free few-shot learning branch TFFS-MedSAM2 based on the pretrained large foundation model Segment Anything Model 2 (SAM2) for pseudo label generation, and an iterative fully-supervised learning branch FSL-nnUNet based on nnUNet for pseudo label refinement. The results on MICCAI2025 challenge CARE-LiSeg (Liver Segmentation) demonstrate an outstanding performance of SSL-MedSAM2 among other methods. The average dice scores on the test set in GED4 and T1 MRI are 0.9710 and 0.9648 respectively, and the Hausdorff distances are 20.07 and 21.97 respectively. The code is available via https://github.com/naisops/SSL-MedSAM2/tree/main.