SSL-MedSAM2: A Semi-supervised Medical Image Segmentation Framework Powered by Few-shot Learning of SAM2
This work addresses the high annotation cost in medical imaging for clinicians, though it appears incremental as it builds on existing foundation models and SSL techniques.
The authors tackled the problem of medical image segmentation with limited annotations by proposing SSL-MedSAM2, a semi-supervised framework that combines a training-free few-shot learning branch based on SAM2 for pseudo-label generation and an iterative fully-supervised branch based on nnUNet for refinement. The results on the CARE-LiSeg liver segmentation challenge showed average dice scores of 0.9710 and 0.9648 on GED4 and T1 MRI test sets, respectively.
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.