Segment Anything Model for Semi-supervised Medical Image Segmentation via Selecting Reliable Pseudo-labels

Semi-supervised learning (SSL) has become a hot topic due to its less dependence on annotated data compared to fully supervised methods. This advantage becomes more evident in the field of medical imaging, where acquiring labeled data is challenging. Generating pseudo-labels for unlabeled images is one of the most classic and intuitive methods in semi-supervised segmentation. However, this method may also produce unreliable pseudo-labels that can provide incorrect guidance to the model and impair its performance. The reliability of pseudo-labels is difficult to evaluate due to the lack of ground truth labels for unlabeled images. In this paper, a SSL framework was presented, in which we proposed a simple but effective strategy to select reliable pseudo-labels by leveraging the Segment Anything Model (SAM) for segmentation. Concretely, the SSL model trained with domain knowledge provides the generated pseudo-labels as prompts to the SAM. Reliable pseudo-labels usually make SAM to conduct predictions consistent with the semi-supervised segmentation model. Based on this result, the reliable pseudo-labels are selected to further boost the existing semi-supervised learning methods. The experimental results show that the proposed strategy effectively improves the performance of different algorithms in the semi-supervised scenarios. On the publicly available ACDC dataset, the proposed method achieves 6.84% and 10.76% improvement over the advanced two baselines respectively on 5% of labeled data. The extended experiments on pseudo-labels verified that the quality of the selected reliable pseudo-labels by the proposed strategy is superior to that of the unreliable pseudo-labels. This study may provide a new avenue for SSL medical image segmentation.