ASLseg: Adapting SAM in the Loop for Semi-supervised Liver Tumor Segmentation
This work addresses the challenge of limited annotated data for liver tumor segmentation, which is crucial for medical diagnosis and planning, though it appears incremental in adapting existing models.
The paper tackled liver tumor segmentation by adapting the Segment Anything Model (SAM) into a semi-supervised learning framework, achieving overwhelming performance on the LiTS dataset.
Liver tumor segmentation is essential for computer-aided diagnosis, surgical planning, and prognosis evaluation. However, obtaining and maintaining a large-scale dataset with dense annotations is challenging. Semi-Supervised Learning (SSL) is a common technique to address these challenges. Recently, Segment Anything Model (SAM) has shown promising performance in some medical image segmentation tasks, but it performs poorly for liver tumor segmentation. In this paper, we propose a novel semi-supervised framework, named ASLseg, which can effectively adapt the SAM to the SSL setting and combine both domain-specific and general knowledge of liver tumors. Specifically, the segmentation model trained with a specific SSL paradigm provides the generated pseudo-labels as prompts to the fine-tuned SAM. An adaptation network is then used to refine the SAM-predictions and generate higher-quality pseudo-labels. Finally, the reliable pseudo-labels are selected to expand the labeled set for iterative training. Extensive experiments on the LiTS dataset demonstrate overwhelming performance of our ASLseg.