用少量标注数据实现精准医学图像分割，靠的是预训练模型+迭代优化。
SSL-MedSAM2: A Semi-supervised Medical Image Segmentation Framework Powered by Few-shot Learning of SAM2
- 基于SAM2的零样本分支生成伪标签，减少人工标注依赖。
- 在肝部分割任务中，Dice达0.9710（GED4）和0.9648（T1 MRI）。
- 适合标注资源少但要求高精度的临床医学图像分析场景。
尽管深度学习在医学图像分割中取得成功，但多数最先进方法依赖大规模标注数据进行全监督训练。然而医学图像标注耗时长，限制了其临床应用。半监督学习（SSL）成为减少标注成本的可行策略。本文提出新型SSL框架SSL-MedSAM2，包含基于预训练大模型SAM2的无训练少样本分支TFFS-MedSAM2用于生成伪标签，以及基于nnUNet的迭代全监督学习分支FSL-nnUNet用于伪标签精炼。在MICCAI2025挑战赛CARE-LiSeg（肝脏分割）上的结果表明，该方法性能显著优于其他方法：在GED4和T1 MRI测试集上平均Dice分数分别为0.9710和0.9648，豪斯多夫距离分别为20.07和21.97。代码已开源：https://github.com/naisops/SSL-MedSAM2/tree/main。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。